{ "maintainer": "Probity", "protocolVersion": "0.1", "records": [ { "answerExposure": "Implementation, demo and retained expected outcomes were available to the atlas runner; not an answer-blind replication", "artifacts": [ { "path": "../experiments/observer-admission/source-pins.json", "sha256": "2ffd87708075c0dd7b230336fdfd72c93bd2fbf3eded37ee632f75ad735418ec" }, { "path": "../experiments/observer-admission/recorded.json", "sha256": "c8d9675ac0ff5fccd6545b6e6bb6ab5ac3bcc14b313d7087b253bab1f7f0f1eb" }, { "path": "../experiments/observer-admission/provenance.json", "sha256": "8ea7581c5555e135963fc1419979157360acc724be7c17c2784136e29ce691f0" } ], "atlasRevision": "91a0759e459acee8355e2f9aba34f8e80d19e038", "claimResults": [ { "claim": "consumer-authority-binding", "expectedValue": "packet authority differs from consumer policy", "recordedField": "/outcomes/authorityRefusal", "result": "pass" }, { "claim": "durable-consumer-admission", "expectedValue": "admitted", "recordedField": "/outcomes/admissionStatus", "result": "pass" }, { "claim": "persisted-replay-refusal", "expectedValue": "interval was already admitted by this consumer", "recordedField": "/outcomes/replayRefusal", "result": "pass" }, { "claim": "signed-claim-tamper-refusal", "expectedValue": "signature does not verify under the pinned key", "recordedField": "/outcomes/tamperRefusal", "result": "pass" }, { "claim": "independent-custody", "result": "not-exercised" }, { "claim": "external-host-ci-adoption", "result": "not-exercised" }, { "claim": "unmediated-effect-capture", "result": "not-exercised" } ], "contract": "https://github.com/probityai/agent-evidence-observer/blob/8562c25fb7ec97596ea9d0297c495340298914b6/docs/CONSUMER-ADMISSION.md", "comparisonOrder": "Retrospective retained-fixture comparison; not a result frozen before expected-answer comparison", "evidenceClaim": "verifier-behavior-on-author-fixture", "experiment": "../experiments.html#observer-consumer-admission", "id": "E6-observer-admission", "limits": [ "One declared broker file write and one local consumer admission", "No live-agent or production-isolation measurement", "No independently operated witness or consumer", "Consumer-state rollback can erase replay protection", "No exactly-once downstream-effect claim" ], "observerRevision": "8562c25fb7ec97596ea9d0297c495340298914b6", "provenance": "../experiments/observer-admission/provenance.json", "report": "../experiments/observer-admission/recorded.json", "reviewState": "retained-measured-record", "roles": { "atlasReplay": "author-produced", "evidenceVantage": "artifact", "fixtureOperator": "same-operator-fixture", "independentOperation": "not-established", "witnessScope": "PEER" } }, { "id": "jep-core07-2026-10-02", "readerRevision": "dd76a53fd553b33a16811fae80b4a99317b3b085", "contract": "https://github.com/probityai/agent-evidence-vectors/blob/4f344209c8ea65f60bab0f51747ae4f80346181d/interop/jep-core07-reader/PROTOCOL.md", "report": "../experiments/jep-core07-2026-10-02/report.json", "provenance": "../experiments/jep-core07-2026-10-02/provenance.json", "reviewState": "submitted-awaiting-producer-response", "evidenceClaim": "verifier-behavior-on-public-producer-fixtures", "roles": { "readerAuthor": "Probity", "runner": "Probity-owned GitHub Actions", "producer": "JEP", "independentEffectCustody": "not-established" }, "answerExposure": "Published expected outcomes were available before implementation; not answer-blind.", "comparisonOrder": "Actual per-case outputs retained before comparison in memory; raw output and comparison published together, not separate revisions.", "limits": [ "Pinned manifest coverage only, not complete JEP Core coverage.", "Acceptance effects are synthetic local SQLite rows.", "No power-loss or distributed failover experiment." ], "claimResults": [ { "claim": "validation-assertions-match-pinned-expectations", "result": "pass", "recordedField": "/summary/validation", "expectedValue": { "total": 25, "passed": 25 } }, { "claim": "producer-assertions-match-pinned-expectations", "result": "pass", "recordedField": "/summary/producer", "expectedValue": { "total": 4, "passed": 4 } }, { "claim": "acceptance-assertions-match-pinned-expectations", "result": "pass", "recordedField": "/summary/acceptance", "expectedValue": { "total": 8, "passed": 8 } }, { "claim": "external-host-ci-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/jep-core07-2026-10-02/original-artifact.zip", "sha256": "2d6271bf522c2975fc5efc6af59c739df5ae777a39f4893025de756d6137346c" }, { "path": "../experiments/jep-core07-2026-10-02/provenance.json", "sha256": "1526f25715de06be9432df0a0097fa78f77c4d4bba03cea55ff89341be368331" }, { "path": "../experiments/jep-core07-2026-10-02/report.json", "sha256": "4f92e1bc30c8ff6c8f89819d9fbcbd7ef42dce0d46f40712c095f10b7d9ca574" } ], "producerSubmission": "https://github.com/hjs-spec/jep-core/issues/47" }, { "id": "remora-e7-2026-10-02", "readerRevision": "a0b89170fd671be2314be6079acccdebdf07a950", "contract": "https://github.com/darklordVirtual/REMORA-research/tree/e4fe474f488c3047b346abb01cbfd77ab447ad69/artifacts/interop/runtime-surface-e7-v0.1", "report": "../experiments/remora-e7-2026-10-02/report.json", "provenance": "../experiments/remora-e7-2026-10-02/provenance.json", "reviewState": "producer-review-open", "evidenceClaim": "verifier-behavior-on-public-producer-fixtures", "roles": { "readerAuthor": "Probity", "runner": "Probity-owned GitHub Actions", "producer": "REMORA", "independentEffectCustody": "not-established" }, "answerExposure": "Published expected outcomes were available before implementation; not answer-blind. REMORA reference-verifier text was also exposed during lint diagnostics after implementation.", "comparisonOrder": "Actual per-case outputs retained before comparison in memory; raw output and comparison published together, not separate revisions.", "limits": [ "Native INDEPENDENT means the external operator and separate implementation satisfy REMORA package criteria; it establishes no independent effect custody.", "Global runtime_capability_surface_completeness remains NOT_ESTABLISHED.", "Producer review is open; it does not establish producer acceptance, final verification or CI adoption." ], "claimResults": [ { "claim": "valid_reference_surface-matches-native-fixture-outcome", "result": "pass", "recordedField": "/results/0/claim_result", "expectedValue": "ESTABLISHED" }, { "claim": "undeclared_tool_invocation_surface-matches-native-fixture-outcome", "result": "pass", "recordedField": "/results/1/claim_result", "expectedValue": "CONTRADICTED" }, { "claim": "runtime_identity_changed-matches-native-fixture-outcome", "result": "pass", "recordedField": "/results/2/claim_result", "expectedValue": "NOT_ESTABLISHED" }, { "claim": "observation_coverage_incomplete-matches-native-fixture-outcome", "result": "pass", "recordedField": "/results/3/claim_result", "expectedValue": "NOT_ESTABLISHED" }, { "claim": "alternative_effect_path_observed-matches-native-fixture-outcome", "result": "pass", "recordedField": "/results/4/claim_result", "expectedValue": "CONTRADICTED" }, { "claim": "global-runtime-capability-surface-completeness", "result": "not-exercised" }, { "claim": "external-host-ci-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/remora-e7-2026-10-02/external-run-record-v1.json", "sha256": "24731968cb599c52f000b4584ed41a5b977637fd9b00f5756f8f8e2c4566fc48" }, { "path": "../experiments/remora-e7-2026-10-02/original-artifact.zip", "sha256": "079a27b72aebb3252546233a5b9a1c3a7400c6f19e2251773520db0350125e1f" }, { "path": "../experiments/remora-e7-2026-10-02/provenance.json", "sha256": "b7906952ba8bcccf3a0b9d2ddf7b4c8628d04a3498f61ed7ccf49f49e6e236a8" }, { "path": "../experiments/remora-e7-2026-10-02/report.json", "sha256": "8cab9f748fb17ba3bd2c20ca1896b1b50be96120e53a1e6c5394aa404a26bca1" } ], "producerSubmission": "https://github.com/darklordVirtual/REMORA-research/issues/707#issuecomment-5957358281", "producerReviewStartedAt": "2026-10-02T17:04:37Z", "producerReviewEndsAt": "2026-10-09T17:04:37Z" }, { "id": "langgraph-durable-2026-10-02", "atlasRevision": "65d502b9e751aa11ab6936f4eeaa544eebc2a00f", "sourceRevision": "90cd62c0ee926b456aa9aada3537f36ee5f17cd3", "readerRevision": "90cd62c0ee926b456aa9aada3537f36ee5f17cd3", "report": "../experiments/langgraph-durable-2026-10-02/report.json", "provenance": "../experiments/langgraph-durable-2026-10-02/provenance.json", "contract": "https://github.com/probityai/agent-evidence-observer/tree/90cd62c0ee926b456aa9aada3537f36ee5f17cd3/interop/langgraph-ticket-2026-10-02", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-native-framework-control", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison published together; not separate raw-result-first revisions.", "limits": [ "Graph-worker hard exits/reopened SQLite checkpoints only; target process remains alive.", "No target-process restart, host power loss, issuer authentication, general exactly-once guarantee or independent custody." ], "claimResults": [ { "claim": "bounded-six-case-population", "result": "pass", "recordedField": "/plannedAttempts", "expectedValue": 6 }, { "claim": "reader-reconstructed-native-record", "result": "pass", "recordedField": "/status", "expectedValue": "verified" }, { "claim": "crash-after-effect-recovers-at-revision-one", "result": "pass", "recordedField": "/records/2", "expectedValue": { "attemptId": "crash-after-effect", "recoveryOutcome": "recovered-durable-checkpoint", "effectOutcome": "verified-local-ticket-update", "httpCalls": 2, "nativeRevision": 1, "workerExitCodes": [ 74, 0 ] } }, { "claim": "pending-intent-no-automatic-replay", "result": "pass", "recordedField": "/records/3", "expectedValue": { "attemptId": "restart-pending", "recoveryOutcome": "recovered-durable-checkpoint", "effectOutcome": "incomplete-no-automatic-replay", "httpCalls": 2, "nativeRevision": 0, "workerExitCodes": [ 73, 0 ] } }, { "claim": "missing-checkpoint-refusal", "result": "pass", "recordedField": "/records/4", "expectedValue": { "attemptId": "missing-checkpoint", "recoveryOutcome": "refused-missing-checkpoint", "effectOutcome": "refused-no-local-row", "httpCalls": 0, "nativeRevision": 0, "workerExitCodes": [ 73, 0 ] } }, { "claim": "wrong-thread-refusal", "result": "pass", "recordedField": "/records/5", "expectedValue": { "attemptId": "wrong-thread", "recoveryOutcome": "refused-missing-checkpoint", "effectOutcome": "refused-no-local-row", "httpCalls": 0, "nativeRevision": 0, "workerExitCodes": [ 73, 0 ] } }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/langgraph-durable-2026-10-02/original-artifact.zip", "sha256": "53226e9a77526c67c759e582b9f40b4512fff78ca64fad99bc99d2e5a4d97ed8" }, { "path": "../experiments/langgraph-durable-2026-10-02/provenance.json", "sha256": "c92f73156c57a0d41c61114c8ca3c36c800904eb7d09a88257f98dcaa953cd9d" }, { "path": "../experiments/langgraph-durable-2026-10-02/report.json", "sha256": "4fe8ff3fbffe96508553433862120c2184752e85cbff22f64b4e23753b50f8c6" } ] }, { "id": "pydantic-failure-2026-10-02", "atlasRevision": "65d502b9e751aa11ab6936f4eeaa544eebc2a00f", "sourceRevision": "afda549c3f20f8e7b031275c06558a50bf20726e", "readerRevision": "afda549c3f20f8e7b031275c06558a50bf20726e", "report": "../experiments/pydantic-failure-2026-10-02/report.json", "provenance": "../experiments/pydantic-failure-2026-10-02/provenance.json", "contract": "https://github.com/probityai/agent-evidence-observer/tree/afda549c3f20f8e7b031275c06558a50bf20726e/interop/pydantic-ai-native-2026-10-02", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-native-framework-control", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison published together; not separate raw-result-first revisions.", "limits": [ "Real Pydantic framework with scripted FunctionModel; no model-quality or real-provider inference measurement.", "Selected loopback ticket effects; no caller authentication, outside adoption or independent custody." ], "claimResults": [ { "claim": "bounded-seven-case-population", "result": "pass", "recordedField": "/plannedAttempts", "expectedValue": 7 }, { "claim": "reader-reconstructed-native-record", "result": "pass", "recordedField": "/status", "expectedValue": "verified" }, { "claim": "retry-exhaustion-remains-error-no-effect", "result": "pass", "recordedField": "/records/5", "expectedValue": { "attemptId": "retry-exhausted", "effectOutcome": "not-recorded-local-row", "executionStatus": "error", "nativeRevision": 0, "retries": 2, "taskQuality": "not-evaluated", "toolAttempts": 2 } }, { "claim": "committed-effect-error-retains-revision-one", "result": "pass", "recordedField": "/records/6", "expectedValue": { "attemptId": "committed-effect-error", "effectOutcome": "verified-local-ticket-update", "executionStatus": "error", "nativeRevision": 1, "retries": 0, "taskQuality": "not-evaluated", "toolAttempts": 1 } }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/pydantic-failure-2026-10-02/original-artifact.zip", "sha256": "caa5db0decc85720f26c0a605c59338646702d348f45a26bd21761a8e412f4e5" }, { "path": "../experiments/pydantic-failure-2026-10-02/provenance.json", "sha256": "d035a941c1f818daa2d488dd7f4f9ee1f715650dda38175244ffa2c2007ce5d7" }, { "path": "../experiments/pydantic-failure-2026-10-02/report.json", "sha256": "4c26e0792c89ceecc3ec9d314f9f6179f7cb54763a6d982e827e88ab23a853c7" } ] }, { "id": "model-operational-2026-10-02", "atlasRevision": "65d502b9e751aa11ab6936f4eeaa544eebc2a00f", "sourceRevision": "ab84161d09bb7bd696bba57717a418a95dd1d976", "readerRevision": "4505b08d6f46574d99c01a29681c2b93edbdb342", "report": "../experiments/model-operational-2026-10-02/report.json", "provenance": "../experiments/model-operational-2026-10-02/provenance.json", "contract": "https://github.com/probityai/agent-evidence-observer/tree/ab84161d09bb7bd696bba57717a418a95dd1d976/interop/local-model-tasks-2026-10-02", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-actual-weight-microtask-result", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison published together; not separate raw-result-first revisions.", "limits": [ "Original 274795286-byte ZIP retained locally and available through expiring GitHub workflow artifact, not committed to Git or represented by the capsule.", "Capsule retains exact selected JSON/text members and excludes model weights/binaries; it cannot replay the full source/binary integrity check or rerun inference alone.", "Fixed configuration order confounds cache/warmup; author microtasks are not a benchmark estimate.", "CPU is whole-process delta; RSS process-lifetime peak; no task memory isolation, monetary cost or independent effects." ], "claimResults": [ { "claim": "complete-declared-population", "result": "pass", "recordedField": "/population", "expectedValue": { "scored": 48, "error": 0, "incomplete": 0, "unknown-start": 0, "planned": 48, "started": 48 } }, { "claim": "evidence-complete", "result": "pass", "recordedField": "/evidence/complete", "expectedValue": true }, { "claim": "declared-run-budget", "result": "pass", "recordedField": "/evidence/withinRunBudget", "expectedValue": true }, { "claim": "task-correctness-short24-structured-extraction", "result": "fail", "recordedField": "/quality/0/correct", "expectedValue": 0 }, { "claim": "task-correctness-short24-arithmetic", "result": "fail", "recordedField": "/quality/1/correct", "expectedValue": 0 }, { "claim": "task-correctness-short24-policy-decision", "result": "fail", "recordedField": "/quality/2/correct", "expectedValue": 0 }, { "claim": "task-correctness-short24-grounded-abstention", "result": "fail", "recordedField": "/quality/3/correct", "expectedValue": 0 }, { "claim": "task-correctness-long96-structured-extraction", "result": "fail", "recordedField": "/quality/4/correct", "expectedValue": 0 }, { "claim": "task-correctness-long96-arithmetic", "result": "fail", "recordedField": "/quality/5/correct", "expectedValue": 0 }, { "claim": "task-correctness-long96-policy-decision", "result": "fail", "recordedField": "/quality/6/correct", "expectedValue": 0 }, { "claim": "task-correctness-long96-grounded-abstention", "result": "fail", "recordedField": "/quality/7/correct", "expectedValue": 0 }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/model-operational-2026-10-02/provenance.json", "sha256": "00d9ff560b02f672704f496eacdbb5ed106a9678c89916b0b54b30951c032e0d" }, { "path": "../experiments/model-operational-2026-10-02/report.json", "sha256": "acb8f021b5a9bda6b64e33ab38f9da592b8d2c2bba81de7bfdaef586256608f2" }, { "path": "../experiments/model-operational-2026-10-02/selected-capsule.zip", "sha256": "1613aeff57e696ac1d0f87bbe2c0fe22157cbd6655f1130a2de95b29929b95e2" } ] }, { "id": "authority-recovery-2026-10-02", "atlasRevision": "55df577ea0f0b22710869c18c4d560309387e26a", "sourceRevision": "b02988a771bea3652660bec934c3c599c3ec4d27", "readerRevision": "b02988a771bea3652660bec934c3c599c3ec4d27", "contract": "https://github.com/probityai/agent-evidence-observer/tree/b02988a771bea3652660bec934c3c599c3ec4d27/interop/langgraph-recovery-authority-2026-10-02", "report": "../experiments/authority-recovery-2026-10-02/report.json", "provenance": "../experiments/authority-recovery-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-native-recovery-authority-control", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "Host-selected deterministic integer recovery clock; signed target grant remains separate.", "Graph workers hard-exit/reopen; target process stays alive; no host power loss, distributed exactly-once or independent custody." ], "claimResults": [ { "claim": "complete-selected-population", "result": "pass", "recordedField": "/plannedAttempts", "expectedValue": 8 }, { "claim": "exact-reader-reconstruction", "result": "pass", "recordedField": "/status", "expectedValue": "verified" }, { "claim": "valid-before-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/0", "expectedValue": { "attemptId": "valid-before", "existingCommit": "absent-before-recovery", "freshRecoveryDispatches": 1, "recoveryAuthority": "authorized", "retainedNativeRevision": 1, "workerExitCodes": [ 73, 0 ] } }, { "claim": "valid-after-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/1", "expectedValue": { "attemptId": "valid-after", "existingCommit": "preserved", "freshRecoveryDispatches": 1, "recoveryAuthority": "authorized", "retainedNativeRevision": 1, "workerExitCodes": [ 73, 0 ] } }, { "claim": "revoked-before-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/2", "expectedValue": { "attemptId": "revoked-before", "existingCommit": "absent-before-recovery", "freshRecoveryDispatches": 0, "recoveryAuthority": "refused-revoked", "retainedNativeRevision": 0, "workerExitCodes": [ 73, 0 ] } }, { "claim": "revoked-after-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/3", "expectedValue": { "attemptId": "revoked-after", "existingCommit": "preserved", "freshRecoveryDispatches": 0, "recoveryAuthority": "refused-revoked", "retainedNativeRevision": 1, "workerExitCodes": [ 73, 0 ] } }, { "claim": "expired-before-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/4", "expectedValue": { "attemptId": "expired-before", "existingCommit": "absent-before-recovery", "freshRecoveryDispatches": 0, "recoveryAuthority": "refused-expired", "retainedNativeRevision": 0, "workerExitCodes": [ 73, 0 ] } }, { "claim": "expired-after-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/5", "expectedValue": { "attemptId": "expired-after", "existingCommit": "preserved", "freshRecoveryDispatches": 0, "recoveryAuthority": "refused-expired", "retainedNativeRevision": 1, "workerExitCodes": [ 73, 0 ] } }, { "claim": "rollback-before-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/6", "expectedValue": { "attemptId": "rollback-before", "existingCommit": "absent-before-recovery", "freshRecoveryDispatches": 0, "recoveryAuthority": "refused-clock-rollback", "retainedNativeRevision": 0, "workerExitCodes": [ 73, 0 ] } }, { "claim": "rollback-after-recovery-and-effect-separate", "result": "pass", "recordedField": "/records/7", "expectedValue": { "attemptId": "rollback-after", "existingCommit": "preserved", "freshRecoveryDispatches": 0, "recoveryAuthority": "refused-clock-rollback", "retainedNativeRevision": 1, "workerExitCodes": [ 73, 0 ] } }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/authority-recovery-2026-10-02/original-artifact.zip", "sha256": "2f5754702be98a1681469b7943872cbb5b55e301081db571496fd0c5fa1066b2" }, { "path": "../experiments/authority-recovery-2026-10-02/provenance.json", "sha256": "e00e9f5031fb4e64a5363a05dcba333e569d5c228f96b2e9f42e2ebb381f9f2b" }, { "path": "../experiments/authority-recovery-2026-10-02/report.json", "sha256": "c3cc19a099737c686f373269cb542941fa893ea9d2da3035514776c74b9b6d6a" } ] }, { "id": "target-process-recovery-2026-10-02", "atlasRevision": "55df577ea0f0b22710869c18c4d560309387e26a", "sourceRevision": "37d1dd42239fbe2ef55f625855e385d7337572c1", "readerRevision": "37d1dd42239fbe2ef55f625855e385d7337572c1", "contract": "https://github.com/probityai/agent-evidence-observer/tree/37d1dd42239fbe2ef55f625855e385d7337572c1/interop/target-recovery-2026-10-02", "report": "../experiments/target-process-recovery-2026-10-02/report.json", "provenance": "../experiments/target-process-recovery-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-native-target-process-control", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "Selected target-process hard exits/reopen and local concurrency only; process IDs are unsigned runner testimony.", "Native SQLite/key/clock/HTTP remain same-operator; no power loss, production containment, general exactly-once or outside adoption." ], "claimResults": [ { "claim": "complete-selected-population", "result": "pass", "recordedField": "/plannedAttempts", "expectedValue": 7 }, { "claim": "exact-reader-reconstruction", "result": "pass", "recordedField": "/status", "expectedValue": "verified" }, { "claim": "retained-completedEffects", "result": "pass", "recordedField": "/completedEffects", "expectedValue": 3 }, { "claim": "retained-incompleteRefusals", "result": "pass", "recordedField": "/incompleteRefusals", "expectedValue": 2 }, { "claim": "retained-startupRefusals", "result": "pass", "recordedField": "/startupRefusals", "expectedValue": 2 }, { "claim": "retained-targetProcesses", "result": "pass", "recordedField": "/targetProcesses", "expectedValue": 14 }, { "claim": "restart-ready-retained-state", "result": "pass", "recordedField": "/records/0", "expectedValue": { "dispatchResponses": [ 200 ], "effectId": "4cf9e2d6ed2f2e5ab47de2a72a6ff467decb5785bc3bfe3d0feed74004ac1490", "id": "restart-ready", "nativeRevision": 1, "outcome": "completed", "targetProcesses": 2 } }, { "claim": "crash-after-intent-retained-state", "result": "pass", "recordedField": "/records/1", "expectedValue": { "dispatchResponses": [ 409 ], "effectId": "642550d9090cb3e226dfb1b148542c50bdc67e7dc1b689704332f948129c5fa6", "id": "crash-after-intent", "nativeRevision": 0, "outcome": "incomplete-refused", "targetProcesses": 2 } }, { "claim": "crash-inside-effect-retained-state", "result": "pass", "recordedField": "/records/2", "expectedValue": { "dispatchResponses": [ 409 ], "effectId": "6679edf1c6faba1be7c78d9c8c9676f4b528171aa924e34cb43f3316a16a6d52", "id": "crash-inside-effect", "nativeRevision": 0, "outcome": "incomplete-refused", "targetProcesses": 2 } }, { "claim": "crash-after-effect-retained-state", "result": "pass", "recordedField": "/records/3", "expectedValue": { "dispatchResponses": [ 200 ], "effectId": "4443f7ac19ea6f902488c8c3288ac16b3451f700d0c6591f97c92ae96f862fa8", "id": "crash-after-effect", "nativeRevision": 1, "outcome": "completed", "targetProcesses": 2 } }, { "claim": "concurrent-intent-retained-state", "result": "pass", "recordedField": "/records/4", "expectedValue": { "dispatchResponses": [ 409, 409, 409, 200, 409, 409, 409, 409 ], "effectId": "8a4856ef7ff4b2e508f95f235de920b7475b9655c79a187685e12f047b0466d8", "id": "concurrent-intent", "nativeRevision": 1, "outcome": "completed", "targetProcesses": 2 } }, { "claim": "missing-store-retained-state", "result": "pass", "recordedField": "/records/5", "expectedValue": { "dispatchResponses": [], "effectId": null, "id": "missing-store", "nativeRevision": 0, "outcome": "startup-refused", "targetProcesses": 2 } }, { "claim": "changed-configuration-retained-state", "result": "pass", "recordedField": "/records/6", "expectedValue": { "dispatchResponses": [], "effectId": null, "id": "changed-configuration", "nativeRevision": 0, "outcome": "startup-refused", "targetProcesses": 2 } }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/target-process-recovery-2026-10-02/original-artifact.zip", "sha256": "3082655631a358344f22c5e982e46f6358a2acd5e6a57af200da19e79b85e70d" }, { "path": "../experiments/target-process-recovery-2026-10-02/provenance.json", "sha256": "5f294cbca4b3e6fd157f3a6a3418cbd9a13b8992754a8a8249f8a39994e1c217" }, { "path": "../experiments/target-process-recovery-2026-10-02/report.json", "sha256": "740ffb0d27fd39241231a4b8122282974f63cf88407c54b7cabc38e9cec77792" } ] }, { "id": "model-paired-cpu-2026-10-02", "atlasRevision": "55df577ea0f0b22710869c18c4d560309387e26a", "sourceRevision": "b7db63c319d53b0cb27638a229f966d477a2bbd5", "readerRevision": "94e62e803959c0ee73d1171a03858f48e6a424e0", "contract": "https://github.com/probityai/agent-evidence-observer/tree/b7db63c319d53b0cb27638a229f966d477a2bbd5/interop/local-model-comparison-2026-10-02", "report": "../experiments/model-paired-cpu-2026-10-02/report.json", "provenance": "../experiments/model-paired-cpu-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-actual-weight-paired-microtask-result", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "Producer-selected compact original retains native source/library/call bytes; full preparation weights/source/dependency wheels remain privately archived and provider-expiring.", "Two separately declared preparation attempts, initial failure before inference and corrected preparation; cumulative transfer is not one 512MiB budget.", "Author tasks/answers exposed; blocked interleaving and cache reset do not make a representative benchmark or independent operation.", "Whole-process CPU and shared lifetime RSS are not per-task allocations; no live decision effects." ], "claimResults": [ { "claim": "complete-selected-population", "result": "pass", "recordedField": "/population", "expectedValue": { "error": 0, "incomplete": 0, "planned": 96, "scored": 96, "started": 96, "unknown-start": 0 } }, { "claim": "exact-reader-reconstruction", "result": "pass", "recordedField": "/evidence/complete", "expectedValue": true }, { "claim": "within-declared-native-run-budget", "result": "pass", "recordedField": "/evidence/withinRunBudget", "expectedValue": true }, { "claim": "smol135-q4-short24-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/0", "expectedValue": { "callElapsedNs": 1756651971, "completionTokens": 143, "configuration": "short24", "correct": 0, "family": "structured-extraction", "formatValid": 1, "model": "smol135-q4", "planned": 6, "processCpuNs": 3420495494, "processLifetimePeakRssKiB": 535884, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol135-q4-short24-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/1", "expectedValue": { "callElapsedNs": 1515703007, "completionTokens": 119, "configuration": "short24", "correct": 0, "family": "arithmetic", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 2952459466, "processLifetimePeakRssKiB": 535884, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol135-q4-short24-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/2", "expectedValue": { "callElapsedNs": 2002556534, "completionTokens": 144, "configuration": "short24", "correct": 0, "family": "policy-decision", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 3910132725, "processLifetimePeakRssKiB": 535884, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol135-q4-short24-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/3", "expectedValue": { "callElapsedNs": 1371674280, "completionTokens": 54, "configuration": "short24", "correct": 0, "family": "grounded-abstention", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 2700402687, "processLifetimePeakRssKiB": 535884, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol135-q4-long96-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/4", "expectedValue": { "callElapsedNs": 3784681197, "completionTokens": 429, "configuration": "long96", "correct": 0, "family": "structured-extraction", "formatValid": 1, "model": "smol135-q4", "planned": 6, "processCpuNs": 7282536540, "processLifetimePeakRssKiB": 535884, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol135-q4-long96-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/5", "expectedValue": { "callElapsedNs": 3507306436, "completionTokens": 400, "configuration": "long96", "correct": 0, "family": "arithmetic", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 6744219566, "processLifetimePeakRssKiB": 535884, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol135-q4-long96-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/6", "expectedValue": { "callElapsedNs": 5026396975, "completionTokens": 576, "configuration": "long96", "correct": 0, "family": "policy-decision", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 9666150142, "processLifetimePeakRssKiB": 535884, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol135-q4-long96-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/7", "expectedValue": { "callElapsedNs": 1374217920, "completionTokens": 54, "configuration": "long96", "correct": 0, "family": "grounded-abstention", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 2705283138, "processLifetimePeakRssKiB": 535884, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-short24-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/8", "expectedValue": { "callElapsedNs": 3838839973, "completionTokens": 99, "configuration": "short24", "correct": 2, "family": "structured-extraction", "formatValid": 5, "model": "smol360-q4", "planned": 6, "processCpuNs": 7601539234, "processLifetimePeakRssKiB": 535884, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-short24-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/9", "expectedValue": { "callElapsedNs": 3052520834, "completionTokens": 63, "configuration": "short24", "correct": 1, "family": "arithmetic", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 6053623001, "processLifetimePeakRssKiB": 535884, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-short24-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/10", "expectedValue": { "callElapsedNs": 3795037397, "completionTokens": 65, "configuration": "short24", "correct": 1, "family": "policy-decision", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7537326757, "processLifetimePeakRssKiB": 535884, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-short24-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/11", "expectedValue": { "callElapsedNs": 4113158549, "completionTokens": 83, "configuration": "short24", "correct": 0, "family": "grounded-abstention", "formatValid": 4, "model": "smol360-q4", "planned": 6, "processCpuNs": 8162708300, "processLifetimePeakRssKiB": 535884, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-long96-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/12", "expectedValue": { "callElapsedNs": 3820667805, "completionTokens": 99, "configuration": "long96", "correct": 2, "family": "structured-extraction", "formatValid": 5, "model": "smol360-q4", "planned": 6, "processCpuNs": 7566034371, "processLifetimePeakRssKiB": 535884, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-long96-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/13", "expectedValue": { "callElapsedNs": 3134390319, "completionTokens": 63, "configuration": "long96", "correct": 1, "family": "arithmetic", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 6216176983, "processLifetimePeakRssKiB": 535884, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-long96-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/14", "expectedValue": { "callElapsedNs": 3827781261, "completionTokens": 65, "configuration": "long96", "correct": 1, "family": "policy-decision", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7600427130, "processLifetimePeakRssKiB": 535884, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "smol360-q4-long96-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/15", "expectedValue": { "callElapsedNs": 4119908075, "completionTokens": 83, "configuration": "long96", "correct": 0, "family": "grounded-abstention", "formatValid": 4, "model": "smol360-q4", "planned": 6, "processCpuNs": 8176278039, "processLifetimePeakRssKiB": 535884, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "scored": 6 } }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/model-paired-cpu-2026-10-02/original-artifact.zip", "sha256": "e3b0daad07fb6880fbb4d66adbe92c9cc9c39d5e824667bd38e9289636340efa" }, { "path": "../experiments/model-paired-cpu-2026-10-02/provenance.json", "sha256": "952c6a8f438beb1f360fc40786584f73dde806f8af33ac4c8561e301e265374b" }, { "path": "../experiments/model-paired-cpu-2026-10-02/report.json", "sha256": "7926e4e5998459c1be38b69a81b14be56a22924ea2ccec04509e2cb8fff7c62b" } ] }, { "id": "openai-agents-ticket-2026-10-02", "atlasRevision": "55df577ea0f0b22710869c18c4d560309387e26a", "sourceRevision": "7a4b26058e54f0e6bbbaeab400dcd93c47607389", "readerRevision": "0ec4c970807d0f1bc4215e6d34dc4a6124fa3b4f", "contract": "https://github.com/probityai/agent-evidence-observer/tree/7a4b26058e54f0e6bbbaeab400dcd93c47607389/interop/openai-agents-ticket-2026-10-02", "report": "../experiments/openai-agents-ticket-2026-10-02/report.json", "provenance": "../experiments/openai-agents-ticket-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-scripted-native-sdk-control", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "Actual OpenAI Agents SDK Runner/function_tool/TraceProcessor with scripted Model; nine model calls do not measure remote inference or model quality.", "Producer implementation, PR synthetic execution, final reader and separately pinned protected target revisions remain distinct.", "Same-operator synthetic HTTP ticket effect/key/clock; no independent custody, target restart or outside recurring adoption." ], "claimResults": [ { "claim": "complete-selected-population", "result": "pass", "recordedField": "/plannedAttempts", "expectedValue": 6 }, { "claim": "exact-reader-reconstruction", "result": "pass", "recordedField": "/status", "expectedValue": "verified" }, { "claim": "typed-quality-not-evaluated", "result": "pass", "recordedField": "/modelQuality", "expectedValue": "not-evaluated" }, { "claim": "scripted-sdk-call-and-resource-accounting", "result": "pass", "recordedField": "/resources", "expectedValue": { "cpuNs": 139848462, "elapsedNs": 3130160511, "modelCalls": 9, "toolCalls": 6 } }, { "claim": "permit-task-effect-and-resource-axes", "result": "pass", "recordedField": "/records/0", "expectedValue": { "case": "permit", "completedSpans": 7, "cpuNs": 54704231, "dispatchStatus": 200, "elapsedNs": 552976444, "modelCalls": 2, "nativeRevision": 1, "taskStatus": "complete", "toolCalls": 1 } }, { "claim": "deny-task-effect-and-resource-axes", "result": "pass", "recordedField": "/records/1", "expectedValue": { "case": "deny", "completedSpans": 7, "cpuNs": 18254681, "dispatchStatus": 409, "elapsedNs": 516192026, "modelCalls": 2, "nativeRevision": 0, "taskStatus": "complete", "toolCalls": 1 } }, { "claim": "changed-arguments-task-effect-and-resource-axes", "result": "pass", "recordedField": "/records/2", "expectedValue": { "case": "changed-arguments", "completedSpans": 7, "cpuNs": 15192915, "dispatchStatus": 409, "elapsedNs": 513480469, "modelCalls": 2, "nativeRevision": 0, "taskStatus": "complete", "toolCalls": 1 } }, { "claim": "producer-error-task-effect-and-resource-axes", "result": "pass", "recordedField": "/records/3", "expectedValue": { "case": "producer-error", "completedSpans": 5, "cpuNs": 10266290, "dispatchStatus": null, "elapsedNs": 508862525, "modelCalls": 1, "nativeRevision": 0, "taskStatus": "error", "toolCalls": 1 } }, { "claim": "committed-effect-error-task-effect-and-resource-axes", "result": "pass", "recordedField": "/records/4", "expectedValue": { "case": "committed-effect-error", "completedSpans": 5, "cpuNs": 20495158, "dispatchStatus": 200, "elapsedNs": 519058610, "modelCalls": 1, "nativeRevision": 1, "taskStatus": "error", "toolCalls": 1 } }, { "claim": "turns-exhausted-task-effect-and-resource-axes", "result": "pass", "recordedField": "/records/5", "expectedValue": { "case": "turns-exhausted", "completedSpans": 5, "cpuNs": 20935187, "dispatchStatus": 200, "elapsedNs": 519590437, "modelCalls": 1, "nativeRevision": 1, "taskStatus": "incomplete", "toolCalls": 1 } }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/openai-agents-ticket-2026-10-02/original-artifact.zip", "sha256": "6f90d31bc08599b97641d6e6215a937b4b3ba5962953ce718e24c9ec904f53d2" }, { "path": "../experiments/openai-agents-ticket-2026-10-02/provenance.json", "sha256": "0737d0fdf9b8f5a23c73eddc3dd5a7c86f5c0544cac70a0f9c147e782d941099" }, { "path": "../experiments/openai-agents-ticket-2026-10-02/report.json", "sha256": "936a277df9f5559a7a423fb6b5f70c9460438f6af41c98659ca7b9e8eb42b748" } ] }, { "id": "execsurface-state-2026-10-02", "atlasRevision": "211dbfb22a65ac48c1fab91b6a13f0e15a362837", "sourceRevision": "88f475da4c4626b52ab78900e03ba9f73aa35640", "readerRevision": "88f475da4c4626b52ab78900e03ba9f73aa35640", "contract": "https://github.com/probityai/agent-evidence-observer/tree/88f475da4c4626b52ab78900e03ba9f73aa35640/interop/execsurface-state-2026-10-02", "report": "../experiments/execsurface-state-2026-10-02/report.json", "provenance": "../experiments/execsurface-state-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-native-metadata-and-endpoint-state-join", "roles": { "producer": "Probity-owned workflow using pinned ExecSurface binary", "companionAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written deterministic overwrite, companion and expected outcomes exposed; not blind.", "comparisonOrder": "Native companion output and verifier comparison emitted together; public raw retention before indexing does not establish a blind or native raw-result-first comparison.", "limits": [ "Voluntary/peer/log-import/software-only predicate with incomplete scope and unknown typed collection health.", "Native schema-v2 metadata does not carry written bytes or write count; nine-byte content comes from separate snapshots and declared workload.", "Same operator controls generated fixture, key, store, clock and captures; no independent custody, principal authentication or outside adoption.", "Selected Linux x86_64 ptrace metadata only; no mmap/io_uring attribution or absence-of-intermediate-write claim.", "Native learn/check producer PASS is a separate outside-interval same-byte calibration, not authority, collection health or task quality.", "Release source/binary association is pinned but Rust build reproducibility is not established." ], "claimResults": [ { "claim": "selected-byte-predicate-valid", "result": "pass", "recordedField": "/predicateVerdict", "expectedValue": "valid" }, { "claim": "selected-evidence-valid", "result": "pass", "recordedField": "/evidenceValid", "expectedValue": true }, { "claim": "declared-carried-write-count", "result": "pass", "recordedField": "/carriedWrites", "expectedValue": 1 }, { "claim": "separate-endpoint-after-byte-count", "result": "pass", "recordedField": "/companionAfterBytes", "expectedValue": 9 }, { "claim": "native-invocation-complete", "result": "pass", "recordedField": "/nativeComplete", "expectedValue": true }, { "claim": "import-origin-remains-disclosed", "result": "pass", "recordedField": "/origin", "expectedValue": "log-import" }, { "claim": "voluntary-tier-remains-disclosed", "result": "pass", "recordedField": "/tier", "expectedValue": "voluntary" }, { "claim": "complete-observation-scope", "result": "fail", "recordedField": "/scopeComplete", "expectedValue": false }, { "claim": "unknown-typed-collection-health-remains-disclosed", "result": "pass", "recordedField": "/collectionHealth", "expectedValue": "unknown-no-typed-envelope" }, { "claim": "native-write-count-not-invented", "result": "pass", "recordedField": "/nativeWriteByteCount", "expectedValue": "not-carried-in-schema-v2" }, { "claim": "producer-calibration-pass", "result": "pass", "recordedField": "/producerDriftVerdict", "expectedValue": "pass" }, { "claim": "producer-comparison-outside-claimed-interval", "result": "pass", "recordedField": "/producerComparisonOutsideInterval", "expectedValue": true }, { "claim": "independent-effect-key-store-clock-custody", "result": "not-exercised" }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "typed-collection-health-envelope", "result": "not-exercised" }, { "claim": "absence-of-intermediate-writes", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/execsurface-state-2026-10-02/original-artifact.zip", "sha256": "6f6c0b9e7d6f8f63cfcf2f1ce07e49fb1ca7c8e1433ba0d73782dbfdb28dc814" }, { "path": "../experiments/execsurface-state-2026-10-02/provenance.json", "sha256": "01ddd16d56af3743b8ba5a62931458f84636e51065b32a2d3bd7cfcbdb93092c" }, { "path": "../experiments/execsurface-state-2026-10-02/report.json", "sha256": "7a6f9e00d7939aad6ea55c5a5143133a255ff788f82fb39f2e51058204a1b30a" } ] }, { "id": "model-format-cpu-2026-10-02", "atlasRevision": "307b29af5c1fcc51a5805ffa290b7fc89a0cb0e7", "sourceRevision": "75797cbb4fafc0669849357dd2275825b469c1f9", "readerRevision": "26fc707f53b79f8770336897e32040ba1f9e9f16", "contract": "https://github.com/probityai/agent-evidence-observer/tree/75797cbb4fafc0669849357dd2275825b469c1f9/interop/local-model-format-control-2026-10-02", "report": "../experiments/model-format-cpu-2026-10-02/report.json", "provenance": "../experiments/model-format-cpu-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-actual-weight-paired-format-and-correctness-result", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "Format/schema correctness separate from typed-exact target correctness; each model/cap/decoder/family row retained independently.", "Protocol/compiler/grammars frozen before inference; selected integer-length, key-order and spacing restrictions limit generalization.", "Exposed author tasks and same-operator native execution; no representative benchmark, live protected decision effects or independent custody.", "Four separately declared preparation envelopes; cumulative transfer exceeds one512MiB envelope.", "Original compact native provider archive retains sources/grammars/outputs and resources; full preparation weights/source/wheels remain privately archived.", "CPU is whole-process delta and RSS shared lifetime peak; not per-model/task allocation." ], "claimResults": [ { "claim": "complete-selected-population", "result": "pass", "recordedField": "/population", "expectedValue": { "error": 0, "incomplete": 0, "planned": 192, "scored": 192, "started": 192, "unknown-start": 0, "unsupported": 0 } }, { "claim": "exact-reader-reconstruction", "result": "pass", "recordedField": "/evidence/complete", "expectedValue": true }, { "claim": "within-declared-native-run-budget", "result": "pass", "recordedField": "/evidence/withinRunBudget", "expectedValue": true }, { "claim": "smol135-q4-short24-unconstrained-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/0", "expectedValue": { "callElapsedNs": 1748998941, "completionTokens": 143, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "structured-extraction", "formatValid": 1, "model": "smol135-q4", "planned": 6, "processCpuNs": 3403629782, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-short24-unconstrained-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/1", "expectedValue": { "callElapsedNs": 1541615422, "completionTokens": 119, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "arithmetic", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 3002349314, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-short24-unconstrained-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/2", "expectedValue": { "callElapsedNs": 1946854423, "completionTokens": 144, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "policy-decision", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 3802209612, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-short24-unconstrained-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/3", "expectedValue": { "callElapsedNs": 1383494679, "completionTokens": 54, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "grounded-abstention", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 2723218601, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-short24-schema-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/4", "expectedValue": { "callElapsedNs": 1914564180, "completionTokens": 90, "configuration": "short24", "correct": 4, "decoder": "schema", "family": "structured-extraction", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 3290480336, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol135-q4-short24-schema-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/5", "expectedValue": { "callElapsedNs": 1309843409, "completionTokens": 47, "configuration": "short24", "correct": 0, "decoder": "schema", "family": "arithmetic", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 2338385152, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol135-q4-short24-schema-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/6", "expectedValue": { "callElapsedNs": 1603433346, "completionTokens": 48, "configuration": "short24", "correct": 0, "decoder": "schema", "family": "policy-decision", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 2902321959, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol135-q4-short24-schema-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/7", "expectedValue": { "callElapsedNs": 1852775548, "completionTokens": 61, "configuration": "short24", "correct": 1, "decoder": "schema", "family": "grounded-abstention", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 3275923524, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol135-q4-long96-unconstrained-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/8", "expectedValue": { "callElapsedNs": 3756403260, "completionTokens": 429, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "structured-extraction", "formatValid": 1, "model": "smol135-q4", "planned": 6, "processCpuNs": 7223925593, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-long96-unconstrained-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/9", "expectedValue": { "callElapsedNs": 3506759259, "completionTokens": 400, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "arithmetic", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 6738459704, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-long96-unconstrained-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/10", "expectedValue": { "callElapsedNs": 5012993864, "completionTokens": 576, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "policy-decision", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 9631752740, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-long96-unconstrained-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/11", "expectedValue": { "callElapsedNs": 1429630471, "completionTokens": 54, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "grounded-abstention", "formatValid": 0, "model": "smol135-q4", "planned": 6, "processCpuNs": 2813989249, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol135-q4-long96-schema-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/12", "expectedValue": { "callElapsedNs": 