{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AI6CU33KZTQDMR7CLRFNGDWKOK","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":"166fe71666c746ecea871c52cee01f08a7d83d87d02d8f459d522d8d05824b57","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T21:34:40Z","title_canon_sha256":"afb104253a7e05f552179d5aa6ce105ef7f9bc7cbcc37e7a90be69328a3a3acf"},"schema_version":"1.0","source":{"id":"2505.21784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21784","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21784v1","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21784","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"AI6CU33KZTQD","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"AI6CU33KZTQDMR7C","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"AI6CU33K","created_at":"2026-07-05T11:11:03Z"}],"graph_snapshots":[{"event_id":"sha256:691ca9a5e500633b2c70735ecf4f4648bc45caa0ad41c92609586c5cb76f6b08","target":"graph","created_at":"2026-07-05T11:11:03Z","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/2505.21784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety reasoning is a recent paradigm where LLMs reason over safety policies before generating responses, thereby mitigating limitations in existing safety measures such as over-refusal and jailbreak vulnerabilities. However, implementing this paradigm is challenging due to the resource-intensive process of creating high-quality policy-embedded chain-of-thought (CoT) datasets while ensuring reasoning remains accurate and free from hallucinations or policy conflicts. To tackle this, we propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning, a novel data generation recipe that leve","authors_text":"Anil Ramakrishna, Aram Galstyan, Charith Peris, Kai-Wei Chang, Ninareh Mehrabi, Rahul Gupta, Richard Zemel, Tharindu Kumarage, Xinyan Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T21:34:40Z","title":"Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21784","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":"sha256:3ab311c4d12861b252f41d625c3949e963503808f5b29aab12d5ab39db512b76","target":"record","created_at":"2026-07-05T11:11:03Z","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":"166fe71666c746ecea871c52cee01f08a7d83d87d02d8f459d522d8d05824b57","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T21:34:40Z","title_canon_sha256":"afb104253a7e05f552179d5aa6ce105ef7f9bc7cbcc37e7a90be69328a3a3acf"},"schema_version":"1.0","source":{"id":"2505.21784","kind":"arxiv","version":1}},"canonical_sha256":"023c2a6f6acce03647e25c4ad30eca72b208e923ae602b7354af12cb753ee934","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"023c2a6f6acce03647e25c4ad30eca72b208e923ae602b7354af12cb753ee934","first_computed_at":"2026-07-05T11:11:03.509044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:03.509044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4e5MRk76GNUUcmiazAgXBzvvZdBAlIrO/lHZKPbavTlnIilHgDl/vUNcSuL1Z+/5s4/OhzR11vww3Q9f2h8XDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:03.509545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ab311c4d12861b252f41d625c3949e963503808f5b29aab12d5ab39db512b76","sha256:691ca9a5e500633b2c70735ecf4f4648bc45caa0ad41c92609586c5cb76f6b08"],"state_sha256":"b03bddc882158e109590137edef5deb64b1b0ed56c43263b334347049a5b2964"}