{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:53LZN4K4XPENLMADPYYQV4MPAT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9b9d95b162143d963387321c4fd59b404372db87204aa19bf2332d79b0db7f01","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T01:16:34Z","title_canon_sha256":"abcf766c89488e63cd6a03eca755bddcd63dcfb301f1551605a7ee559f7b9bbe"},"schema_version":"1.0","source":{"id":"2506.02357","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02357","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02357v2","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02357","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_12","alias_value":"53LZN4K4XPEN","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_16","alias_value":"53LZN4K4XPENLMAD","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_8","alias_value":"53LZN4K4","created_at":"2026-07-05T11:34:51Z"}],"graph_snapshots":[{"event_id":"sha256:772ef530c23897daded2c1e912c1b834b1100d8e9e0e02de26f69aebaeb7d3f2","target":"graph","created_at":"2026-07-05T11:34:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.02357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these conflict with operational goals. This paper introduces a lightweight, interpretable benchmark to evaluate an LLM agent's ability to uphold a high-level safety principle when faced with conflicting task instructions. Our evaluation of six LLMs reveals two primary findings: (1) a quantifiable \"cost of compliance\" where safety constraints degrade task performan","authors_text":"Ram Potham (Independent Researcher)","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T01:16:34Z","title":"Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02357","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:235b76309ee0d423daf551a85ab099d54b15c1b4b44b5ecdea32c81f91a15047","target":"record","created_at":"2026-07-05T11:34:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9b9d95b162143d963387321c4fd59b404372db87204aa19bf2332d79b0db7f01","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T01:16:34Z","title_canon_sha256":"abcf766c89488e63cd6a03eca755bddcd63dcfb301f1551605a7ee559f7b9bbe"},"schema_version":"1.0","source":{"id":"2506.02357","kind":"arxiv","version":2}},"canonical_sha256":"eed796f15cbbc8d5b0037e310af18f04e0c51b11b9b0faeb9023e9acdefe1766","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eed796f15cbbc8d5b0037e310af18f04e0c51b11b9b0faeb9023e9acdefe1766","first_computed_at":"2026-07-05T11:34:51.858428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:51.858428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ymUlYTW6pWldn+fedSvPwOVQV+HOskX+ygk8+ePRWNLzH9IEkwRgWZLwjPGr1TAhewoGevjf/BgeTLcnqs+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:51.858933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02357","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:235b76309ee0d423daf551a85ab099d54b15c1b4b44b5ecdea32c81f91a15047","sha256:772ef530c23897daded2c1e912c1b834b1100d8e9e0e02de26f69aebaeb7d3f2"],"state_sha256":"2cce2fd948dd6c740dfd38ca8ee24bb88d6965bcae5a9db21e3ba714d2f68249"}