1906001266, "completionTokens": 90, "configuration": "long96", "correct": 4, "decoder": "schema", "family": "structured-extraction", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 3276471820, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol135-q4-long96-schema-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/13", "expectedValue": { "callElapsedNs": 1312814830, "completionTokens": 47, "configuration": "long96", "correct": 0, "decoder": "schema", "family": "arithmetic", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 2344196756, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol135-q4-long96-schema-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/14", "expectedValue": { "callElapsedNs": 1604524678, "completionTokens": 48, "configuration": "long96", "correct": 0, "decoder": "schema", "family": "policy-decision", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 2901527030, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol135-q4-long96-schema-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/15", "expectedValue": { "callElapsedNs": 1821108516, "completionTokens": 61, "configuration": "long96", "correct": 1, "decoder": "schema", "family": "grounded-abstention", "formatValid": 6, "model": "smol135-q4", "planned": 6, "processCpuNs": 3217245274, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-short24-unconstrained-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/16", "expectedValue": { "callElapsedNs": 3812049695, "completionTokens": 99, "configuration": "short24", "correct": 2, "decoder": "unconstrained", "family": "structured-extraction", "formatValid": 5, "model": "smol360-q4", "planned": 6, "processCpuNs": 7546162854, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 2, "scored": 6 } }, { "claim": "smol360-q4-short24-unconstrained-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/17", "expectedValue": { "callElapsedNs": 3047815670, "completionTokens": 63, "configuration": "short24", "correct": 1, "decoder": "unconstrained", "family": "arithmetic", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 6043374211, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 2, "scored": 6 } }, { "claim": "smol360-q4-short24-unconstrained-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/18", "expectedValue": { "callElapsedNs": 3779328066, "completionTokens": 65, "configuration": "short24", "correct": 1, "decoder": "unconstrained", "family": "policy-decision", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7505077496, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-short24-unconstrained-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/19", "expectedValue": { "callElapsedNs": 4116130685, "completionTokens": 83, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "grounded-abstention", "formatValid": 4, "model": "smol360-q4", "planned": 6, "processCpuNs": 8163646601, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol360-q4-short24-schema-structured-extraction-all-six-strict-targets", "result": "pass", "recordedField": "/quality/20", "expectedValue": { "callElapsedNs": 4151733060, "completionTokens": 86, "configuration": "short24", "correct": 6, "decoder": "schema", "family": "structured-extraction", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7774438523, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-short24-schema-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/21", "expectedValue": { "callElapsedNs": 3048508138, "completionTokens": 47, "configuration": "short24", "correct": 3, "decoder": "schema", "family": "arithmetic", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 5810181985, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-short24-schema-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/22", "expectedValue": { "callElapsedNs": 3940970775, "completionTokens": 54, "configuration": "short24", "correct": 1, "decoder": "schema", "family": "policy-decision", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7524211133, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-short24-schema-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/23", "expectedValue": { "callElapsedNs": 3786387640, "completionTokens": 45, "configuration": "short24", "correct": 3, "decoder": "schema", "family": "grounded-abstention", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7276418126, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-long96-unconstrained-structured-extraction-all-six-strict-targets", "result": "fail", "recordedField": "/quality/24", "expectedValue": { "callElapsedNs": 3809516954, "completionTokens": 99, "configuration": "long96", "correct": 2, "decoder": "unconstrained", "family": "structured-extraction", "formatValid": 5, "model": "smol360-q4", "planned": 6, "processCpuNs": 7541916870, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 2, "scored": 6 } }, { "claim": "smol360-q4-long96-unconstrained-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/25", "expectedValue": { "callElapsedNs": 3042072832, "completionTokens": 63, "configuration": "long96", "correct": 1, "decoder": "unconstrained", "family": "arithmetic", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 6032356113, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 2, "scored": 6 } }, { "claim": "smol360-q4-long96-unconstrained-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/26", "expectedValue": { "callElapsedNs": 3800238469, "completionTokens": 65, "configuration": "long96", "correct": 1, "decoder": "unconstrained", "family": "policy-decision", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7547128481, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-long96-unconstrained-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/27", "expectedValue": { "callElapsedNs": 4099009964, "completionTokens": 83, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "grounded-abstention", "formatValid": 4, "model": "smol360-q4", "planned": 6, "processCpuNs": 8132947649, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 6 } }, { "claim": "smol360-q4-long96-schema-structured-extraction-all-six-strict-targets", "result": "pass", "recordedField": "/quality/28", "expectedValue": { "callElapsedNs": 4065443035, "completionTokens": 86, "configuration": "long96", "correct": 6, "decoder": "schema", "family": "structured-extraction", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7607120128, "processLifetimePeakRssKiB": 554152, "promptTokens": 323, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-long96-schema-arithmetic-all-six-strict-targets", "result": "fail", "recordedField": "/quality/29", "expectedValue": { "callElapsedNs": 3044806279, "completionTokens": 47, "configuration": "long96", "correct": 3, "decoder": "schema", "family": "arithmetic", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 5802632432, "processLifetimePeakRssKiB": 554152, "promptTokens": 295, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-long96-schema-policy-decision-all-six-strict-targets", "result": "fail", "recordedField": "/quality/30", "expectedValue": { "callElapsedNs": 3941387854, "completionTokens": 54, "configuration": "long96", "correct": 1, "decoder": "schema", "family": "policy-decision", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7524940958, "processLifetimePeakRssKiB": 554152, "promptTokens": 396, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "smol360-q4-long96-schema-grounded-abstention-all-six-strict-targets", "result": "fail", "recordedField": "/quality/31", "expectedValue": { "callElapsedNs": 3762554292, "completionTokens": 45, "configuration": "long96", "correct": 3, "decoder": "schema", "family": "grounded-abstention", "formatValid": 6, "model": "smol360-q4", "planned": 6, "processCpuNs": 7228610778, "processLifetimePeakRssKiB": 554152, "promptTokens": 400, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 6, "scored": 6 } }, { "claim": "independent-effect-key-store-clock-custody", "result": "not-exercised" }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "protected-decision-effects", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/model-format-cpu-2026-10-02/original-artifact.zip", "sha256": "e64eafb149f4a0975831b5ca36df74ca89abef0c8dd1ca2c40cc71e317d123fe" }, { "path": "../experiments/model-format-cpu-2026-10-02/provenance.json", "sha256": "3ba30e6c165d771078db77309250024eff2620b50151e5521bee7ac185c42838" }, { "path": "../experiments/model-format-cpu-2026-10-02/report.json", "sha256": "c2a7d1954f3fb005ab8f2d0faeb121f005deed7a54cd5d03ceeb4b13c861153d" } ] }, { "id": "google-adk-ticket-2026-10-02", "atlasRevision": "6c9530460f48da368673f7ad933756cd51ce1139", "sourceRevision": "a6cb0b0eb767e01ad2d0813c9483c39af08163cd", "readerRevision": "420a96a830b84fbdaf4fed052901f45686afec18", "contract": "https://github.com/probityai/agent-evidence-observer/tree/a6cb0b0eb767e01ad2d0813c9483c39af08163cd/interop/adk-ticket-2026-10-02", "report": "../experiments/google-adk-ticket-2026-10-02/report.json", "provenance": "../experiments/google-adk-ticket-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-native-google-adk-scripted-reference-result", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "Real Google ADK nativeRunner/plugin/retry paths with scriptedBaseLlm; no remote inference or model-quality evaluation.", "Typed MCPisError throughFunctionTool is not actual MCP transport.", "Task complete/error/incomplete separate from signednativeRevision; after-effect error and early close retain committed effects.", "Author-operated target/store/key/clock/capture and exposed expected outcomes; no independent custody/outside adoption.", "Original synthetic execution source, producer implementation, reviewed reader and protected target baseline separately pinned." ], "claimResults": [ { "claim": "bounded-reference-evidence-verified", "result": "pass", "recordedField": "/status", "expectedValue": "verified" }, { "claim": "declared-reference-population", "result": "pass", "recordedField": "/plannedAttempts", "expectedValue": 12 }, { "claim": "scripted-SDK-resource-counts", "result": "pass", "recordedField": "/resources", "expectedValue": { "cpuNs": 2216386701, "elapsedNs": 8200260906, "httpPosts": 9, "modelCalls": 25, "toolCalls": 18 } }, { "claim": "model-quality-not-measured", "result": "pass", "recordedField": "/modelQuality", "expectedValue": "not-evaluated" }, { "claim": "permit-task-completion", "result": "pass", "recordedField": "/records/0/taskStatus", "expectedValue": "complete" }, { "claim": "permit-native-revision-one", "result": "pass", "recordedField": "/records/0/nativeRevision", "expectedValue": 1 }, { "claim": "deny-task-completion", "result": "pass", "recordedField": "/records/1/taskStatus", "expectedValue": "complete" }, { "claim": "deny-native-revision-one", "result": "fail", "recordedField": "/records/1/nativeRevision", "expectedValue": 0 }, { "claim": "changed-arguments-task-completion", "result": "pass", "recordedField": "/records/2/taskStatus", "expectedValue": "complete" }, { "claim": "changed-arguments-native-revision-one", "result": "fail", "recordedField": "/records/2/nativeRevision", "expectedValue": 0 }, { "claim": "unhandled-before-task-completion", "result": "fail", "recordedField": "/records/3/taskStatus", "expectedValue": "error" }, { "claim": "unhandled-before-native-revision-one", "result": "fail", "recordedField": "/records/3/nativeRevision", "expectedValue": 0 }, { "claim": "unhandled-after-task-completion", "result": "fail", "recordedField": "/records/4/taskStatus", "expectedValue": "error" }, { "claim": "unhandled-after-native-revision-one", "result": "pass", "recordedField": "/records/4/nativeRevision", "expectedValue": 1 }, { "claim": "handled-first-task-completion", "result": "pass", "recordedField": "/records/5/taskStatus", "expectedValue": "complete" }, { "claim": "handled-first-native-revision-one", "result": "pass", "recordedField": "/records/5/nativeRevision", "expectedValue": 1 }, { "claim": "handled-last-task-completion", "result": "pass", "recordedField": "/records/6/taskStatus", "expectedValue": "complete" }, { "claim": "handled-last-native-revision-one", "result": "pass", "recordedField": "/records/6/nativeRevision", "expectedValue": 1 }, { "claim": "exhausted-first-task-completion", "result": "fail", "recordedField": "/records/7/taskStatus", "expectedValue": "error" }, { "claim": "exhausted-first-native-revision-one", "result": "fail", "recordedField": "/records/7/nativeRevision", "expectedValue": 0 }, { "claim": "exhausted-last-task-completion", "result": "fail", "recordedField": "/records/8/taskStatus", "expectedValue": "error" }, { "claim": "exhausted-last-native-revision-one", "result": "fail", "recordedField": "/records/8/nativeRevision", "expectedValue": 0 }, { "claim": "returned-error-first-task-completion", "result": "pass", "recordedField": "/records/9/taskStatus", "expectedValue": "complete" }, { "claim": "returned-error-first-native-revision-one", "result": "pass", "recordedField": "/records/9/nativeRevision", "expectedValue": 1 }, { "claim": "returned-error-last-task-completion", "result": "pass", "recordedField": "/records/10/taskStatus", "expectedValue": "complete" }, { "claim": "returned-error-last-native-revision-one", "result": "pass", "recordedField": "/records/10/nativeRevision", "expectedValue": 1 }, { "claim": "incomplete-close-task-completion", "result": "fail", "recordedField": "/records/11/taskStatus", "expectedValue": "incomplete" }, { "claim": "incomplete-close-native-revision-one", "result": "pass", "recordedField": "/records/11/nativeRevision", "expectedValue": 1 }, { "claim": "independent-effect-key-store-clock-custody", "result": "not-exercised" }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/google-adk-ticket-2026-10-02/original-artifact.zip", "sha256": "4602b83d1b3e52d6aea8def21eff28f5b18b78c04da9213e4187ee2c1abf31e6" }, { "path": "../experiments/google-adk-ticket-2026-10-02/provenance.json", "sha256": "5f23ac9220ca2f00e62f8bc6ea78bdbc49a16b4eee55d01ee5fb5133eadc6207" }, { "path": "../experiments/google-adk-ticket-2026-10-02/report.json", "sha256": "f66b10be372a4a9410978cf7c2279985ef4aeb9a27cf16d33944af0e8f49df9a" } ] }, { "id": "installed-format-policy-2026-10-02", "atlasRevision": "6c9530460f48da368673f7ad933756cd51ce1139", "sourceRevision": "efa0a2932e31dc69db60bb812b142e580fbf993c", "readerRevision": "efa0a2932e31dc69db60bb812b142e580fbf993c", "contract": "https://github.com/probityai/agent-evidence-observer/tree/efa0a2932e31dc69db60bb812b142e580fbf993c/interop/model-consumer-2026-10-02", "report": "../experiments/installed-format-policy-2026-10-02/report.json", "provenance": "../experiments/installed-format-policy-2026-10-02/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-installed-native-reader-upgrade-and-publication-policy-result", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written tasks/controls and expected outcomes exposed; not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "Actual framework-free installed0.0.2\u21920.0.3 upgrade and selectedhostpolicy run, not a new inference experiment.", "Verified scoped-report publication separate from held policy1/6 correctness, no dispatch or recovery authority.", "Full original2268member provider artifact retained including previous upgrade, wheels, immutable fixture packets and rawgate streams; no omissions.", "Same operator selects installation/reader/policy/expected outcomes; no registry release, outside recurring use or independent custody.", "Consumer source/reviewed commit and actualnative192 producer source/run remain separate." ], "claimResults": [ { "claim": "baseline-installed-version", "result": "pass", "recordedField": "/baseline-installation/version", "expectedValue": "0.0.2" }, { "claim": "baseline-framework-modules-absent", "result": "pass", "recordedField": "/baseline-installation/frameworkModules", "expectedValue": { "llama_cpp": false, "inspect_ai": false, "langgraph": false, "pydantic_ai": false, "agents": false } }, { "claim": "baseline-original-evidence-state", "result": "pass", "recordedField": "/baseline-original/gate/evidenceDecision", "expectedValue": "verified" }, { "claim": "baseline-original-selected-publication-state", "result": "pass", "recordedField": "/baseline-original/gate/publicationDecision", "expectedValue": "publish" }, { "claim": "baseline-comparison-evidence-state", "result": "pass", "recordedField": "/baseline-comparison/gate/evidenceDecision", "expectedValue": "verified" }, { "claim": "baseline-comparison-selected-publication-state", "result": "pass", "recordedField": "/baseline-comparison/gate/publicationDecision", "expectedValue": "publish" }, { "claim": "baseline-format-evidence-state", "result": "pass", "recordedField": "/baseline-format/gate/evidenceDecision", "expectedValue": "not-verified" }, { "claim": "baseline-format-selected-publication-state", "result": "pass", "recordedField": "/baseline-format/gate/publicationDecision", "expectedValue": "hold" }, { "claim": "candidate-installed-version", "result": "pass", "recordedField": "/candidate-installation/version", "expectedValue": "0.0.3" }, { "claim": "candidate-framework-modules-absent", "result": "pass", "recordedField": "/candidate-installation/frameworkModules", "expectedValue": { "llama_cpp": false, "inspect_ai": false, "langgraph": false, "pydantic_ai": false, "agents": false } }, { "claim": "candidate-original-evidence-state", "result": "pass", "recordedField": "/candidate-original/gate/evidenceDecision", "expectedValue": "verified" }, { "claim": "candidate-original-selected-publication-state", "result": "pass", "recordedField": "/candidate-original/gate/publicationDecision", "expectedValue": "publish" }, { "claim": "candidate-comparison-evidence-state", "result": "pass", "recordedField": "/candidate-comparison/gate/evidenceDecision", "expectedValue": "verified" }, { "claim": "candidate-comparison-selected-publication-state", "result": "pass", "recordedField": "/candidate-comparison/gate/publicationDecision", "expectedValue": "publish" }, { "claim": "candidate-format-evidence-state", "result": "pass", "recordedField": "/candidate-format/gate/evidenceDecision", "expectedValue": "verified" }, { "claim": "candidate-format-selected-publication-state", "result": "pass", "recordedField": "/candidate-format/gate/publicationDecision", "expectedValue": "publish" }, { "claim": "prior-native-report-hashes-preserved", "result": "pass", "recordedField": "/preservedReports", "expectedValue": { "original": "acb8f021b5a9bda6b64e33ab38f9da592b8d2c2bba81de7bfdaef586256608f2", "comparison": "62fb95b5fff895ff76e4a42e17e391ec0525d3c5f9fade90efc64f5c0cad0892" } }, { "claim": "old-reader-refuses-unsupported-format", "result": "pass", "recordedField": "/baseline-reader/exit", "expectedValue": 1 }, { "claim": "schema-policy-evidence-verified", "result": "pass", "recordedField": "/candidate-format-quality/gate/evidenceDecision", "expectedValue": "verified" }, { "claim": "schema-policy-selected-quality-hold", "result": "pass", "recordedField": "/candidate-format-quality/gate/publicationDecision", "expectedValue": "hold-selected-score-or-resource" }, { "claim": "two-low-policy-score-refusals", "result": "pass", "recordedField": "/candidate-format-quality/gate/policyFailures", "expectedValue": [ { "row": { "decoder": "schema", "model": "smol360-q4", "configuration": "short24", "family": "policy-decision" }, "field": "correct", "measured": 1, "minimum": 3 }, { "row": { "decoder": "schema", "model": "smol360-q4", "configuration": "long96", "family": "policy-decision" }, "field": "correct", "measured": 1, "minimum": 3 } ] }, { "claim": "changed-source-evidence-refused", "result": "pass", "recordedField": "/candidate-mutant/gate/evidenceDecision", "expectedValue": "not-verified" }, { "claim": "changed-source-publication-held", "result": "pass", "recordedField": "/candidate-mutant/gate/publicationDecision", "expectedValue": "hold" }, { "claim": "independent-effect-key-store-clock-custody", "result": "not-exercised" }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/installed-format-policy-2026-10-02/original-artifact.zip", "sha256": "a609ce71f6172d83f27a2992437d690ab6f7df85c1954cad87986152e5282c24" }, { "path": "../experiments/installed-format-policy-2026-10-02/provenance.json", "sha256": "5943a111e63beb959a34b87580d1e81173fe35ddc6f83ec072cce95a1964f104" }, { "path": "../experiments/installed-format-policy-2026-10-02/report.json", "sha256": "748125384aceea85cc1cd99f1cc5de781281689110f1157a545f71a05f427ac4" } ] }, { "id": "model-boundary-cpu-2026-10-02", "atlasRevision": "f41a3920db3cfd37923cdf0ab206f94bb9d7b2bb", "sourceRevision": "6cfd28dc61aa0ae43be5da8382fe959c94235997", "readerRevision": "fdda91d18aa4cca5eeb51b0b8d5de8232abb9110", "contract": "https://github.com/probityai/agent-evidence-observer/tree/6cfd28dc61aa0ae43be5da8382fe959c94235997/interop/local-model-boundary-tasks-2026-10-02", "report": "../experiments/model-boundary-cpu-2026-10-02/report.json", "provenance": "../experiments/model-boundary-cpu-2026-10-02/provenance.json", "derivedFindings": "../experiments/model-boundary-cpu-2026-10-02/finite-findings.