{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SPVIOYDQDU6RF33WFH2BXJGQ5L","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":"a608e468b679e9344da0c195db8131091d02ba6226b1e0347e0a125336b9bfb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T21:17:16Z","title_canon_sha256":"83218a263c270e43982eecf91161a404750973d6a8a539b6d66ded5ddf128aea"},"schema_version":"1.0","source":{"id":"2605.24229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24229","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24229v1","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24229","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_12","alias_value":"SPVIOYDQDU6R","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_16","alias_value":"SPVIOYDQDU6RF33W","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_8","alias_value":"SPVIOYDQ","created_at":"2026-05-26T01:02:53Z"}],"graph_snapshots":[{"event_id":"sha256:7a084819cd74062c05aee78e8418fc497d1299116b2c4cd74f1c6c7757d1616a","target":"graph","created_at":"2026-05-26T01:02:53Z","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/2605.24229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Frontier AI developers now train models against long written behavioral specifications, such as Anthropic's constitution (Anthropic, 2025a) and OpenAI's Model Spec (OpenAI, 2025a), integrated into post-training via methods like character training (Anthropic, 2024) and deliberative alignment (Guan et al., 2024). These documents serve a governance function, but it is unclear how well models actually follow them under adversarial, multi-turn pressure similar to what they would face in real-world deployment. We propose a multi-method audit pipeline that treats each lab's published specification as","authors_text":"Arya Jakkli, Neel Nanda, Senthooran Rajamanoharan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T21:17:16Z","title":"How Well Do Models Follow Their Constitutions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24229","kind":"arxiv","version":1},"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":"sha256:332811979d5fedbaa9b23f5aa6a56bc9d14cfcd8a1ef9d71ca969b94bdb43d0e","target":"record","created_at":"2026-05-26T01:02:53Z","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":"a608e468b679e9344da0c195db8131091d02ba6226b1e0347e0a125336b9bfb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T21:17:16Z","title_canon_sha256":"83218a263c270e43982eecf91161a404750973d6a8a539b6d66ded5ddf128aea"},"schema_version":"1.0","source":{"id":"2605.24229","kind":"arxiv","version":1}},"canonical_sha256":"93ea8760701d3d12ef7629f41ba4d0ead9a61bb58afbd91a706d116f41f646e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93ea8760701d3d12ef7629f41ba4d0ead9a61bb58afbd91a706d116f41f646e3","first_computed_at":"2026-05-26T01:02:53.887180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:53.887180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q10Uha6i1604HsLaxRfBo2F5O9MYbAWRzz75lii7q8s5WOjN3FZcU2rJtKOhtXLTgfzjc7/+dC2twGgNGdVMBA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:53.887847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:332811979d5fedbaa9b23f5aa6a56bc9d14cfcd8a1ef9d71ca969b94bdb43d0e","sha256:7a084819cd74062c05aee78e8418fc497d1299116b2c4cd74f1c6c7757d1616a"],"state_sha256":"a6e24f7620e32ab684e4b94ece41e8ae1b0fcfcb737ffe8832256fe61a216fdc"}