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-finite-typed-policy-grounded-boundary-result", "roles": { "producer": "Probity-owned workflow", "readerAuthor": "Probity", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written cases, public targets and previous public failures informed selection;48 identities include46 literal inputs and two repeated positive-control inputs. Not blind.", "comparisonOrder": "Native output and comparison emitted and published together; public Atlas retention before indexing does not establish a blind or raw-result-first comparison.", "limits": [ "All24 model/cap/decoder/family rows and384 original attempt scores retained unchanged; pair correctness separate from schema validity.", "48 authored case identities include46 unique literal inputs and two repeated positive controls; exposed targets, not blind or representative.", "No protected model decision effects, independent operation/effect custody or outside recurring use.", "Five separate preparation envelopes; cumulative2167006362 response-body bytes cannot be presented as one512MiB acquisition.", "Complete original preparation privately archived; public871-member original compact maps to901 full members with30 explicit omissions.", "Total process CPU includes initialization; returned-call CPU and shared lifetime RSS keep their original scopes.", "Post hoc vocabulary diagnosis and cap comparisons do not alter the frozen rubric or published scores." ], "artifacts": [ { "path": "../experiments/model-boundary-cpu-2026-10-02/original-artifact.zip", "sha256": "d8ff26e82aca136daf734da65ede259b2bfaed9dd547ba25b92d65bdeeef019f" }, { "path": "../experiments/model-boundary-cpu-2026-10-02/provenance.json", "sha256": "f653dfa3c02a9290a470a8ff8c4327297d7a732ee7421c347864335f7c1025a6" }, { "path": "../experiments/model-boundary-cpu-2026-10-02/report.json", "sha256": "fa7b0e39b69bcd42f82fc93096e071b534557c34cf0e03e73e1bac56dcdd72af" }, { "path": "../experiments/model-boundary-cpu-2026-10-02/finite-findings.json", "sha256": "2ff6357c8c2eef79d5606257dad39f5c9491053e19640429b9a165328922ac7b" } ], "claimResults": [ { "claim": "all384-original-attempts-scored", "result": "pass", "recordedField": "/population", "expectedValue": { "error": 0, "incomplete": 0, "planned": 384, "scored": 384, "started": 384, "unknown-start": 0, "unsupported": 0 } }, { "claim": "evidence-complete-and-within-run-budget", "result": "pass", "recordedField": "/evidence", "expectedValue": { "complete": true, "withinRunBudget": true } }, { "claim": "protected-effects-not-executed", "result": "pass", "recordedField": "/effects", "expectedValue": "not executed" }, { "claim": "smol135-q4-short24-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/0", "expectedValue": { "callElapsedNs": 4723831541, "completionTokens": 310, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 9240492026, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol135-q4-short24-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/1", "expectedValue": { "callElapsedNs": 5976613495, "completionTokens": 384, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 11693640399, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol135-q4-short24-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/2", "expectedValue": { "callElapsedNs": 7814501471, "completionTokens": 384, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 15363970770, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol135-q4-short24-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "pass", "recordedField": "/quality/3", "expectedValue": { "callElapsedNs": 4291221990, "completionTokens": 131, "configuration": "short24", "correct": 16, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 8, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 7754893355, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol135-q4-short24-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/4", "expectedValue": { "callElapsedNs": 5077534177, "completionTokens": 138, "configuration": "short24", "correct": 0, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 9286420480, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol135-q4-short24-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/5", "expectedValue": { "callElapsedNs": 7993651119, "completionTokens": 220, "configuration": "short24", "correct": 3, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 14628609279, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol135-q4-long96-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/6", "expectedValue": { "callElapsedNs": 6497086579, "completionTokens": 553, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 12617390214, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol135-q4-long96-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/7", "expectedValue": { "callElapsedNs": 10725354267, "completionTokens": 1041, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 20732146066, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol135-q4-long96-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/8", "expectedValue": { "callElapsedNs": 14098939614, "completionTokens": 1231, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 27341884632, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol135-q4-long96-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "pass", "recordedField": "/quality/9", "expectedValue": { "callElapsedNs": 4320565423, "completionTokens": 131, "configuration": "long96", "correct": 16, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 8, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 7797561488, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol135-q4-long96-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/10", "expectedValue": { "callElapsedNs": 5112517206, "completionTokens": 138, "configuration": "long96", "correct": 0, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 9348957832, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol135-q4-long96-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/11", "expectedValue": { "callElapsedNs": 7948825378, "completionTokens": 220, "configuration": "long96", "correct": 3, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 14550379810, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol360-q4-short24-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/12", "expectedValue": { "callElapsedNs": 9954980498, "completionTokens": 159, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19774843637, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol360-q4-short24-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/13", "expectedValue": { "callElapsedNs": 15309358990, "completionTokens": 384, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 2, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 30337025043, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol360-q4-short24-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/14", "expectedValue": { "callElapsedNs": 17731268785, "completionTokens": 211, "configuration": "short24", "correct": 1, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35279417494, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 10, "scored": 16 } }, { "claim": "smol360-q4-short24-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/15", "expectedValue": { "callElapsedNs": 10347515652, "completionTokens": 133, "configuration": "short24", "correct": 13, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 5, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19844845665, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol360-q4-short24-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/16", "expectedValue": { "callElapsedNs": 12744687672, "completionTokens": 151, "configuration": "short24", "correct": 2, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 24487405820, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol360-q4-short24-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/17", "expectedValue": { "callElapsedNs": 18142441570, "completionTokens": 176, "configuration": "short24", "correct": 1, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35251934237, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol360-q4-long96-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/18", "expectedValue": { "callElapsedNs": 9897596024, "completionTokens": 159, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19661772937, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol360-q4-long96-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/19", "expectedValue": { "callElapsedNs": 18560132988, "completionTokens": 573, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 36688759188, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "smol360-q4-long96-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/20", "expectedValue": { "callElapsedNs": 17766238167, "completionTokens": 211, "configuration": "long96", "correct": 1, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35348355485, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 10, "scored": 16 } }, { "claim": "smol360-q4-long96-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/21", "expectedValue": { "callElapsedNs": 10294154970, "completionTokens": 133, "configuration": "long96", "correct": 13, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 5, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19721071852, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol360-q4-long96-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/22", "expectedValue": { "callElapsedNs": 12591439115, "completionTokens": 151, "configuration": "long96", "correct": 2, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 24186369255, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "smol360-q4-long96-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/quality/23", "expectedValue": { "callElapsedNs": 18069864840, "completionTokens": 176, "configuration": "long96", "correct": 1, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35113092656, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "independent-effect-custody", "result": "not-exercised" }, { "claim": "outside-recurring-host-use", "result": "not-exercised" }, { "claim": "representative-benchmark-performance", "result": "out-of-scope" } ] }, { "id": "atomic-delegation-2026-10-02", "readerRevision": "80be8dae6feb8b9106181b78fba2c7c6a7c8f4d8", "contract": "https://github.com/astrogilda/atomic/blob/80be8dae6feb8b9106181b78fba2c7c6a7c8f4d8/tools/native-evaluation/README.md", "report": "../experiments/atomic-delegation-2026-10-02/report.json", "provenance": "../experiments/atomic-delegation-2026-10-02/provenance.json", "reviewState": "author-operated-upstream-review-pending", "evidenceClaim": "native-local-certificate-selection-persistence", "roles": { "fixtureAuthor": "Probity", "runner": "Probity local workspace", "keyClockFilesystemCustodian": "Probity local workspace", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Author-written native cases and expected outcomes exposed; not blind.", "comparisonOrder": "Original native observations and test assertions emitted together, not separate public raw-result-first revisions.", "limits": [ "Normal fresh reader-process restart, not crash-mid-write consistency.", "Self-contained local grant selection does not establish external issuer authority or server permission enforcement.", "Local key, clock and filesystem remain under one operator; child PIDs are unsigned testimony.", "No remote revocation, independently operated effect custody, model task quality or recurring outside use is established.", "Full author-assembled ZIP packages byte-exact original retained-run files; it is not a CI provider archive." ], "claimResults": [ { "claim": "complete-declared-native-population", "result": "pass", "recordedField": "/declared_cases", "expectedValue": [ "exact_retry_and_process_restart_preserve_a_narrow_grant", "revocation_survives_restart_and_does_not_revoke_a_distinct_renewal", "expired_and_corrupt_grants_stay_inactive_after_restart", "local_selection_does_not_establish_external_issuer_authority" ] }, { "claim": "exact_retry_and_process_restart_preserve_a_narrow_grant", "result": "pass", "recordedField": "/results/0", "expectedValue": { "argv": [ "/workspace/atomic-pr-tools/target-native/debug/deps/delegation_restart-024c3e55c7b51ced", "--exact", "exact_retry_and_process_restart_preserve_a_narrow_grant", "--nocapture" ], "returncode": 0, "timed_out": false, "wall_seconds": 0.11508546500044758, "stdout": "case-0.stdout", "stderr": "case-0.stderr", "case": "exact_retry_and_process_restart_preserve_a_narrow_grant", "observations": [ { "active_id": "FYTMI4JUHEX6QWDYQFFFUE6XNUDVEMHAI5XEDCNNOASRE4N7WASQ", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295072, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 1, "verified_for_delegate": 1 }, { "active_id": "FYTMI4JUHEX6QWDYQFFFUE6XNUDVEMHAI5XEDCNNOASRE4N7WASQ", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295080, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 1, "verified_for_delegate": 1 } ], "passed": true } }, { "claim": "revocation_survives_restart_and_does_not_revoke_a_distinct_renewal", "result": "pass", "recordedField": "/results/1", "expectedValue": { "argv": [ "/workspace/atomic-pr-tools/target-native/debug/deps/delegation_restart-024c3e55c7b51ced", "--exact", "revocation_survives_restart_and_does_not_revoke_a_distinct_renewal", "--nocapture" ], "returncode": 0, "timed_out": false, "wall_seconds": 0.21452056100133632, "stdout": "case-1.stdout", "stderr": "case-1.stderr", "case": "revocation_survives_restart_and_does_not_revoke_a_distinct_renewal", "observations": [ { "active_id": "KFPC4CDU7EPEVTTDKX6WD3OFK5CXAKF5MV6NLNQTY2N7JEIH7OFQ", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295090, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 1, "verified_for_delegate": 1 }, { "active_id": null, "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": false, "allows_staging": false, "coverage": "local-store-selection-only", "locally_revoked": 1, "pid": 295092, "scope": null, "stored": 1, "verified_for_delegate": 1 }, { "active_id": "M6ZCTVT2LSE4KYPPODAI6K5WORHIIWQGNDKMUJD2WE2HKFN6CX4A", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 1, "pid": 295094, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 2, "verified_for_delegate": 2 }, { "active_id": "M6ZCTVT2LSE4KYPPODAI6K5WORHIIWQGNDKMUJD2WE2HKFN6CX4A", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 1, "pid": 295096, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 2, "verified_for_delegate": 2 } ], "passed": true } }, { "claim": "expired_and_corrupt_grants_stay_inactive_after_restart", "result": "pass", "recordedField": "/results/2", "expectedValue": { "argv": [ "/workspace/atomic-pr-tools/target-native/debug/deps/delegation_restart-024c3e55c7b51ced", "--exact", "expired_and_corrupt_grants_stay_inactive_after_restart", "--nocapture" ], "returncode": 0, "timed_out": false, "wall_seconds": 0.2147393360010028, "stdout": "case-2.stdout", "stderr": "case-2.stderr", "case": "expired_and_corrupt_grants_stay_inactive_after_restart", "observations": [ { "active_id": null, "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": false, "allows_staging": false, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295100, "scope": null, "stored": 1, "verified_for_delegate": 1 }, { "active_id": null, "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": false, "allows_staging": false, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295102, "scope": null, "stored": 3, "verified_for_delegate": 1 }, { "active_id": null, "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": false, "allows_staging": false, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295104, "scope": null, "stored": 3, "verified_for_delegate": 1 }, { "active_id": "TOQB4BPMBHHIW2UEBH6XCTYBCIXIGJX6FMSZN333J7VED7KEOXYA", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295106, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 4, "verified_for_delegate": 2 } ], "passed": true } }, { "claim": "local_selection_does_not_establish_external_issuer_authority", "result": "pass", "recordedField": "/results/3", "expectedValue": { "argv": [ "/workspace/atomic-pr-tools/target-native/debug/deps/delegation_restart-024c3e55c7b51ced", "--exact", "local_selection_does_not_establish_external_issuer_authority", "--nocapture" ], "returncode": 0, "timed_out": false, "wall_seconds": 0.11401919700074359, "stdout": "case-3.stdout", "stderr": "case-3.stderr", "case": "local_selection_does_not_establish_external_issuer_authority", "observations": [ { "active_id": "ETUSTGDNWUQKSALWLOLN5T37SDVXSAPB65UGPKCQ2CLVFAGDREUQ", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295110, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 1, "verified_for_delegate": 1 }, { "active_id": "ETUSTGDNWUQKSALWLOLN5T37SDVXSAPB65UGPKCQ2CLVFAGDREUQ", "allows_other_project": false, "allows_other_view": false, "allows_production": false, "allows_push": false, "allows_record": true, "allows_staging": true, "coverage": "local-store-selection-only", "locally_revoked": 0, "pid": 295112, "scope": { "permissions": [ "record" ], "projects": [ "acme/project" ], "servers": [ "https://staging.example.test" ], "views": [ "review/*" ], "workspaces": [] }, "stored": 2, "verified_for_delegate": 1 } ], "passed": true } }, { "claim": "upstream-maintainer-acceptance", "result": "not-exercised" }, { "claim": "outside-recurring-host-use", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" }, { "claim": "server-permission-enforcement", "result": "not-exercised" }, { "claim": "remote-revocation", "result": "not-exercised" }, { "claim": "crash-mid-write", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/atomic-delegation-2026-10-02/native-run-capsule.zip", "sha256": "ba31071e1f0a60644117e3f4c300b16b07bc75c58caf3a5259047054132c3719" }, { "path": "../experiments/atomic-delegation-2026-10-02/report.json", "sha256": "92b6cd64f85e7a87e8aee04bff128195e578acfd969170c231bbb1ac55f5f7c1" }, { "path": "../experiments/atomic-delegation-2026-10-02/provenance.json", "sha256": "15fc513822f79e2cd3e12cfd22301e7f73e139359818f062e234958d5fd40f41" } ] }, { "id": "installed-boundary-policy-2026-10-02", "atlasRevision": "1bdfce81e3afff4ec1c18afdfe3c7d423b693198", "sourceRevision": "72fc276003232e3b34aed057adc9a76db4f147e3", "readerRevision": "72fc276003232e3b34aed057adc9a76db4f147e3", "report": "../experiments/installed-boundary-policy-2026-10-02/report.json", "provenance": "../experiments/installed-boundary-policy-2026-10-02/provenance.json", "contract": "https://github.com/probityai/agent-evidence-observer/tree/72fc276003232e3b34aed057adc9a76db4f147e3/interop/model-consumer-2026-10-02", "reviewState": "author-retained-measured-record", "evidenceClaim": "author-operated-installed-reader-publication-and-quality-policy-result", "roles": { "atlasOperator": "Probity", "independentEffectCustody": "not-established", "independentOperation": "not-established", "outsideRecurringUse": "not-established", "producer": "Probity-owned workflow", "readerAuthor": "Probity", "retentionHolder": "Probity" }, "answerExposure": "Author-written cases, targets and host quality thresholds exposed; not blind.", "comparisonOrder": "Original CI execution and comparison emitted together. Selected raw Atlas retention precedes indexing at dc54f604d90278fc41c730313ffa9310a18d7ebc; it does not establish blind or independent comparison.", "limits": [ "Author-operated installed0.0.3-to0.0.4 reader and host-selected publication/quality policy; no new inference.", "Public selected capsule omits native packet duplicates and unrelated earlier workflow results; hashes cannot recreate omitted bytes.", "The complete provider original is retained separately; native compact archive and preparation originals have their own retention records.", "Evidence verification and complete measurement are distinct from selected quality acceptance, action authority, recurring outside adoption and independent effect custody." ], "claimResults": [ { "claim": "ordinary-installed-0.0.3-to0.0.4-upgrade", "result": "pass", "recordedField": "/upgrade/candidate-installation", "expectedValue": { "frameworkModules": { "agents": false, "google": false, "inspect_ai": false, "langgraph": false, "llama_cpp": false, "pydantic_ai": false }, "version": "0.0.4" } }, { "claim": "baseline-boundary-refuses-before-reader-launch", "result": "pass", "recordedField": "/upgrade/baseline-boundary/gate", "expectedValue": { "evidenceDecision": "not-verified", "launched": false, "policySha256": "493fe7fc7205681661fa89e3ab55689bc88723873854f2fd77fc46cbb599eef1", "publicationDecision": "hold", "reason": "policy fields differ" } }, { "claim": "complete-evidence-publication", "result": "pass", "recordedField": "/upgrade/candidate-boundary/gate", "expectedValue": { "casePopulation": { "authoredIdentities": 48, "casesPerFamily": 16, "pairsPerFamily": 8, "uniqueLiteralInputs": 46 }, "child": { "returncode": 0, "streams": { "reader.stderr": { "bytes": 0, "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, "reader.stdout": { "bytes": 291513, "sha256": "9b9f2d5012a66ebd1ccb7a308ab859f0fed1da948fccc3915ae40ea79e9578c0" } }, "timedOut": false }, "evidenceDecision": "verified", "launched": true, "policyFailures": [], "policySha256": "493fe7fc7205681661fa89e3ab55689bc88723873854f2fd77fc46cbb599eef1", "publicationDecision": "publish", "resources": { "completionTokens": 7498, "elapsedNs": 257401173568, "preparationPayloadBytes": 472221945, "processLifetimePeakRssKiB": 567192, "promptTokens": 35280, "returnedCallProcessCpuNs": 496051239620, "totalProcessCpuNs": 497394631919 }, "scope": "host-selected report publication; no dispatch or recovery authority" } }, { "claim": "selected-quality-policy-acceptance", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate", "expectedValue": { "casePopulation": { "authoredIdentities": 48, "casesPerFamily": 16, "pairsPerFamily": 8, "uniqueLiteralInputs": 46 }, "child": { "returncode": 0, "streams": { "reader.stderr": { "bytes": 0, "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, "reader.stdout": { "bytes": 291513, "sha256": "9b9f2d5012a66ebd1ccb7a308ab859f0fed1da948fccc3915ae40ea79e9578c0" } }, "timedOut": false }, "evidenceDecision": "verified", "launched": true, "policyFailures": [ { "field": "correct", "measured": 0, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } }, { "field": "correct", "measured": 3, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } }, { "field": "correct", "measured": 0, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } }, { "field": "correct", "measured": 3, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } }, { "field": "correct", "measured": 2, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } }, { "field": "correct", "measured": 1, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } }, { "field": "correct", "measured": 2, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } }, { "field": "correct", "measured": 1, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } }, { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } } ], "policySha256": "7e88df5bedbf75e633611e8eac4455e42e1cc6a86d1081deceb94cc85d50d50b", "publicationDecision": "hold-selected-score-or-resource", "resources": { "completionTokens": 7498, "elapsedNs": 257401173568, "preparationPayloadBytes": 472221945, "processLifetimePeakRssKiB": 567192, "promptTokens": 35280, "returnedCallProcessCpuNs": 496051239620, "totalProcessCpuNs": 497394631919 }, "scope": "host-selected report publication; no dispatch or recovery authority" } }, { "claim": "installed-smol135-q4-short24-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/0", "expectedValue": { "callElapsedNs": 4723831541, "completionTokens": 310, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 9240492026, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol135-q4-short24-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/1", "expectedValue": { "callElapsedNs": 5976613495, "completionTokens": 384, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 11693640399, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol135-q4-short24-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/2", "expectedValue": { "callElapsedNs": 7814501471, "completionTokens": 384, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 15363970770, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol135-q4-short24-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "pass", "recordedField": "/native/quality/3", "expectedValue": { "callElapsedNs": 4291221990, "completionTokens": 131, "configuration": "short24", "correct": 16, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 8, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 7754893355, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol135-q4-short24-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/4", "expectedValue": { "callElapsedNs": 5077534177, "completionTokens": 138, "configuration": "short24", "correct": 0, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 9286420480, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol135-q4-short24-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/5", "expectedValue": { "callElapsedNs": 7993651119, "completionTokens": 220, "configuration": "short24", "correct": 3, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 14628609279, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol135-q4-long96-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/6", "expectedValue": { "callElapsedNs": 6497086579, "completionTokens": 553, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 12617390214, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol135-q4-long96-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/7", "expectedValue": { "callElapsedNs": 10725354267, "completionTokens": 1041, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 20732146066, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol135-q4-long96-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/8", "expectedValue": { "callElapsedNs": 14098939614, "completionTokens": 1231, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 0, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 27341884632, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol135-q4-long96-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "pass", "recordedField": "/native/quality/9", "expectedValue": { "callElapsedNs": 4320565423, "completionTokens": 131, "configuration": "long96", "correct": 16, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 8, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 7797561488, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol135-q4-long96-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/10", "expectedValue": { "callElapsedNs": 5112517206, "completionTokens": 138, "configuration": "long96", "correct": 0, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 9348957832, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol135-q4-long96-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/11", "expectedValue": { "callElapsedNs": 7948825378, "completionTokens": 220, "configuration": "long96", "correct": 3, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 14550379810, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol360-q4-short24-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/12", "expectedValue": { "callElapsedNs": 9954980498, "completionTokens": 159, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19774843637, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol360-q4-short24-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/13", "expectedValue": { "callElapsedNs": 15309358990, "completionTokens": 384, "configuration": "short24", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 2, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 30337025043, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol360-q4-short24-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/14", "expectedValue": { "callElapsedNs": 17731268785, "completionTokens": 211, "configuration": "short24", "correct": 1, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35279417494, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 10, "scored": 16 } }, { "claim": "installed-smol360-q4-short24-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/15", "expectedValue": { "callElapsedNs": 10347515652, "completionTokens": 133, "configuration": "short24", "correct": 13, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 5, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19844845665, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol360-q4-short24-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/16", "expectedValue": { "callElapsedNs": 12744687672, "completionTokens": 151, "configuration": "short24", "correct": 2, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 24487405820, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol360-q4-short24-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/17", "expectedValue": { "callElapsedNs": 18142441570, "completionTokens": 176, "configuration": "short24", "correct": 1, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35251934237, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol360-q4-long96-unconstrained-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/18", "expectedValue": { "callElapsedNs": 9897596024, "completionTokens": 159, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19661772937, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol360-q4-long96-unconstrained-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/19", "expectedValue": { "callElapsedNs": 18560132988, "completionTokens": 573, "configuration": "long96", "correct": 0, "decoder": "unconstrained", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 36688759188, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 0, "scored": 16 } }, { "claim": "installed-smol360-q4-long96-unconstrained-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/20", "expectedValue": { "callElapsedNs": 17766238167, "completionTokens": 211, "configuration": "long96", "correct": 1, "decoder": "unconstrained", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35348355485, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 10, "scored": 16 } }, { "claim": "installed-smol360-q4-long96-schema-typed-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/21", "expectedValue": { "callElapsedNs": 10294154970, "completionTokens": 133, "configuration": "long96", "correct": 13, "decoder": "schema", "family": "typed-boundary", "formatValid": 16, "fullyCorrectPairs": 5, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 19721071852, "processLifetimePeakRssKiB": 567192, "promptTokens": 1051, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol360-q4-long96-schema-policy-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/22", "expectedValue": { "callElapsedNs": 12591439115, "completionTokens": 151, "configuration": "long96", "correct": 2, "decoder": "schema", "family": "policy-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 24186369255, "processLifetimePeakRssKiB": 567192, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "installed-smol360-q4-long96-schema-grounded-boundary-all-sixteen-targets-and-eight-pairs", "result": "fail", "recordedField": "/native/quality/23", "expectedValue": { "callElapsedNs": 18069864840, "completionTokens": 176, "configuration": "long96", "correct": 1, "decoder": "schema", "family": "grounded-boundary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 35113092656, "processLifetimePeakRssKiB": 567192, "promptTokens": 2031, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "selected-quality-smol135-q4-short24-schema-policy-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/0", "expectedValue": { "field": "correct", "measured": 0, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol135-q4-short24-schema-policy-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/1", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol135-q4-short24-schema-grounded-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/2", "expectedValue": { "field": "correct", "measured": 3, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol135-q4-short24-schema-grounded-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/3", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol135-q4-long96-schema-policy-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/4", "expectedValue": { "field": "correct", "measured": 0, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol135-q4-long96-schema-policy-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/5", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol135-q4-long96-schema-grounded-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/6", "expectedValue": { "field": "correct", "measured": 3, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol135-q4-long96-schema-grounded-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/7", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol135-q4" } } }, { "claim": "selected-quality-smol360-q4-short24-schema-policy-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/8", "expectedValue": { "field": "correct", "measured": 2, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } } }, { "claim": "selected-quality-smol360-q4-short24-schema-policy-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/9", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } } }, { "claim": "selected-quality-smol360-q4-short24-schema-grounded-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/10", "expectedValue": { "field": "correct", "measured": 1, "minimum": 8, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } } }, { "claim": "selected-quality-smol360-q4-short24-schema-grounded-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/11", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "short24", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } } }, { "claim": "selected-quality-smol360-q4-long96-schema-policy-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/12", "expectedValue": { "field": "correct", "measured": 2, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } } }, { "claim": "selected-quality-smol360-q4-long96-schema-policy-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/13", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "policy-boundary", "model": "smol360-q4" } } }, { "claim": "selected-quality-smol360-q4-long96-schema-grounded-boundary-correct", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/14", "expectedValue": { "field": "correct", "measured": 1, "minimum": 8, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } } }, { "claim": "selected-quality-smol360-q4-long96-schema-grounded-boundary-fullyCorrectPairs", "result": "fail", "recordedField": "/upgrade/candidate-boundary-quality/gate/policyFailures/15", "expectedValue": { "field": "fullyCorrectPairs", "measured": 0, "minimum": 4, "row": { "configuration": "long96", "decoder": "schema", "family": "grounded-boundary", "model": "smol360-q4" } } }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" }, { "claim": "model-action-acceptance", "result": "not-exercised" }, { "claim": "new-model-inference", "result": "not-exercised" }, { "claim": "general-benchmark-performance", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/installed-boundary-policy-2026-10-02/provenance.json", "sha256": "eab42b64b41a96050b119be7b3ac8a6be8f4030b8e24ff631e5ec180a58117b9" }, { "path": "../experiments/installed-boundary-policy-2026-10-02/report.json", "sha256": "5683be39874d2fd50c557c01e04f18dfae9d2394f84a8d73b06eb31a0b264276" }, { "path": "../experiments/installed-boundary-policy-2026-10-02/selected-capsule.zip", "sha256": "e1b29236fd546fe4fc5b0cc3a602893a08b89549c8bc393041d04d09f6f9367d" }, { "path": "../experiments/installed-boundary-policy-2026-10-02/source-contract.json", "sha256": "7f838482ac352411d389a88f550c642a82d065f8a3cac9c7dbf2976afc3c1f31" } ] }, { "id": "model-vocabulary-cpu-2026-10-03", "atlasRevision": "806abee71076def61e6a6d4f91e166d75f926459", "sourceRevision": "62f5d0c6fbd785259db2d5c8076dd844b53a0593", "readerRevision": "ff556045011010025cc95b7572bffb0dbe0dc0d6", "report": "../experiments/model-vocabulary-cpu-2026-10-03/report.json", "provenance": "../experiments/model-vocabulary-cpu-2026-10-03/provenance.json", "contract": "https://github.com/probityai/agent-evidence-observer/tree/ff556045011010025cc95b7572bffb0dbe0dc0d6/interop/local-model-vocabulary-2026-10-02", "reviewState": "author-retained-measured-record", "evidenceClaim": "authored-native-action-vocabulary-and-installed-quality-hold", "roles": { "atlasOperator": "Probity", "independentEffectCustody": "not-established", "independentOperation": "not-established", "outsideRecurringUse": "not-established", "producer": "Probity-owned workflow", "readerAuthor": "Probity", "retentionHolder": "Probity" }, "answerExposure": "Authored policy inputs and targets exposed; vocabulary intervention informed by previous 384-call results; not blind.", "comparisonOrder": "Native inference follows frozen protocol, source-bound controls and protected merge; Atlas raw retention precedes indexing at e1122b6c08915207921ca575d98115cea4790062. Same-operator replay does not establish independent custody.", "limits": [ "Finite authored CPU policy task; schema validity does not imply policy correctness.", "Installed review performs no model calls and grants no action authority.", "Same operator source-bound readback; outside producer acceptance, recurring adoption and independent effect custody remain unestablished.", "Public retention preserves all native packet members; full weights, dependency wheels, source archive and CI installed environment remain outside this capsule. Their hashes cannot reconstruct omitted bytes.", "Provider retention expiry is recorded; separate same-operator retention is not independent custody." ], "artifacts": [ { "path": "../experiments/model-vocabulary-cpu-2026-10-03/original-artifact.zip", "sha256": "eef05226335f9e2de6783ee797d891cbd1fe47058264e2d57eb41f1ec39131d8" }, { "path": "../experiments/model-vocabulary-cpu-2026-10-03/installed-capsule.zip", "sha256": "93a86439639978dc35af686b46b7b51c202a44e868d8c759a75e08cb5cd79ca9" }, { "path": "../experiments/model-vocabulary-cpu-2026-10-03/provider-inventory.json", "sha256": "e50753f843e5d42facb65ef9e20b5f5c3ff9a2e7abc98d63a7cb75577dd86339" }, { "path": "../experiments/model-vocabulary-cpu-2026-10-03/source-contract.json", "sha256": "4a3a47b14308f726af505ac489c9cb4c482cd48c09eacd3881c2fafe44f14ff7" }, { "path": "../experiments/model-vocabulary-cpu-2026-10-03/native-report.json", "sha256": "4b9638a73ce0fc8e7273fc8969cfc92467b5779903e47a501b3989b357b4d9b0" }, { "path": "../experiments/model-vocabulary-cpu-2026-10-03/installed-replay.json", "sha256": "1cde7314140f7bb9d8aad9cca1ece0cc5fee3f32c8bb0e7dcb65628a5a11fb97" }, { "path": "../experiments/model-vocabulary-cpu-2026-10-03/provenance.json", "sha256": "fefb96f1cac94f9cffbcdfd90d5434ba3dd4e2c993bf4c69c4a9d39e921d4e8f" }, { "path": "../experiments/model-vocabulary-cpu-2026-10-03/report.json", "sha256": "b921ec50bb757e06f738bdec620f3a68051e3d6ce7630460116e782e99dd2dd2" } ], "claimResults": [ { "claim": "complete-native-population", "result": "pass", "recordedField": "/native/population", "expectedValue": { "error": 0, "incomplete": 0, "planned": 128, "scored": 128, "started": 128, "unknown-start": 0, "unsupported": 0 } }, { "claim": "complete-evidence-within-declared-budget", "result": "pass", "recordedField": "/native/evidence", "expectedValue": { "complete": true, "withinRunBudget": true } }, { "claim": "control-complete-policy-correctness", "result": "fail", "recordedField": "/comparison/control", "expectedValue": { "correct": 4, "fullyCorrectPairs": 0, "planned": 64, "plannedPairs": 32 } }, { "claim": "vocabulary-complete-policy-correctness", "result": "fail", "recordedField": "/comparison/vocabulary", "expectedValue": { "correct": 18, "fullyCorrectPairs": 2, "planned": 64, "plannedPairs": 32 } }, { "claim": "default-quality--smol135-q4--short24--policy-control", "result": "fail", "recordedField": "/native/quality/0", "expectedValue": { "callElapsedNs": 3254003474, "completionTokens": 138, "configuration": "short24", "correct": 0, "decoder": "schema", "family": "policy-control", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 5877617962, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "default-quality--smol135-q4--short24--policy-vocabulary", "result": "fail", "recordedField": "/native/quality/1", "expectedValue": { "callElapsedNs": 3392850988, "completionTokens": 160, "configuration": "short24", "correct": 2, "decoder": "schema", "family": "policy-vocabulary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 6115132509, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "default-quality--smol135-q4--long96--policy-control", "result": "fail", "recordedField": "/native/quality/2", "expectedValue": { "callElapsedNs": 3234003521, "completionTokens": 138, "configuration": "long96", "correct": 0, "decoder": "schema", "family": "policy-control", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 5838096661, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "default-quality--smol135-q4--long96--policy-vocabulary", "result": "fail", "recordedField": "/native/quality/3", "expectedValue": { "callElapsedNs": 3345352631, "completionTokens": 160, "configuration": "long96", "correct": 2, "decoder": "schema", "family": "policy-vocabulary", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol135-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 6032573582, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "default-quality--smol360-q4--short24--policy-control", "result": "fail", "recordedField": "/native/quality/4", "expectedValue": { "callElapsedNs": 7927821593, "completionTokens": 151, "configuration": "short24", "correct": 2, "decoder": "schema", "family": "policy-control", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 15137474454, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "default-quality--smol360-q4--short24--policy-vocabulary", "result": "fail", "recordedField": "/native/quality/5", "expectedValue": { "callElapsedNs": 7730355000, "completionTokens": 137, "configuration": "short24", "correct": 7, "decoder": "schema", "family": "policy-vocabulary", "formatValid": 16, "fullyCorrectPairs": 1, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 14862366865, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "default-quality--smol360-q4--long96--policy-control", "result": "fail", "recordedField": "/native/quality/6", "expectedValue": { "callElapsedNs": 7953110788, "completionTokens": 151, "configuration": "long96", "correct": 2, "decoder": "schema", "family": "policy-control", "formatValid": 16, "fullyCorrectPairs": 0, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 15178022558, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "default-quality--smol360-q4--long96--policy-vocabulary", "result": "fail", "recordedField": "/native/quality/7", "expectedValue": { "callElapsedNs": 7833989075, "completionTokens": 137, "configuration": "long96", "correct": 7, "decoder": "schema", "family": "policy-vocabulary", "formatValid": 16, "fullyCorrectPairs": 1, "model": "smol360-q4", "planned": 16, "plannedPairs": 8, "processCpuNs": 15045158430, "processLifetimePeakRssKiB": 557932, "promptTokens": 1328, "resourceScope": "returned calls only; CPU is whole-process delta, RSS is lifetime peak, not task allocation", "schemaValid": 16, "scored": 16 } }, { "claim": "native-resource--elapsed_ns", "result": "pass", "recordedField": "/native/elapsed_ns", "expectedValue": 45317547439 }, { "claim": "native-resource--process_cpu_ns", "result": "pass", "recordedField": "/native/process_cpu_ns", "expectedValue": 84910453532 }, { "claim": "native-resource--nativeTokens", "result": "pass", "recordedField": "/native/nativeTokens", "expectedValue": { "completion": 1172, "prompt": 10624 } }, { "claim": "native-resource--preparation", "result": "pass", "recordedField": "/native/preparation", "expectedValue": { "complete": true, "elapsedSeconds": 8.880832050999999, "scope": "retained transfer/source selection receipts reconstructed; weights/source wheels omitted from native packet and retained in full preparation archive; not an independent transfer or inference witness", "selectedPayloadBytes": 472221945, "selectedPayloadBytesByCategory": { "dependencies": 45457867, "metadata": 30738, "model": 376044704, "source": 50688636 } } }, { "claim": "installed-replay--evidenceDecision", "result": "pass", "recordedField": "/installed/evidenceDecision", "expectedValue": "accept-scoped-evidence" }, { "claim": "installed-replay--stdoutReplayExact", "result": "pass", "recordedField": "/installed/stdoutReplayExact", "expectedValue": true }, { "claim": "installed-replay--structuredReplayExact", "result": "pass", "recordedField": "/installed/structuredReplayExact", "expectedValue": true }, { "claim": "installed-replay--evidenceOnlyStillQualityHold", "result": "pass", "recordedField": "/installed/evidenceOnlyStillQualityHold", "expectedValue": true }, { "claim": "installed-replay--mutations", "result": "pass", "recordedField": "/installed/mutations", "expectedValue": { "changedHelperReselected": "hold-evidence", "changedTerminalOriginalPins": "hold-evidence", "overBudgetTerminalReselected": "hold-evidence" } }, { "claim": "installed-replay--cumulativeSixPreparationsResponseBodyBytes", "result": "pass", "recordedField": "/installed/cumulativeSixPreparationsResponseBodyBytes", "expectedValue": 2639228307 }, { "claim": "installed-default-quality", "result": "fail", "recordedField": "/installed/consumerDecision", "expectedValue": "hold-quality" }, { "claim": "outside-producer-acceptance", "result": "not-exercised" }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" }, { "claim": "model-action-acceptance", "result": "not-exercised" }, { "claim": "general-benchmark-performance", "result": "not-exercised" }, { "claim": "independent-transfer-or-inference-witness", "result": "not-exercised" } ] }, { "id": "model-tool-arguments-cpu-2026-10-03", "atlasRevision": "91632533e3834ebefb7e96a25d2d7ca6fe9e7499", "sourceRevision": "51e0c12551339cce5898d3bfae2ba9ef3d9607f5", "readerRevision": "884814fe8cbc2e3b21d267fbaf86726c37892b14", "report": "../experiments/model-tool-arguments-cpu-2026-10-03/native-report.json", "provenance": "../experiments/model-tool-arguments-cpu-2026-10-03/provenance.json", "contract": "https://github.com/probityai/agent-evidence-observer/tree/884814fe8cbc2e3b21d267fbaf86726c37892b14/interop/local-model-tool-arguments-2026-10-03", "reviewState": "author-retained-measured-record", "evidenceClaim": "authored-native-tool-arguments-with-strict-quality-hold", "roles": { "atlasOperator": "Probity", "independentEffectCustody": "not-established", "independentOperation": "not-established", "outsideRecurringUse": "not-established", "producer": "Probity-owned workflow", "readerAuthor": "Probity", "retentionHolder": "Probity" }, "answerExposure": "Authored inputs, targets and thresholds exposed; prospective new study follows earlier 384/128-call findings; not blind.", "comparisonOrder": "Prospective protocol and reviewed source precede the protected Observer main execution; exact native provider bytes are retained additively in Atlas afterward. Neither raw retention nor replay establishes independent execution.", "limits": [ "Finite exposed authored tool-argument and abstention cases; no representative benchmark or blind evaluation.", "Native inference, evidence publication and semantic quality are separate; all eight strict quality rows hold.", "No tools or protected publication/admission/dispatch/recovery effects execute from model answers.", "Atlas retains the entire compact native provider artifact, not the complete preparation artifact containing model weights, wheels, archive and installed environment; hashes cannot reconstruct omitted bytes.", "Provider artifact expiry is disclosed; durable author-held Git bytes do not establish independent effect custody, outside acceptance or recurring adoption.", "Atlas validation reads data only and performs no new inference or installation of packet code." ], "artifacts": [ { "path": "../experiments/model-tool-arguments-cpu-2026-10-03/original-artifact.zip", "sha256": "67ef1e638e814c71bbf354fe9895ea0faf5d9ef11eae2ff76b10b065bd7a7e54" }, { "path": "../experiments/model-tool-arguments-cpu-2026-10-03/native-report.json", "sha256": "92b0a21e5fe5efc682e7b6c287a850e28847f33b4515b1a02155ad706bb673ba" }, { "path": "../experiments/model-tool-arguments-cpu-2026-10-03/provenance.json", "sha256": "158c40fb504e0e44b3dc49e5539483b03aedceb92008c5c63d05340da68ffab7" }, { "path": "../experiments/model-tool-arguments-cpu-2026-10-03/source-contract.json", "sha256": "1cf2a5f3527f72db90ad0881c5dd360bb0775f005cd4cc8971e287015fe400d4" }, { "path": "../experiments/model-tool-arguments-cpu-2026-10-03/README.md", "sha256": "3b22b8f171370927c15ea5b2e0b98df0019a08f21e00e997ca957433842fbfb2" } ], "claimResults": [ { "claim": "complete-native-population", "result": "pass", "recordedField": "/population", "expectedValue": { "error": 0, "incomplete": 0, "planned": 128, "scored": 128, "started": 128, "unknown-start": 0, "unsupported": 0 } }, { "claim": "complete-evidence-within-run-budget", "result": "pass", "recordedField": "/evidence", "expectedValue": { "complete": true, "withinRunBudget": true } }, { "claim": "scoped-evidence-publication", "result": "pass", "recordedField": "/publicationDecision", "expectedValue": "publish-scoped-report" }, { "claim": "strict-tool-quality", "result": "fail", "recordedField": "/qualityDecision", "expectedValue": "hold-tool-decision-quality" }, { "claim": "strict-quality-row--0", "result": "fail", "recordedField": "/quality/0", "expectedValue": { "configuration": "short24", "correct": 0, "correctAbstentions": 0, "formatValid": 0, "fullyCorrectPairs": 0, "mode": "control", "model": "smol135-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 0, "scored": 16, "truncatedReturns": 16 } }, { "claim": "strict-quality-row--1", "result": "fail", "recordedField": "/quality/1", "expectedValue": { "configuration": "short24", "correct": 0, "correctAbstentions": 0, "formatValid": 0, "fullyCorrectPairs": 0, "mode": "tool-schema", "model": "smol135-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 0, "scored": 16, "truncatedReturns": 16 } }, { "claim": "strict-quality-row--2", "result": "fail", "recordedField": "/quality/2", "expectedValue": { "configuration": "long96", "correct": 0, "correctAbstentions": 0, "formatValid": 16, "fullyCorrectPairs": 0, "mode": "control", "model": "smol135-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 16, "scored": 16, "truncatedReturns": 0 } }, { "claim": "strict-quality-row--3", "result": "fail", "recordedField": "/quality/3", "expectedValue": { "configuration": "long96", "correct": 0, "correctAbstentions": 0, "formatValid": 16, "fullyCorrectPairs": 0, "mode": "tool-schema", "model": "smol135-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 16, "scored": 16, "truncatedReturns": 0 } }, { "claim": "strict-quality-row--4", "result": "fail", "recordedField": "/quality/4", "expectedValue": { "configuration": "short24", "correct": 0, "correctAbstentions": 0, "formatValid": 0, "fullyCorrectPairs": 0, "mode": "control", "model": "smol360-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 0, "scored": 16, "truncatedReturns": 16 } }, { "claim": "strict-quality-row--5", "result": "fail", "recordedField": "/quality/5", "expectedValue": { "configuration": "short24", "correct": 0, "correctAbstentions": 0, "formatValid": 0, "fullyCorrectPairs": 0, "mode": "tool-schema", "model": "smol360-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 0, "scored": 16, "truncatedReturns": 16 } }, { "claim": "strict-quality-row--6", "result": "fail", "recordedField": "/quality/6", "expectedValue": { "configuration": "long96", "correct": 7, "correctAbstentions": 0, "formatValid": 16, "fullyCorrectPairs": 0, "mode": "control", "model": "smol360-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 16, "scored": 16, "truncatedReturns": 0 } }, { "claim": "strict-quality-row--7", "result": "fail", "recordedField": "/quality/7", "expectedValue": { "configuration": "long96", "correct": 7, "correctAbstentions": 0, "formatValid": 16, "fullyCorrectPairs": 0, "mode": "tool-schema", "model": "smol360-q4", "planned": 16, "plannedAbstentions": 8, "plannedPairs": 8, "schemaValid": 16, "scored": 16, "truncatedReturns": 0 } }, { "claim": "native--nativeTokens", "result": "pass", "recordedField": "/nativeTokens", "expectedValue": { "completion": 3468, "prompt": 29992 } }, { "claim": "native--resources", "result": "pass", "recordedField": "/resources", "expectedValue": { "elapsed_ns": 228445554164, "process_cpu_ns": 430234663000, "process_maxrss_kib": 577276 } }, { "claim": "native--preparationReuse", "result": "pass", "recordedField": "/preparationReuse", "expectedValue": { "inferencePerformed": false, "nativeFiles": 31, "newArchiveResponseBodyBytes": 465478943, "selectedFiles": 66, "status": "passed" } }, { "claim": "native--effectsExecuted", "result": "pass", "recordedField": "/effectsExecuted", "expectedValue": 0 }, { "claim": "native--providerCalls", "result": "pass", "recordedField": "/providerCalls", "expectedValue": 0 }, { "claim": "native--providerDollars", "result": "pass", "recordedField": "/providerDollars", "expectedValue": 0 }, { "claim": "outside-producer-acceptance", "result": "not-exercised" }, { "claim": "external-host-recurring-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" }, { "claim": "independent-inference-witness", "result": "not-exercised" }, { "claim": "model-action-acceptance", "result": "not-exercised" }, { "claim": "general-benchmark-performance", "result": "not-exercised" } ] }, { "id": "aps-jcs-2026-10-04", "atlasRevision": "419700b6a2c1bb60a77ef87d13d1a15ab057069a", "sourceRevision": "646490a834e1eca4aad230033502b73f3b5cd9d1", "readerRevision": "fa3e6705746e0131a7884591a86e5c05b6c050ab", "admissionRevision": "ecc8b5ef4b380a2fe38e5079d128307a1c702717", "contract": "https://github.com/probityai/agent-evidence-vectors/blob/fa3e6705746e0131a7884591a86e5c05b6c050ab/interop/aps-jcs/README.md", "report": "../experiments/aps-jcs-2026-10-04/report.json", "provenance": "../experiments/aps-jcs-2026-10-04/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "raw-admission-serializer-and-signed-receipt-comparison", "roles": { "producer": "Pinned public native inputs and Probity-authored finite controls", "readerAuthor": "Probity", "runner": "Probity-owned GitHub Actions", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Frozen public conformance expectations and authored receipt controls were exposed before implementation.", "comparisonOrder": "Native outputs and comparisons were emitted together; original archives and selected source were published before Atlas indexing.", "limits": [ "Two runtimes repeat the same 1,223 identities; populations remain separate.", "Parsed serialization, strict raw parsing and signed serialized receipt verification remain separate.", "The 42 parsed acceptances on raw-refusal rows include profile differences; they are not all duplicate losses.", "RFC 8785 and opt-in I-JSON numeric and Unicode policies differ; all 23 strict-parser policy rows remain retained.", "Selected licensed first-party source is retained separately from native output. Registry packages restore from integrity lockfiles; Node and Rust runtimes are not vendored.", "Author-operated conformance; separately proposed APS dependency and formal pre-run study confirmation remain separate." ], "claimResults": [ { "claim": "native-admission-outcomes--v20.20.2", "result": "pass", "recordedField": "/runs/0/summary", "expectedValue": { "corpus_cases": 1223, "expected_accepted": 1048, "aps_raw_accepted": 1069, "parsed_refusal_bypasses": 42, "raw_policy_differences": 23, "signed_receipt_controls": 5 } }, { "claim": "signed-receipt-controls--v20.20.2", "result": "pass", "recordedField": "/runs/0/receipts", "expectedValue": [ { "name": "clean", "input_sha256": "8cfcb557f79d51926b4d99dd0b265e02a7e810de73be381147a6897ef426f895", "input_bytes": 726, "serialized_verifier": { "valid": true, "status": "valid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "verified", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": true } ], "other_signatures": "none", "errors": [] } }, { "name": "duplicate-issuer", "input_sha256": "7584f31304a7348b9e715a2a452b07fd4d3450abd3e6cbefb4a2ac4e1de0c0c8", "input_bytes": 755, "serialized_verifier": { "valid": false, "status": "invalid", "receipt_id_valid": "not_checked", "stage": "not_checked", "signer_authority": "not_checked", "signature_results": [], "other_signatures": "none", "errors": [ "parse_error", "$: duplicate object member" ] }, "parse_first_verifier": { "valid": true, "status": "valid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "verified", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": true } ], "other_signatures": "none", "errors": [] } }, { "name": "escaped-duplicate-issuer", "input_sha256": "260749c25e98f7d5bbbcc6e46db91755caa3cda0e362627f1ac959aaa8ee9c30", "input_bytes": 760, "serialized_verifier": { "valid": false, "status": "invalid", "receipt_id_valid": "not_checked", "stage": "not_checked", "signer_authority": "not_checked", "signature_results": [], "other_signatures": "none", "errors": [ "parse_error", "$: duplicate object member" ] }, "parse_first_verifier": { "valid": true, "status": "valid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "verified", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": true } ], "other_signatures": "none", "errors": [] } }, { "name": "wrong-key", "input_sha256": "8cfcb557f79d51926b4d99dd0b265e02a7e810de73be381147a6897ef426f895", "input_bytes": 726, "serialized_verifier": { "valid": false, "status": "invalid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "invalid", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": false } ], "other_signatures": "none", "errors": [ "signature_invalid" ] } }, { "name": "resource-depth", "input_sha256": "91dad941059a748a11a48ad7fc3ce8b56c274ac5dc83893a530f35e62c32b886", "input_bytes": 1201, "serialized_verifier": { "valid": false, "status": "indeterminate", "receipt_id_valid": "not_checked", "stage": "not_checked", "signer_authority": "not_checked", "signature_results": [], "other_signatures": "none", "errors": [ "RESOURCE_LIMIT", "$: JSON nesting limit exceeded" ] } } ] }, { "claim": "native-admission-outcomes--v22.23.3", "result": "pass", "recordedField": "/runs/1/summary", "expectedValue": { "corpus_cases": 1223, "expected_accepted": 1048, "aps_raw_accepted": 1069, "parsed_refusal_bypasses": 42, "raw_policy_differences": 23, "signed_receipt_controls": 5 } }, { "claim": "signed-receipt-controls--v22.23.3", "result": "pass", "recordedField": "/runs/1/receipts", "expectedValue": [ { "name": "clean", "input_sha256": "8cfcb557f79d51926b4d99dd0b265e02a7e810de73be381147a6897ef426f895", "input_bytes": 726, "serialized_verifier": { "valid": true, "status": "valid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "verified", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": true } ], "other_signatures": "none", "errors": [] } }, { "name": "duplicate-issuer", "input_sha256": "7584f31304a7348b9e715a2a452b07fd4d3450abd3e6cbefb4a2ac4e1de0c0c8", "input_bytes": 755, "serialized_verifier": { "valid": false, "status": "invalid", "receipt_id_valid": "not_checked", "stage": "not_checked", "signer_authority": "not_checked", "signature_results": [], "other_signatures": "none", "errors": [ "parse_error", "$: duplicate object member" ] }, "parse_first_verifier": { "valid": true, "status": "valid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "verified", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": true } ], "other_signatures": "none", "errors": [] } }, { "name": "escaped-duplicate-issuer", "input_sha256": "260749c25e98f7d5bbbcc6e46db91755caa3cda0e362627f1ac959aaa8ee9c30", "input_bytes": 760, "serialized_verifier": { "valid": false, "status": "invalid", "receipt_id_valid": "not_checked", "stage": "not_checked", "signer_authority": "not_checked", "signature_results": [], "other_signatures": "none", "errors": [ "parse_error", "$: duplicate object member" ] }, "parse_first_verifier": { "valid": true, "status": "valid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "verified", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": true } ], "other_signatures": "none", "errors": [] } }, { "name": "wrong-key", "input_sha256": "8cfcb557f79d51926b4d99dd0b265e02a7e810de73be381147a6897ef426f895", "input_bytes": 726, "serialized_verifier": { "valid": false, "status": "invalid", "receipt_id_valid": true, "stage": { "status": "valid", "receipt_type": "aps:action-intent:v1", "stage": "action-intent", "boundary_identity": "not_applicable", "failures": [] }, "signer_authority": "invalid", "signature_results": [ { "signer": "did:example:agent", "key_id": "k1", "required": true, "valid": false } ], "other_signatures": "none", "errors": [ "signature_invalid" ] } }, { "name": "resource-depth", "input_sha256": "91dad941059a748a11a48ad7fc3ce8b56c274ac5dc83893a530f35e62c32b886", "input_bytes": 1201, "serialized_verifier": { "valid": false, "status": "indeterminate", "receipt_id_valid": "not_checked", "stage": "not_checked", "signer_authority": "not_checked", "signature_results": [], "other_signatures": "none", "errors": [ "RESOURCE_LIMIT", "$: JSON nesting limit exceeded" ] } } ] }, { "claim": "cross-runtime-machine-agreement", "result": "pass", "recordedField": "/machineOutcomesAgree", "expectedValue": true }, { "claim": "cross-runtime-receipt-agreement", "result": "pass", "recordedField": "/receiptOutcomesAgree", "expectedValue": true }, { "claim": "diagnostic-prose-differences", "result": "pass", "recordedField": "/diagnosticProseDifferences", "expectedValue": 88 }, { "claim": "outside-recurring-host-adoption", "result": "not-exercised" }, { "claim": "independently-operated-custody", "result": "not-exercised" }, { "claim": "formal-frozen-APS-study", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/aps-jcs-2026-10-04/README.md", "sha256": "6d564505ed6e1e8e62ad6b5c4d75ad18fafd77e1957698907ef3a3d8d9911746" }, { "path": "../experiments/aps-jcs-2026-10-04/native-manifest.json", "sha256": "7f2c2393d051263aa5741d1b24359a9189fd9af23872e61ecfcd53209f528061" }, { "path": "../experiments/aps-jcs-2026-10-04/original-node20.zip", "sha256": "89b48e8a1b93bf1e5b819e9cdad53237ca6711b83130cad83b2e6bae1f79248a" }, { "path": "../experiments/aps-jcs-2026-10-04/original-node22.zip", "sha256": "68d7c8602d44d93688be5e4a933f21eb7573d9ffcde01257ffa361bc387c35a2" }, { "path": "../experiments/aps-jcs-2026-10-04/provenance.json", "sha256": "fde1456aee1f9bffbeec63532d677707f86c1b2147a17e26503ac7d479070740" }, { "path": "../experiments/aps-jcs-2026-10-04/report.json", "sha256": "96b5bb6eef3e61c8ff9925c93dbf934bbc5c537808a450282753b4c8f1a3d88c" }, { "path": "../experiments/aps-jcs-2026-10-04/runtime-comparison.json", "sha256": "ade9968728f4969b3d8c26145225162d771da47049b6985b173c5a9490defb8e" }, { "path": "../experiments/aps-jcs-2026-10-04/selected-source.zip", "sha256": "e0c7ef56651ec4bd362ebfb0057e786d485247a0ebcdecc3ac88d07ae29f9bb9" }, { "path": "../experiments/aps-jcs-2026-10-04/source-lock.json", "sha256": "66b55ebc6bd99035e399379a07d9a3304665d7e99bdab9229829f198217cbb64" }, { "path": "../experiments/aps-jcs-2026-10-04/source-manifest.json", "sha256": "8c1c6b51af1e074310505269526581a06b0e45256e604998b80130b46fc3658c" }, { "path": "../experiments/aps-jcs-2026-10-04/validate_capsule.py", "sha256": "c75fa2d339f91563525ba9e11df6632d5ce1e756cd1c8377a82aa269d643767e" } ] }, { "id": "google-adk-responses-2026-10-04", "atlasRevision": "419700b6a2c1bb60a77ef87d13d1a15ab057069a", "sourceRevision": "86a47f6974bae349a5c9ea15a74a4b450614ae42", "readerRevision": "de522aa60966309599d03b06d02f50a52d7fb58f", "verifyRevision": "e835ce2bd6a960e7a1cc2fa6522f16d55dce728a", "contract": "https://github.com/probityai/agent-evidence-observer/blob/de522aa60966309599d03b06d02f50a52d7fb58f/interop/adk-user-responses-2026-10-04/README.md", "report": "../experiments/google-adk-responses-2026-10-04/report.json", "provenance": "../experiments/google-adk-responses-2026-10-04/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "native-user-response-routing-callback-effect-and-separate-verify-comparison", "roles": { "producer": "Actual pinned Google ADK Runner with fixed public BaseLlm responses", "readerAuthor": "Probity", "runner": "Probity-owned GitHub Actions", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established; author-operated PEER", "outsideRecurringUse": "not-established" }, "answerExposure": "Fixed public model responses, authored controls and expected outcomes were exposed before execution.", "comparisonOrder": "Native outputs and assertions were emitted together. Failed, corrected, PR and merged-main originals were retained before Atlas indexing.", "limits": [ "Three finite three-turn cases on each fully qualified execution; resumability disabled.", "Actual ADK framework with a fixed public BaseLlm script, no provider inference or model-quality measurement.", "The LRO write is a same-author host completion, separate from the native start-only tool body.", "Two distinct Observer/witness keys remain author-held PEER custody with author-operated storage and clock.", "Actual Verify event_absence/v1 covers the six plugin-delivered native turns; whole-second projections retain original fractional timestamps separately.", "First failed reader attempt and intermediate correction remain separate original archives.", "The older 16-row comparison remains pinned separately; the prospective eight-task implementation-owned study has not started.", "Restore the originally empty denied-workspace directory before installed-reader replay; no file bytes change." ], "claimResults": [ { "claim": "issuing-call-later-root-and-effects--37202968778", "result": "pass", "recordedField": "/qualifiedRuns/0/rows", "expectedValue": [ { "case": "approval-granted", "modelCalls": 4, "nativeLaterTextAuthors": [ "root" ], "nativeResponseAuthors": [ "issuer" ], "observedWrites": 1, "toolBodyCalls": 1, "originalTool": "approved_write", "originalCallId": "adk-667a6b80-69fb-48c8-843a-3df3cac1cb75", "suppliedResponseId": "adk-588b1668-63bc-4f0e-91e5-6132f1b78321", "suppliedResponseName": "adk_request_confirmation", "callbacks": 38, "callbackFailures": 0, "callbackClosed": true, "hostCompletionCalls": 0 }, { "case": "approval-denied", "modelCalls": 4, "nativeLaterTextAuthors": [ "root" ], "nativeResponseAuthors": [ "issuer" ], "observedWrites": 0, "toolBodyCalls": 0, "originalTool": "approved_write", "originalCallId": "adk-f52a4db5-10d4-4a6c-91cf-b2dff1127cb3", "suppliedResponseId": "adk-1a4746ff-ef4e-4e63-bd11-8b7cbcb3f89b", "suppliedResponseName": "adk_request_confirmation", "callbacks": 38, "callbackFailures": 0, "callbackClosed": true, "hostCompletionCalls": 0 }, { "case": "long-running-completed", "modelCalls": 4, "nativeLaterTextAuthors": [ "root" ], "nativeResponseAuthors": [ "issuer" ], "observedWrites": 1, "toolBodyCalls": 1, "originalTool": "pending_work", "originalCallId": "adk-9242db5f-cd27-4187-84d3-86e392d5a13f", "suppliedResponseId": "adk-9242db5f-cd27-4187-84d3-86e392d5a13f", "suppliedResponseName": "pending_work", "callbacks": 33, "callbackFailures": 0, "callbackClosed": true, "hostCompletionCalls": 1 } ] }, { "claim": "installed-routing-reader-repeat--37202968778", "result": "pass", "recordedField": "/qualifiedRuns/0/routingRepeatedByteExact", "expectedValue": true }, { "claim": "native-semantic-controls--37202968778", "result": "pass", "recordedField": "/qualifiedRuns/0/semanticControls", "expectedValue": 19 }, { "claim": "actual-verify-six-repeated-cases--37202968778", "result": "pass", "recordedField": "/qualifiedRuns/0/verify/rows", "expectedValue": [ { "absentEventType": "root-native-output", "case": "approval-granted/user-response", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "cd0b642354bc383fd1925792f31a1f3573e5cc6ae43f9634a6d51eff65980bad", "literalRepeat": true, "nativeEvents": 2 }, { "absentEventType": "issuer-native-output", "case": "approval-granted/later-plain-text", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "1aaabab7657619dab70aba8baab2c48b527260c7ad0ae50dbd0847dc730de4e4", "literalRepeat": true, "nativeEvents": 1 }, { "absentEventType": "root-native-output", "case": "approval-denied/user-response", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "8c710e3026bf7ae1cf512af1cb1e5d299b373ce7d025bdc15e650d99d014884a", "literalRepeat": true, "nativeEvents": 2 }, { "absentEventType": "issuer-native-output", "case": "approval-denied/later-plain-text", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "e45e7ffb23a0199481ee1d4c15d29e0f5163119821aeb157cfdf2c034533cdd7", "literalRepeat": true, "nativeEvents": 1 }, { "absentEventType": "root-native-output", "case": "long-running-completed/user-response", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "0aade8aff7b2b7774005d4d986afcb793768cfb8e99a8f8b1dffa33ec497b3b2", "literalRepeat": true, "nativeEvents": 1 }, { "absentEventType": "issuer-native-output", "case": "long-running-completed/later-plain-text", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "85cf4144e9e2050ff00228ef79aaea6b50c9a6190db0dd8664c46c1612738684", "literalRepeat": true, "nativeEvents": 1 } ] }, { "claim": "actual-verify-boundary-controls--37202968778", "result": "pass", "recordedField": "/qualifiedRuns/0/verify/controls", "expectedValue": [ { "control": "event-present", "decision": "contradicted", "reselectedBytes": true }, { "control": "coverage-unknown", "decision": "not_established", "reselectedBytes": true }, { "control": "malformed-duplicate", "exitStatus": 2, "verdictBytes": 0 } ] }, { "claim": "issuing-call-later-root-and-effects--37204220648", "result": "pass", "recordedField": "/qualifiedRuns/1/rows", "expectedValue": [ { "case": "approval-granted", "modelCalls": 4, "nativeLaterTextAuthors": [ "root" ], "nativeResponseAuthors": [ "issuer" ], "observedWrites": 1, "toolBodyCalls": 1, "originalTool": "approved_write", "originalCallId": "adk-ac817898-5c72-479b-8174-0fdf4d0c87fd", "suppliedResponseId": "adk-770a44ee-4c17-42ee-a2c4-22eb1b551d02", "suppliedResponseName": "adk_request_confirmation", "callbacks": 38, "callbackFailures": 0, "callbackClosed": true, "hostCompletionCalls": 0 }, { "case": "approval-denied", "modelCalls": 4, "nativeLaterTextAuthors": [ "root" ], "nativeResponseAuthors": [ "issuer" ], "observedWrites": 0, "toolBodyCalls": 0, "originalTool": "approved_write", "originalCallId": "adk-3c80001d-91fe-4f13-8d46-07621a8f7b04", "suppliedResponseId": "adk-11c412d9-f1ad-404f-89bb-fc4118482370", "suppliedResponseName": "adk_request_confirmation", "callbacks": 38, "callbackFailures": 0, "callbackClosed": true, "hostCompletionCalls": 0 }, { "case": "long-running-completed", "modelCalls": 4, "nativeLaterTextAuthors": [ "root" ], "nativeResponseAuthors": [ "issuer" ], "observedWrites": 1, "toolBodyCalls": 1, "originalTool": "pending_work", "originalCallId": "adk-08e466dd-355f-4ee6-aa48-71a5e46a1a77", "suppliedResponseId": "adk-08e466dd-355f-4ee6-aa48-71a5e46a1a77", "suppliedResponseName": "pending_work", "callbacks": 33, "callbackFailures": 0, "callbackClosed": true, "hostCompletionCalls": 1 } ] }, { "claim": "installed-routing-reader-repeat--37204220648", "result": "pass", "recordedField": "/qualifiedRuns/1/routingRepeatedByteExact", "expectedValue": true }, { "claim": "native-semantic-controls--37204220648", "result": "pass", "recordedField": "/qualifiedRuns/1/semanticControls", "expectedValue": 19 }, { "claim": "actual-verify-six-repeated-cases--37204220648", "result": "pass", "recordedField": "/qualifiedRuns/1/verify/rows", "expectedValue": [ { "absentEventType": "root-native-output", "case": "approval-granted/user-response", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "97b09c75cbfdcd1dd62a12b20eb9184fc96d46b0fec3520af91dc4a11afc6c02", "literalRepeat": true, "nativeEvents": 2 }, { "absentEventType": "issuer-native-output", "case": "approval-granted/later-plain-text", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "b4c50a200af01b081c5eb43c39f0b88f2a6e1f4504e3314d057884879cdea769", "literalRepeat": true, "nativeEvents": 1 }, { "absentEventType": "root-native-output", "case": "approval-denied/user-response", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "fca7b255c10093157575d130680972c73004829a49afa4b3e0d29cc2eb0cef31", "literalRepeat": true, "nativeEvents": 2 }, { "absentEventType": "issuer-native-output", "case": "approval-denied/later-plain-text", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "95a3dd7ca99859b4f404cd39ef431cfef75f9896c8829460fce3d03d4b619f36", "literalRepeat": true, "nativeEvents": 1 }, { "absentEventType": "root-native-output", "case": "long-running-completed/user-response", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "f93900a1cca64fe9a13b787e604faa7abfdba0f0daf8753c008e360cca43214d", "literalRepeat": true, "nativeEvents": 1 }, { "absentEventType": "issuer-native-output", "case": "long-running-completed/later-plain-text", "claimType": "event_absence/v1", "decision": "supported", "decisionSHA256": "b07847192acbc7463bf82d53b91ba03daedb04801ee1252197fdb5e57526e213", "literalRepeat": true, "nativeEvents": 1 } ] }, { "claim": "actual-verify-boundary-controls--37204220648", "result": "pass", "recordedField": "/qualifiedRuns/1/verify/controls", "expectedValue": [ { "control": "event-present", "decision": "contradicted", "reselectedBytes": true }, { "control": "coverage-unknown", "decision": "not_established", "reselectedBytes": true }, { "control": "malformed-duplicate", "exitStatus": 2, "verdictBytes": 0 } ] }, { "claim": "outside-recurring-host-adoption", "result": "not-exercised" }, { "claim": "independently-operated-effect-custody", "result": "not-exercised" }, { "claim": "prospective-eight-task-study", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/google-adk-responses-2026-10-04/README.md", "sha256": "3b54f04d4a5fe7f87d96cde302b34301f4e6876a8ada71b436e033d6c316a5d4" }, { "path": "../experiments/google-adk-responses-2026-10-04/first-failed-artifact.zip", "sha256": "b6080fea3c0dcd50e9de2c9b853aedea673b007490cc47f550f0dda1dffb3f2a" }, { "path": "../experiments/google-adk-responses-2026-10-04/label-correction-artifact.zip", "sha256": "ad66c11b615d0e020dedaecba7121a89bc0ce9225e5e877f6dd679cca5d216b7" }, { "path": "../experiments/google-adk-responses-2026-10-04/main-artifact.zip", "sha256": "24cb05e6dcc2226ada9acccd6ebec4c671503a9e7109572a267c5ac99ddd4283" }, { "path": "../experiments/google-adk-responses-2026-10-04/native-manifest.json", "sha256": "e483477122adeff59e9b730dff89c6813aaee0709ed397fb58dcf91b15d4fefd" }, { "path": "../experiments/google-adk-responses-2026-10-04/original-artifact.zip", "sha256": "c9f86ee644798ed44f902484d195ed05c94fb85b92b96ab897b61537fad46e9d" }, { "path": "../experiments/google-adk-responses-2026-10-04/provenance.json", "sha256": "b731ed1ae4d75c575170a2a9c0eafb1091923e108d98785e426c0903c8706475" }, { "path": "../experiments/google-adk-responses-2026-10-04/report.json", "sha256": "3bea6fcbce2faf040206f299b0336c85822023e765541bff645c6cc7efa399f1" }, { "path": "../experiments/google-adk-responses-2026-10-04/validate_capsule.py", "sha256": "a1fc9fc7e5a44f51e78344807f4284790cf930a9b632112badb00ca3fb2a4dc3" } ] }, { "id": "go-jcs-2026-10-04", "sourceRevision": "19d51d7fe467d4706a3ff08adf8a748f29fc21e0", "readerRevision": "7573937b882de4f32cbc4cd69dfaab8098729412", "contract": "https://github.com/probityai/jcs-admit/blob/7573937b882de4f32cbc4cd69dfaab8098729412/interop/go-jcs/README.md", "report": "../experiments/go-jcs-2026-10-04/report.json", "provenance": "../experiments/go-jcs-2026-10-04/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "raw-input-admission-and-pinned-go-canonical-byte-comparison", "roles": { "producer": "Public RFC, Go-rail, attack and Node number fixtures; Probity-authored finite controls", "readerAuthor": "Probity", "runner": "Probity-owned GitHub Actions", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-exercised", "outsideRecurringUse": "not-established" }, "answerExposure": "Public fixture expectations and finite controls were available before implementation.", "comparisonOrder": "Native outputs and comparisons were emitted together; all four originals were byte-retained before Atlas indexing.", "limits": [ "Finite conformance inputs and exposed expected answers; no task or workload experiment.", "Six executions on two Go runtimes repeat the same 1,263 case identities: two final-PR, two branch-push and two merged-main runs; each stays separate.", "Go accepts objects or arrays; number samples use declared array wrappers, admitted scalar roots refuse separately.", "RFC 8785 and I-JSON policies differ; bare Go outcomes remain separate from admission policy.", "The original native archives retain source and reports. Installed executable hashes are recorded, but executables and the full installed runtime are outside those provider archives.", "The upstream multi-gigabyte number benchmark was not selected." ], "claimResults": [ { "claim": "complete-conformance-outcomes--pull-request-go1.27.1", "result": "pass", "recordedField": "/runs/0/summary", "expectedValue": { "cases": 1263, "consumer_exact_byte_matches": 1077, "raw_admission_refusals": 181, "scalar_domain_refusals": 5, "bare_go_observations": 1263 } }, { "claim": "bare-go-outcomes-retained--pull-request-go1.27.1", "result": "pass", "recordedField": "/runs/0/bareGoAccepted", "expectedValue": 1129 }, { "claim": "clean-native-worktree--pull-request-go1.27.1", "result": "pass", "recordedField": "/runs/0/worktreeStatus", "expectedValue": [] }, { "claim": "complete-conformance-outcomes--pull-request-go1.25.5", "result": "pass", "recordedField": "/runs/1/summary", "expectedValue": { "cases": 1263, "consumer_exact_byte_matches": 1077, "raw_admission_refusals": 181, "scalar_domain_refusals": 5, "bare_go_observations": 1263 } }, { "claim": "bare-go-outcomes-retained--pull-request-go1.25.5", "result": "pass", "recordedField": "/runs/1/bareGoAccepted", "expectedValue": 1129 }, { "claim": "clean-native-worktree--pull-request-go1.25.5", "result": "pass", "recordedField": "/runs/1/worktreeStatus", "expectedValue": [] }, { "claim": "complete-conformance-outcomes--push-go1.25.5", "result": "pass", "recordedField": "/runs/2/summary", "expectedValue": { "cases": 1263, "consumer_exact_byte_matches": 1077, "raw_admission_refusals": 181, "scalar_domain_refusals": 5, "bare_go_observations": 1263 } }, { "claim": "bare-go-outcomes-retained--push-go1.25.5", "result": "pass", "recordedField": "/runs/2/bareGoAccepted", "expectedValue": 1129 }, { "claim": "clean-native-worktree--push-go1.25.5", "result": "pass", "recordedField": "/runs/2/worktreeStatus", "expectedValue": [] }, { "claim": "complete-conformance-outcomes--push-go1.27.1", "result": "pass", "recordedField": "/runs/3/summary", "expectedValue": { "cases": 1263, "consumer_exact_byte_matches": 1077, "raw_admission_refusals": 181, "scalar_domain_refusals": 5, "bare_go_observations": 1263 } }, { "claim": "bare-go-outcomes-retained--push-go1.27.1", "result": "pass", "recordedField": "/runs/3/bareGoAccepted", "expectedValue": 1129 }, { "claim": "clean-native-worktree--push-go1.27.1", "result": "pass", "recordedField": "/runs/3/worktreeStatus", "expectedValue": [] }, { "claim": "outside-recurring-host-adoption", "result": "not-exercised" }, { "claim": "independently-operated-custody", "result": "not-exercised" }, { "claim": "task-or-workload-execution", "result": "not-exercised" }, { "claim": "complete-conformance-outcomes--main-go1.25.5", "result": "pass", "recordedField": "/runs/4/summary", "expectedValue": { "cases": 1263, "consumer_exact_byte_matches": 1077, "raw_admission_refusals": 181, "scalar_domain_refusals": 5, "bare_go_observations": 1263 } }, { "claim": "bare-go-outcomes-retained--main-go1.25.5", "result": "pass", "recordedField": "/runs/4/bareGoAccepted", "expectedValue": 1129 }, { "claim": "clean-native-worktree--main-go1.25.5", "result": "pass", "recordedField": "/runs/4/worktreeStatus", "expectedValue": [] }, { "claim": "complete-conformance-outcomes--main-go1.27.1", "result": "pass", "recordedField": "/runs/5/summary", "expectedValue": { "cases": 1263, "consumer_exact_byte_matches": 1077, "raw_admission_refusals": 181, "scalar_domain_refusals": 5, "bare_go_observations": 1263 } }, { "claim": "bare-go-outcomes-retained--main-go1.27.1", "result": "pass", "recordedField": "/runs/5/bareGoAccepted", "expectedValue": 1129 }, { "claim": "clean-native-worktree--main-go1.27.1", "result": "pass", "recordedField": "/runs/5/worktreeStatus", "expectedValue": [] } ], "artifacts": [ { "path": "../experiments/go-jcs-2026-10-04/README.md", "sha256": "1adf30db6ae10b14cf14f1d24e1f6cc06deb0854e93af79cddb8d3c81754c037" }, { "path": "../experiments/go-jcs-2026-10-04/main-go1.25.5-report.json", "sha256": "36a06e6d0f67890100a47d8c4f3b8c2b6ca4d088552f0f3bda487518d734d449" }, { "path": "../experiments/go-jcs-2026-10-04/main-go1.25.5.zip", "sha256": "c17c9dc62e887ed592201c6fdd154df4f27071741438c83a9c6858b1b0798a60" }, { "path": "../experiments/go-jcs-2026-10-04/main-go1.27.1-report.json", "sha256": "153858305f7328866be7d2a00072df22200b5274e5d969ae76a8cacc755166c0" }, { "path": "../experiments/go-jcs-2026-10-04/main-go1.27.1.zip", "sha256": "ad11325a8298558c8d2db6725871caaf51204d4bd4b49e96c222a1780f0bada2" }, { "path": "../experiments/go-jcs-2026-10-04/provenance.json", "sha256": "450c91415d71bc1280ffb9502b3ec9f8f72238ed5114c40f3514a11f23bcda5b" }, { "path": "../experiments/go-jcs-2026-10-04/pull-request-go1.25.5-report.json", "sha256": "9ef8fd237ba820ee6f0b987a2e7815290a258a3a6c45592d87122f68b9526818" }, { "path": "../experiments/go-jcs-2026-10-04/pull-request-go1.25.5.zip", "sha256": "63fcfc2cbfb0ede901305ccbc25cf9addeaa50e831b770cca6038fa3312df120" }, { "path": "../experiments/go-jcs-2026-10-04/pull-request-go1.27.1-report.json", "sha256": "23ceec37d3d440b43d755b33de60e28d67a6f0f09297cc3f2f82eca90ecac7ee" }, { "path": "../experiments/go-jcs-2026-10-04/pull-request-go1.27.1.zip", "sha256": "cc36ef263594c0b556e5440e94dc4232ffcf8512b41036684786fe0e255ed37e" }, { "path": "../experiments/go-jcs-2026-10-04/push-go1.25.5-report.json", "sha256": "04b51d60f42fa286f5e3eb92633e9432c44f7a2541497b5225742601d40bc5cd" }, { "path": "../experiments/go-jcs-2026-10-04/push-go1.25.5.zip", "sha256": "9aa87226b34dc0f824db057809bfa0f1d3d1f2e5ae9d523a9c8b5c7aaa866b2e" }, { "path": "../experiments/go-jcs-2026-10-04/push-go1.27.1-report.json", "sha256": "4f9bd064c46aae47f104e8b0eff0629460b10703d89bb2c4de96a70c254a153d" }, { "path": "../experiments/go-jcs-2026-10-04/push-go1.27.1.zip", "sha256": "44865d54036bc4186cb7a5e041c8632147ab0d1d749b4ca8c03f1955bec93d1b" }, { "path": "../experiments/go-jcs-2026-10-04/report.json", "sha256": "542c349084e338972dc9bd57254e09be0b9dc0ea12686be3d86e0dd61e050394" }, { "path": "../experiments/go-jcs-2026-10-04/source-pins.json", "sha256": "ed4fbcfea9808c6b4d8b29b3ed57e9ebda228268e7c0a9a3059ab21d2b325f52" }, { "path": "../experiments/go-jcs-2026-10-04/validate_capsule.py", "sha256": "22a6b5313d42f32f1a898f8421d8c7a7f8da0d91dc8672da024a6361386a14f6" } ], "atlasRevision": "419700b6a2c1bb60a77ef87d13d1a15ab057069a" }, { "id": "ag2-push-authority-2026-10-04", "sourceRevision": "fd789e3ca8a77d14c8e3e89923665fe62c00cb9a", "readerRevision": "4b5ca47854c9be2814eeb5fe6f72b79b0182d2c7", "contract": "https://github.com/probityai/agent-evidence-observer/blob/4b5ca47854c9be2814eeb5fe6f72b79b0182d2c7/interop/ag2-push-authority-2026-10-04/README.md", "report": "../experiments/ag2-push-authority-2026-10-04/report.json", "provenance": "../experiments/ag2-push-authority-2026-10-04/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "native-task-and-push-url-admission-dispatch-target-and-observed-effect-comparison", "roles": { "producer": "Pinned native AG2 TestConfig and A2A Python, with Probity-authored finite controls", "readerAuthor": "Probity", "runner": "Probity-owned GitHub Actions", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "not-established", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "Public fixed responses and finite expected outcomes were exposed before execution.", "comparisonOrder": "Original failures and passing native archives were retained before Lab indexing.", "limits": [ "18 finite actual native tasks per qualified run; fixed answers and no provider inference.", "Explicit same-author post-completion sender call; no automatic task callback dispatch.", "Controlled ASGI target and native plaintext gRPC loopback; no external callback target.", "PEER keys, target and custody; no outside operator or host adoption.", "Original native JSON and wire bytes retained; the reader checks JSON semantics without decoding protobuf wire.", "Older 16 rows unchanged; prospective eight-task study not started." ], "claimResults": [ { "claim": "native-task-population--pull-request", "result": "pass", "recordedField": "/qualifiedRuns/0/nativeTasks", "expectedValue": 18 }, { "claim": "target-callbacks--pull-request", "result": "pass", "recordedField": "/qualifiedRuns/0/targetCallbacks", "expectedValue": 6 }, { "claim": "observed-writes--pull-request", "result": "pass", "recordedField": "/qualifiedRuns/0/observedWrites", "expectedValue": 3 }, { "claim": "semantic-controls--pull-request", "result": "pass", "recordedField": "/qualifiedRuns/0/semanticControls", "expectedValue": 16 }, { "claim": "installed-reader-repeat--pull-request", "result": "pass", "recordedField": "/qualifiedRuns/0/readerRepeatedByteExact", "expectedValue": true }, { "claim": "native-task-population--main", "result": "pass", "recordedField": "/qualifiedRuns/1/nativeTasks", "expectedValue": 18 }, { "claim": "target-callbacks--main", "result": "pass", "recordedField": "/qualifiedRuns/1/targetCallbacks", "expectedValue": 6 }, { "claim": "observed-writes--main", "result": "pass", "recordedField": "/qualifiedRuns/1/observedWrites", "expectedValue": 3 }, { "claim": "semantic-controls--main", "result": "pass", "recordedField": "/qualifiedRuns/1/semanticControls", "expectedValue": 16 }, { "claim": "installed-reader-repeat--main", "result": "pass", "recordedField": "/qualifiedRuns/1/readerRepeatedByteExact", "expectedValue": true }, { "claim": "outside-effect-custody", "result": "not-exercised" }, { "claim": "automatic-task-dispatch", "result": "not-exercised" }, { "claim": "callback-network-service", "result": "not-exercised" }, { "claim": "recurring-consumer-adoption", "result": "not-exercised" }, { "claim": "provider-or-model-quality", "result": "not-exercised" }, { "claim": "configuration-callback-effect-matrix--pull-request", "result": "pass", "recordedField": "/qualifiedRuns/0/decision/rows", "expectedValue": [ { "case": "jsonrpc/accepted", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 1, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "jsonrpc/registration-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "jsonrpc/dispatch-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "jsonrpc/target-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "jsonrpc/legacy-config-only", "explicitDispatch": false, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "jsonrpc/sdk-policy-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "rest/accepted", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 1, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "rest/registration-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "rest/dispatch-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "rest/target-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "rest/legacy-config-only", "explicitDispatch": false, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "rest/sdk-policy-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "grpc/accepted", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 1, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "grpc/registration-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "grpc/dispatch-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "grpc/target-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "grpc/legacy-config-only", "explicitDispatch": false, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "grpc/sdk-policy-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 } ] }, { "claim": "configuration-callback-effect-matrix--main", "result": "pass", "recordedField": "/qualifiedRuns/1/decision/rows", "expectedValue": [ { "case": "jsonrpc/accepted", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 1, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "jsonrpc/registration-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "jsonrpc/dispatch-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "jsonrpc/target-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "jsonrpc/legacy-config-only", "explicitDispatch": false, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "jsonrpc/sdk-policy-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "rest/accepted", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 1, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "rest/registration-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "rest/dispatch-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "rest/target-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "rest/legacy-config-only", "explicitDispatch": false, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "rest/sdk-policy-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "grpc/accepted", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 1, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "grpc/registration-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 }, { "case": "grpc/dispatch-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "grpc/target-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 1 }, { "case": "grpc/legacy-config-only", "explicitDispatch": false, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 1, "targetCallbacks": 0 }, { "case": "grpc/sdk-policy-denied", "explicitDispatch": true, "modelCalls": 1, "nativeTasks": 1, "observedWrites": 0, "storedConfigs": 0, "targetCallbacks": 0 } ] } ], "artifacts": [ { "path": "../experiments/ag2-push-authority-2026-10-04/AG2-PR70-FIRST-FAILED-ARTIFACTS.json", "sha256": "f7417e1fb877d3f5934f143cc38ad9e2905476e8f5ac6776507d09441efcd6f6" }, { "path": "../experiments/ag2-push-authority-2026-10-04/AG2-PR70-FIRST-FAILED-JOB.log", "sha256": "989ef29567fd46e9d4d4b2825341cf31cbd859af0a176035c6937089f3f36c72" }, { "path": "../experiments/ag2-push-authority-2026-10-04/AG2-PR70-FIRST-FAILED-JOBS.json", "sha256": "183a92c3ac135f11f6f9292e8aa2443201fc730b390766e1c23d6d3573e7c972" }, { "path": "../experiments/ag2-push-authority-2026-10-04/README.md", "sha256": "0f766a9919e46d63281dc503bcbf6c8d9e1f0f78988fbd2311f2b2533f5d1282" }, { "path": "../experiments/ag2-push-authority-2026-10-04/first-local-original.zip", "sha256": "5d0ca756502d04298195942283aa0cd3558c45f9410e174da4cef92b7224ea1d" }, { "path": "../experiments/ag2-push-authority-2026-10-04/main-artifact.zip", "sha256": "1e1eb76e719cbd21ad9aa3935aa757b83756cd6a742fd2a5b828010c0cff6e14" }, { "path": "../experiments/ag2-push-authority-2026-10-04/original-artifact.zip", "sha256": "636df5972a318b862abf44b68f52e00f6f57cc9526bad1f26a886ef014360568" }, { "path": "../experiments/ag2-push-authority-2026-10-04/provenance.json", "sha256": "08cd4f63917daefb955879e752abb9ed2f84efb131f0818cc99d6102b77ad745" }, { "path": "../experiments/ag2-push-authority-2026-10-04/report.json", "sha256": "1c8eebd082e111d3c6bea6309f991545a0c86b6b2fb535374684da44027f2403" }, { "path": "../experiments/ag2-push-authority-2026-10-04/validate_capsule.py", "sha256": "6f8f3d21c482587aa0cc76987a487fb902e55f2b79ebccb49287eaf798b5fef0" } ], "atlasRevision": "91824c04833725b208842a8fcc523c7e91a3f8e4" }, { "id": "remora-boundary-2026-10-04", "readerRevision": "308c5b4401b18d42ed73dea80459375932e6b8e8", "contract": "https://github.com/darklordVirtual/REMORA-research/blob/fe324dd734734d9227aa894330ac52c2bb916b94/artifacts/interop/index.json", "report": "../experiments/remora-boundary-2026-10-04/report.json", "provenance": "../experiments/remora-boundary-2026-10-04/provenance.json", "reviewState": "producer-review-pending-submission", "evidenceClaim": "verifier-behavior-on-public-producer-fixtures", "roles": { "readerAuthor": "Probity", "runner": "Probity-owned GitHub Actions", "producer": "REMORA", "independentOperation": "not-established", "independentEffectCustody": "not-established" }, "answerExposure": "Expected outcomes are inside the frozen fixtures and the reader compares against them; not answer-blind. Whether reference-verifier text was read while the reader was written is not recorded.", "comparisonOrder": "Native outputs and comparisons were emitted together in one run.", "limits": [ "Run records state SECOND_IMPLEMENTATION, EXTERNAL operator and NOT_INDEPENDENT; under REMORA's rule they support REPRODUCED, not EXTERNALLY_VERIFIED.", "Authorization signatures use a public test-only HMAC key created and checked by the reader; no REMORA-issued authorization is authenticated.", "The effect hash rule is unsupported until the contract defines its preimage; no frozen case uses it.", "Fixture premises such as revocation visibility at presentation and the observed field values are taken as supplied.", "No production safety, authority, independent effect custody or lifecycle change follows from these records." ], "claimResults": [ { "claim": "exact-call-binding-v1-cases-match-fixture", "result": "pass", "recordedField": "/qualifiedRuns/0/contracts/0/passingExpectations", "expectedValue": 15 }, { "claim": "fresh-authority-v1-cases-match-fixture", "result": "pass", "recordedField": "/qualifiedRuns/0/contracts/1/passingExpectations", "expectedValue": 14 }, { "claim": "effect-evidence-v1-cases-match-fixture", "result": "pass", "recordedField": "/qualifiedRuns/0/contracts/2/passingExpectations", "expectedValue": 12 }, { "claim": "exact_call_binding-status", "result": "pass", "recordedField": "/qualifiedRuns/0/contracts/0/claims/0/status", "expectedValue": "ESTABLISHED" }, { "claim": "single_use_authorization-status", "result": "pass", "recordedField": "/qualifiedRuns/0/contracts/0/claims/1/status", "expectedValue": "ESTABLISHED" }, { "claim": "fresh_authority_at_dispatch-status", "result": "pass", "recordedField": "/qualifiedRuns/0/contracts/1/claims/0/status", "expectedValue": "ESTABLISHED" }, { "claim": "effect_state_distinction-status", "result": "pass", "recordedField": "/qualifiedRuns/0/contracts/2/claims/0/status", "expectedValue": "ESTABLISHED" }, { "claim": "interpreters-agree-on-every-case", "result": "pass", "recordedField": "/interpretersAgreeOnEveryCase", "expectedValue": true }, { "claim": "source-mutations-caught", "result": "pass", "recordedField": "/qualifiedRuns/0/sourceFaults", "expectedValue": 9 }, { "claim": "run-record-independence", "result": "pass", "recordedField": "/independence", "expectedValue": "NOT_INDEPENDENT" }, { "claim": "effect-hash-rule", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" }, { "claim": "production-safety", "result": "out-of-scope" }, { "claim": "producer-acceptance", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/remora-boundary-2026-10-04/README.md", "sha256": "55918e419e36ada33fee74826378d6771e6200adcd7c16c11f1c90735cbd9dd5" }, { "path": "../experiments/remora-boundary-2026-10-04/effect-evidence-v1.external-run-record-v1.json", "sha256": "fe60202e10a2185931d3308b5b9d9020011068bc41c8ab68b846a2104da8b336" }, { "path": "../experiments/remora-boundary-2026-10-04/exact-call-binding-v1.external-run-record-v1.json", "sha256": "424a92720998bbe8a0d511ce12cbfe818f18e9ef4280a88765555702245f83e3" }, { "path": "../experiments/remora-boundary-2026-10-04/fresh-authority-v1.external-run-record-v1.json", "sha256": "7df0efaea898336c8befee3912932d2a53696825d7473f892ee814c7a2f8e137" }, { "path": "../experiments/remora-boundary-2026-10-04/provenance.json", "sha256": "9f2957963108aa06b9372a8355b6e20b6dd4dd77f0f4e249b7a00614493d9865" }, { "path": "../experiments/remora-boundary-2026-10-04/python-3.13.15-artifact.zip", "sha256": "75d6b940c30c1145ee1a1bcf0bd524dea1b80218d6e6eec511776781fb39fab1" }, { "path": "../experiments/remora-boundary-2026-10-04/python-3.14.7-artifact.zip", "sha256": "0c14ca0708f690fffe967463000d8373875e295bb1180f23c486bdb9f42abf0b" }, { "path": "../experiments/remora-boundary-2026-10-04/report.json", "sha256": "155783143d733ca3b1941f97eb4a930d45e9964d4f827eebfae1f7c998cdefad" }, { "path": "../experiments/remora-boundary-2026-10-04/validate_capsule.py", "sha256": "2b800db166f1e6b1d20017cd703cc30e8818993aa02f2edda011fd2c73b4b23b" } ] }, { "id": "aeoess-receipt-signature-2026-10-05", "contract": "https://github.com/Agent-Authority-Conformance/aps-conformance-suite/blob/f8d6eb4461759ce7dbb4c33ab03a688ba2bb541f/CONTRIBUTING.md", "report": "../experiments/aeoess-receipt-signature-2026-10-05/report.json", "provenance": "../experiments/aeoess-receipt-signature-2026-10-05/provenance.json", "reviewState": "upstream-merged-retained-run", "evidenceClaim": "source-reported-outside-verifier-and-primitive-checks-on-public-fixtures", "roles": { "runner": "Claude under Tymofii Pidlisnyi (@aeoess)’s revocable mandate, as declared in RUN.md", "humanReviewer": "Tymofii Pidlisnyi (@aeoess), source-reported", "verifierAuthor": "tomjwxf", "identifierPrimitive": "GNU coreutils sha256sum, invoked by runner-authored digests21.py", "atlasRetentionAndIntegrityChecks": "Probity", "independentEffectCustody": "not-established", "corpusMemberAuthors": "giskard09, tomjwxf and astrogilda, as declared by original RUN.md and corpus README", "adapterAndHarnessAuthor": "astrogilda (Probity)" }, "answerExposure": "Published expected outcomes and the author harness were available before the run; not answer-blind.", "comparisonOrder": "The original harness emitted verifier answers and comparison results together. No separate raw-result revision preceded comparison.", "limits": [ "Operator identity, human review and container custody are declared by the original source, not independently authenticated.", "Four context-bearing identifier checks remain outside the runner primitive coverage.", "Author harness interpretation and grading remain a separate layer.", "Repeated runs use the same 25 fixtures; no agent, production effect or independent custody measurement.", "Merged run record does not establish full-family admission or maintained host CI adoption." ], "claimResults": [ { "claim": "outside-verifier-fixture-comparisons", "result": "pass", "recordedField": "/outsideVerifier/passingFixtureComparisons", "expectedValue": 25 }, { "claim": "outside-context-free-identifiers", "result": "pass", "recordedField": "/identifiers/outsideContextFreeIdentifiers", "expectedValue": 21 }, { "claim": "always-valid-negative-control-failures", "result": "pass", "recordedField": "/controls/alwaysValidFailures", "expectedValue": 8 }, { "claim": "signature-mutation-affected-members", "result": "pass", "recordedField": "/controls/signatureMutationAffectedMembers", "expectedValue": 5 }, { "claim": "outside-context-bearing-identifier-checks", "result": "not-exercised" }, { "claim": "independent-semantic-grading", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" }, { "claim": "maintained-host-ci-adoption", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/aeoess-receipt-signature-2026-10-05/RUN.md", "sha256": "829457a044c4bd68dbd3496a0aa6410003cc06fd3f45c59606e44d135a1aa141" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/README.md", "sha256": "1ad946e7d14b873e07b93d7ff744a15df229ba6b7e05b04bf2f103811d6cba2e" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/report1.json", "sha256": "0e63176501c98c8c947bef3410f2766b99acc0ad4c5d2069b38eaee04fe735b5" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/report2.json", "sha256": "0e63176501c98c8c947bef3410f2766b99acc0ad4c5d2069b38eaee04fe735b5" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/report.json", "sha256": "0dc448e44914c8738c9443358db86a8a4cf9232425a1dad5025fb82f6f895f99" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/provenance.json", "sha256": "ff4fbf110b545dcf6ff12615926e8cc69f377814969e8a9bafc1c94e91c3d701" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/source-manifest.json", "sha256": "56fd51bc8043c48867c739f75173f3df8c80bc68340ee525ea325879d5def3aa" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/selected-public-source.zip", "sha256": "9d3454dacb9ea35491bdbe63645b22db93e293046071dcccdbb84a5eebaa0eea" }, { "path": "../experiments/aeoess-receipt-signature-2026-10-05/validate_capsule.py", "sha256": "f7319d9d5bb3f18ab12cd016a7fd6fa699ad12afcd02b15b814112157a735cbb" } ] }, { "id": "w3c-report-replay-2026-10-06", "atlasRevision": "0f5d25ab4cb00337f332eb109ac0dbc8b5651e00", "sourceRevision": "2f3aee40a454df6de0f571d119f057d7dbb8dd67", "readerRevision": "e07cd52999204d7c0f6562a5098dc4784fe025a6", "report": "../experiments/w3c-report-replay-2026-10-06/report.json", "provenance": "../experiments/w3c-report-replay-2026-10-06/provenance.json", "contract": "https://github.com/probityai/agent-evidence-vectors/tree/2f3aee40a454df6de0f571d119f057d7dbb8dd67", "reviewState": "author-retained-measured-record", "evidenceClaim": "historical-report-accounting-and-separate-diagnostic-control-dependencies", "roles": { "verifierAuthor": "Probity", "historicalRunner": "Probity, author-operated", "diagnosticRunner": "Probity, author-operated", "retentionAndAccounting": "Probity", "independentOperator": "not-established" }, "answerExposure": "Published expected answers and author-selected predicates were exposed; not answer-blind.", "comparisonOrder": "Historical harness outcomes and comparison grades emitted together. Diagnostic copies remove one predicate each; outputs are retained separately from the historical report.", "limits": [ "Synthetic conformance artifacts; the customer refund story is hypothetical.", "Retained-output accounting executes no captured reader or mutant code and performs no new model inference.", "Historical 272-case report and separate 232-fixture diagnostic population are not combined.", "Report validity, evidence conclusion and actual action completion are distinct.", "Reader binding check is a historical proposed rule; its draft normative status is not promoted.", "No independent operation, effect custody, production workload, customer payment or outside maintained job is established." ], "claimResults": [ { "claim": "historical-harness-comparisons", "result": "pass", "recordedField": "/historical/harnessPassingComparisons", "expectedValue": 272 }, { "claim": "historical-report-state-accounting", "result": "pass", "recordedField": "/historical/reportStates", "expectedValue": { "pass": 31, "fail": 239, "inconclusive": 2 } }, { "claim": "historical-report-crosswalk", "result": "pass", "recordedField": "/historical/crosswalk", "expectedValue": [ { "count": 3, "kind": "accept", "observed_result": "degraded", "observed_verdict": "valid", "report_state": "fail" }, { "count": 27, "kind": "accept", "observed_result": "fail", "observed_verdict": "valid", "report_state": "fail" }, { "count": 25, "kind": "accept", "observed_result": "pass", "observed_verdict": "valid", "report_state": "pass" }, { "count": 6, "kind": "accept", "observed_result": "pass_indirect", "observed_verdict": "valid", "report_state": "pass" }, { "count": 2, "kind": "indeterminate", "observed_result": null, "observed_verdict": "invalid", "report_state": "inconclusive" }, { "count": 209, "kind": "reject", "observed_result": null, "observed_verdict": "invalid", "report_state": "fail" } ] }, { "claim": "negative-witness-state-recorded-control", "result": "pass", "recordedField": "/diagnostic/0", "expectedValue": { "cases": 232, "changedRejects": 1, "mutation": "negative-witness-state", "unchanged": 231, "unchangedAccepts": 116 } }, { "claim": "checker-and-configuration-recorded-control", "result": "pass", "recordedField": "/diagnostic/1", "expectedValue": { "cases": 232, "changedRejects": 2, "mutation": "checker-and-configuration", "unchanged": 230, "unchangedAccepts": 116 } }, { "claim": "real-workload-action-completion", "result": "not-exercised" }, { "claim": "independent-operation", "result": "not-exercised" }, { "claim": "outside-maintained-host-adoption", "result": "not-exercised" }, { "claim": "current-vectors-reader-replay", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/w3c-report-replay-2026-10-06/LICENSE", "sha256": "8b506a9d145be0a6fbef3f0519996faf84c770f8ab8d32d120c8682f2ad6181f" }, { "path": "../experiments/w3c-report-replay-2026-10-06/README.md", "sha256": "a66e23b93bf31bd336ffbf733badea52aeac4afba8797133502bb39d029b69d9" }, { "path": "../experiments/w3c-report-replay-2026-10-06/SOURCE-ORIGIN.json", "sha256": "a2a4e58b3f54c2ae34f58e9259972e45e94ab50978568ef9079e7e8cc4c520bc" }, { "path": "../experiments/w3c-report-replay-2026-10-06/checker-and-configuration.mutant.py", "sha256": "6c2541c985569a3cf3483efc8e121a2a615fef64ab490c7fde98161dc9b4775e" }, { "path": "../experiments/w3c-report-replay-2026-10-06/checker-and-configuration.per-case.json", "sha256": "7cd4cd6575588a21b518fc70c3f39bc9672d7a79fee5dd20c22363517408147e" }, { "path": "../experiments/w3c-report-replay-2026-10-06/control-summary.json", "sha256": "95839e879d12d942bf0ac3c67608971eb40ac6ac005625a260429e4be4946312" }, { "path": "../experiments/w3c-report-replay-2026-10-06/historical-summary.json", "sha256": "bda9105e4c040d8140f6ab42ca7b22929b1bef1adf0527c65380d39557aee3f2" }, { "path": "../experiments/w3c-report-replay-2026-10-06/logic-control-configuration.json", "sha256": "736f640557727e9b524c6925b7b29efbfcec56f8b6258cf02be8bf0590bb3a0e" }, { "path": "../experiments/w3c-report-replay-2026-10-06/logic-control-evidence.json", "sha256": "815adc01af215bda4d7b10edf1e9707c578667762234cf955cd04c192b3a3167" }, { "path": "../experiments/w3c-report-replay-2026-10-06/logic-mutation-summary.json", "sha256": "24edc6eb36ce9bf06abaddbcadf12c2c9fb78b65c85e2a9f44f14de4b9327aea" }, { "path": "../experiments/w3c-report-replay-2026-10-06/negative-witness-state.mutant.py", "sha256": "a57f365c5046ab4e400ef215ca3beea93fd975239a92726eb2eb0618c127816d" }, { "path": "../experiments/w3c-report-replay-2026-10-06/negative-witness-state.per-case.json", "sha256": "bdc424f51334c17079dd41af3cf62919ec4a33bb351a3281c60f36adb2395992" }, { "path": "../experiments/w3c-report-replay-2026-10-06/original-RUN.json", "sha256": "00007b271fd027a5c952c17a8100190b8af360929f906936be352bb806c97448" }, { "path": "../experiments/w3c-report-replay-2026-10-06/original-conformance-report.json", "sha256": "ee349e66697a2f4f95dd8223fd261810f99f5f2807e03bde03c9a9f57359529d" }, { "path": "../experiments/w3c-report-replay-2026-10-06/original-report.json", "sha256": "37288d8dfc01f56cb5ef553232258dc596928bc962e2309e0c7dc09ae588baf2" }, { "path": "../experiments/w3c-report-replay-2026-10-06/per-case-outcomes.csv", "sha256": "57ec77ae8e30cf56b0ec7c6c1300e382df3fd9cafafa6e12d86d195cb0965753" }, { "path": "../experiments/w3c-report-replay-2026-10-06/per-case-outcomes.json", "sha256": "0c328d01013c28137507ca9460caa61642d023479fe9a9edded42f18499bf751" }, { "path": "../experiments/w3c-report-replay-2026-10-06/provenance.json", "sha256": "45d71e357596d90b636b0a9eb3a0c1edfe9f6dbecea7107dced4124e099ac219" }, { "path": "../experiments/w3c-report-replay-2026-10-06/report-replay-configuration.json", "sha256": "edc9489a5415616762dd67d2d740c8f064f709643724ed2c1cf55db3b09c6ff9" }, { "path": "../experiments/w3c-report-replay-2026-10-06/report.json", "sha256": "892a154384a1c6d988d45fa093496d7a526edfee9c240742aa35d8e995304642" }, { "path": "../experiments/w3c-report-replay-2026-10-06/source-manifest.json", "sha256": "ebbae4a8725f6a2557372877bb877211b32ec17436f26784275479393da72786" } ] }, { "id": "aps-corrected20-2026-10-10", "atlasRevision": "3cb950429c35a66ea57e4ea04360d11ca39fbb4f", "sourceRevision": "407ca2d5ad10c846860ad1b6faafc971ae9690e5", "readerRevision": "sha256:1d9b8fc840a974796b2098d367e37599cbce4d7455186bbeeeb7f3879c873bda", "contract": "https://github.com/agent-passport-system/agent-passport-system/blob/407ca2d5ad10c846860ad1b6faafc971ae9690e5/fixtures/agent-passport-v2/README.md", "report": "../experiments/aps-corrected20-2026-10-10/report.json", "provenance": "../experiments/aps-corrected20-2026-10-10/provenance.json", "reviewState": "author-retained-measured-record", "evidenceClaim": "independently-written-and-operated-reader-on-producer-authored-finite-synthetic-corpus", "roles": { "producer": "APS/AEOESS", "readerAuthor": "Probity", "runner": "Probity, normal canonical one-CPU job", "atlasOperator": "Probity", "retentionHolder": "Probity", "independentOperation": "Probity operated the reader separately from APS/AEOESS fixture authors; not independent of Probity", "independentEffectCustody": "not-established", "outsideRecurringUse": "not-established" }, "answerExposure": "The corrected public fixture, all upstream expected outcomes and README annotations were available before the reader and run.", "comparisonOrder": "The independently written reader emitted raw checks, its outcomes and comparisons in one report; not answer-blind or separately graded.", "limits": [ "Finite printable-ASCII corpus reader; not general JCS conformance.", "Signature verification uses cryptography/OpenSSL; no independent cryptographic-backend claim.", "Diagnostic agreement does not force the five normatively undetermined SDK outcomes.", "Resolver answers are supplied synthetic data, without historical validity windows or authenticated lookup.", "No APS package qualification, principal binding, live DID lookup, host adoption, federation enrollment or commercial agreement.", "Twenty public synthetic cases, not a representative deployment population.", "Three declared full-outcome differences remain visible; PASS means the bounded diagnostic comparison, not uniform verdict agreement.", "The five upstream draft annotations are separate from the two indeterminate source outcomes.", "No new package release, maintainer acceptance of this reader, host adoption, federation enrollment or commercial agreement.", "Both selected SDK invocations stopped at IPC creation; their corpus/ambiguity checks remain not exercised.", "Original dependency audit remains adverse; the finite reader result is a separate evidence layer." ], "claimResults": [ { "claim": "corrected-corpus-source-SHA256", "result": "pass", "recordedField": "/fixtureSHA256", "expectedValue": "9fce76dbf13de9749a2ef52c8dedecce08e4874da0203b39a7d941eb479b5ac5" }, { "claim": "finite-diagnostic-comparison", "result": "pass", "recordedField": "/mismatches", "expectedValue": [] }, { "claim": "upstream-SDK-observation-population", "result": "pass", "recordedField": "/sourceObservations", "expectedValue": { "valid": 4, "invalid": 14, "indeterminate": 2 } }, { "claim": "separate-reader-outcome-population", "result": "pass", "recordedField": "/readerOutcomes", "expectedValue": { "valid": 4, "invalid": 11, "indeterminate": 3, "unsupported": 2 } }, { "claim": "five-separate-upstream-draft-annotations", "result": "pass", "recordedField": "/separateSDKAnnotations", "expectedValue": [ "did-web-resolver-not-found", "expired", "not-yet-valid", "record-type-changed", "version-changed" ] }, { "claim": "reader-does-not-import-APS-SDK", "result": "pass", "recordedField": "/readerImportsAPSSDK", "expectedValue": false }, { "claim": "selected-SDK-corpus-characterization", "result": "not-exercised" }, { "claim": "historical-ambiguous-key-SDK-characterization", "result": "not-exercised" }, { "claim": "authenticated-historical-key-authority", "result": "not-exercised" }, { "claim": "principal-binding", "result": "not-exercised" }, { "claim": "general-JCS-conformance", "result": "out-of-scope" }, { "claim": "independent-cryptographic-backend", "result": "out-of-scope" }, { "claim": "outside-recurring-host-adoption", "result": "not-exercised" }, { "claim": "independent-effect-custody", "result": "not-exercised" } ], "artifacts": [ { "path": "../experiments/aps-corrected20-2026-10-10/README.md", "sha256": "3267d8d1113852f0074d32a4a11f72376c82ece7766ad52e87a8b2b99816457c" }, { "path": "../experiments/aps-corrected20-2026-10-10/job-runtime-provenance.json", "sha256": "c1c557a9307794e776224521ae4b0769d9b8bf51567e432b7a8a73469dabf07b" }, { "path": "../experiments/aps-corrected20-2026-10-10/native-resource-profile.json", "sha256": "812af5af7e78bd85412e2a99b0f0c9306b4805b899487fe3b2c2bc5445d7b7c1" }, { "path": "../experiments/aps-corrected20-2026-10-10/node-runtime.json", "sha256": "4bdd8a588d78a43e0a7168650d9d92515d3cb1b163dd54af924028b1e32c7321" }, { "path": "../experiments/aps-corrected20-2026-10-10/npm-audit.json", "sha256": "d8753f1c88af71a51bbe0a299122cc9598110f4cd7e0dd122cc4977190e05991" }, { "path": "../experiments/aps-corrected20-2026-10-10/npm-runtime.json", "sha256": "8204dc949a57d8d035354a9d3d935977033a36beb52998b7ae6f1d8d099302c5" }, { "path": "../experiments/aps-corrected20-2026-10-10/original-native-result.json", "sha256": "731f42c819ef24f4691f5abfaae6baef17e8a71433edd076d7d8bb756647ef3d" }, { "path": "../experiments/aps-corrected20-2026-10-10/producer/LICENSE", "sha256": "c6276a9c8c67588338d8439b0c7d27b3451335fc652e02a2be990e81c51ef40a" }, { "path": "../experiments/aps-corrected20-2026-10-10/producer/README.md", "sha256": "e9fda90aebaade446408f8f287f2d2d8f8b188753b5346e67db8e9b834adab09" }, { "path": "../experiments/aps-corrected20-2026-10-10/producer/agent-passport-vectors-v2.json", "sha256": "9fce76dbf13de9749a2ef52c8dedecce08e4874da0203b39a7d941eb479b5ac5" }, { "path": "../experiments/aps-corrected20-2026-10-10/provenance.json", "sha256": "fae84df0376e94fec2ddc8e96a9b7fb219a5fc09e874bb1b13faf948e4becbcc" }, { "path": "../experiments/aps-corrected20-2026-10-10/python-runtime-advisories.json", "sha256": "d8efaa78b047795cbcdd2d0d574247de26c5154df4421a9e428f7b9446f8d2a7" }, { "path": "../experiments/aps-corrected20-2026-10-10/python-runtime.json", "sha256": "8f9ee2e2bbf770912874b686a30f5f50215fbcf5fb68d527b5908aa3af8ebaaa" }, { "path": "../experiments/aps-corrected20-2026-10-10/read_corpus.py", "sha256": "1d9b8fc840a974796b2098d367e37599cbce4d7455186bbeeeb7f3879c873bda" }, { "path": "../experiments/aps-corrected20-2026-10-10/reader-requirements.txt", "sha256": "2e1656c458cd8838941bd224f9ae1c2f29beb7f320740d260629e66bcae2eeab" }, { "path": "../experiments/aps-corrected20-2026-10-10/reader.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../experiments/aps-corrected20-2026-10-10/reader.stdout", "sha256": "b8829566bad7cb629fa2c4fcfa7744db6d5f7c6213398ebafe6e3d8e68c00d09" }, { "path": "../experiments/aps-corrected20-2026-10-10/report.json", "sha256": "1598f87559130cb0e7a2e4ca59e5d6a2a584b402149bc28baad30dd9eaa01df1" }, { "path": "../experiments/aps-corrected20-2026-10-10/sdk-348.stderr", "sha256": "d570f1365339472ad7ed7fc173661a8ef492a21d0aff9c81dc371b5356d1b4ce" }, { "path": "../experiments/aps-corrected20-2026-10-10/sdk-c31.stderr", "sha256": "50188c2caf8bdd4f44d09c5cb960b607aaf29041bd575294d51f80ecc1a927aa" }, { "path": "../experiments/aps-corrected20-2026-10-10/sdk-source-after.json", "sha256": "5181e8a70b6bba5d744b6691de8bb1c05e34077a9c2e1fbb982de656fe7327c4" }, { "path": "../experiments/aps-corrected20-2026-10-10/sdk-source-before.json", "sha256": "e27ea476542d802fd32df0391efcc0f18d683c09084aebaaec6935121bae1e3d" }, { "path": "../experiments/aps-corrected20-2026-10-10/selected-source.zip", "sha256": "eb2abcb435590456e4228476d499cc48e4e9a4184c8f6e767355d1ea6076cc13" }, { "path": "../experiments/aps-corrected20-2026-10-10/source-after.json", "sha256": "72373a3f9f7d941acd52043e04f5a9d61c46e9bcb90e088428caa84472493a2b" }, { "path": "../experiments/aps-corrected20-2026-10-10/source-manifest.json", "sha256": "79fac1ad6164c1f356ff5fb91fdec701bc598c3260f44e65dab0d79378fe89a5" } ] }, { "id": "trace-m1-consumer-2026-10-11", "experiment": "../trace-m1-consumer.html", "contract": "https://github.com/darklordVirtual/REMORA-research/pull/822", "evidenceClaim": "signature-report-binding-and-native-claim-ceiling-on-public-synthetic-inputs", "report": "../interop/trace-m1/retained/public-report.json", "provenance": "../interop/trace-m1/retained/QUALIFICATION.json", "reviewState": "retained-independent-consumer-result", "roles": { "readerAuthorship": "Probity; second implementation maintained outside REMORA", "fixtureOperator": "Probity", "evidenceVantage": "artifact", "producerIndependence": "external implementation and operator; no REMORA runtime or reference-verifier imports", "independentWitness": "not-established" }, "answerExposure": "Author read producer source and expected cases before implementation; not an answer-blind study", "comparisonOrder": "Synthetic known-answer replay; retained native output compared to published fixture expectations", "limits": [ "Bounded ASCII JSON, explicit report digest, P1Y retention and frozen synthetic inputs", "Native reason codes are preserved; independent refusal codes are not equated", "Signature and binding checks do not establish truth, workload identity, authority or effects", "Unsigned external-evidence mapping is not a TRACE Trust Record or conformance level", "No REMORA or AgenTrust host adoption, deployment or commercial agreement is established" ], "claimResults": [ { "claim": "frozen-case-population", "result": "pass", "recordedField": "/cases", "expectedValue": 12 }, { "claim": "declared-comparison-agreement", "result": "pass", "recordedField": "/agreements", "expectedValue": 12 }, { "claim": "native-contradiction-preserved", "result": "pass", "recordedField": "/rows/1/observed/native_result/status", "expectedValue": "CONTRADICTED" }, { "claim": "absent-selected-report-refused", "result": "pass", "recordedField": "/rows/11/observed/decision", "expectedValue": "REFUSED" }, { "claim": "trace-trust-record-ceiling-preserved", "result": "pass", "recordedField": "/rows/0/observed/claim_ceiling/trace_trust_record", "expectedValue": false }, { "claim": "native-result-truth", "result": "not-exercised" }, { "claim": "outside-host-adoption", "result": "not-exercised" }, { "claim": "trace-conformance", "result": "out-of-scope" } ], "artifacts": [ { "path": "../interop/trace-m1/retained/QUALIFICATION.json", "sha256": "fbc672e3d71e43893a31f475ddd644002a5fef3f617ee371a2aa97c4439a0df3" }, { "path": "../interop/trace-m1/retained/public-report.json", "sha256": "bd3f39ba3fb2ee3277389758640915068dc97662e6a1139e7908f9a1ad7d457a" }, { "path": "../interop/trace-m1/retained/qualification/controls.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/controls.stderr", "sha256": "baae5c5cfe21515dc81ee6ada181d4111b88a7f1c4cedf070bdfb9d25e287eeb" }, { "path": "../interop/trace-m1/retained/qualification/controls.stdout", "sha256": "b4c28013d47253fbc76d1975a9a164133d4decdf50761c131b47b139413fa74d" }, { "path": "../interop/trace-m1/retained/qualification/coverage-json.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/coverage-json.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/coverage-json.stdout", "sha256": "f65f791937f6c29a4e65eb022629cc14d372c4e8cf72f5097f85e7d3954a0c2b" }, { "path": "../interop/trace-m1/retained/qualification/coverage-report.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/coverage-report.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/coverage-report.stdout", "sha256": "c918bb5efa800ab6389aa17ca25ceb220a1b73434d685cf5e79b5c3b7b42ce7d" }, { "path": "../interop/trace-m1/retained/qualification/coverage.json", "sha256": "091a28eca1d02acd506b52b611e55913ed65646a79fb22928d57f320ed3fec3a" }, { "path": "../interop/trace-m1/retained/qualification/export.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/export.stdout", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/fetch.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/fetch.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/fetch.stdout", "sha256": "59881a8a4f882c942f845240fd7086021d6b0fe219e403c9d7d2a9fc99fd5b7d" }, { "path": "../interop/trace-m1/retained/qualification/format.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/format.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/format.stdout", "sha256": "2ce9758b9f8abd876ec3e76c589e099e8b05377b1e7ea2331e81ee80f07bdff8" }, { "path": "../interop/trace-m1/retained/qualification/lint.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/lint.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/lint.stdout", "sha256": "82b3e6a6c090a57601d22943bd23fca9218d1031dbe5a7b754092f9a156b4f18" }, { "path": "../interop/trace-m1/retained/qualification/per-file-coverage.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/per-file-coverage.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/per-file-coverage.stdout", "sha256": "b264f9d3c7c79a5a843944796b1d416915e2119ba688c905902e1c9a9dcf1106" }, { "path": "../interop/trace-m1/retained/qualification/replay.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/replay.stderr", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" }, { "path": "../interop/trace-m1/retained/qualification/replay.stdout", "sha256": "1cdb7b336dc333576293625798d74c0a05a7885a2c63210ba5a2157ef20eb424" }, { "path": "../interop/trace-m1/retained/qualification/sync.exit", "sha256": "9a271f2a916b0b6ee6cecb2426f0b3206ef074578be55d9bc94f6f3fe3ab86aa" }, { "path": "../interop/trace-m1/retained/qualification/sync.stderr", "sha256": "cb1ec13a2b8ec50d80fcab305307cb5c00d65e0182bdb1bcfcecd5728819171f" }, { "path": "../interop/trace-m1/retained/qualification/sync.stdout", "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" } ] } ] }