{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROICRIYVT7Z27WGRKK73O7YJI2","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":"ea628424a5c0183e1ed2e8a840290997eeec92ab831febb8c473eb9e604e029e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-22T11:16:53Z","title_canon_sha256":"4aa2cdddca48481f3b02691cd36de3b853b31c803f01296e95aa90363627975e"},"schema_version":"1.0","source":{"id":"2412.16974","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16974","created_at":"2026-07-05T09:53:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16974v1","created_at":"2026-07-05T09:53:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16974","created_at":"2026-07-05T09:53:15Z"},{"alias_kind":"pith_short_12","alias_value":"ROICRIYVT7Z2","created_at":"2026-07-05T09:53:15Z"},{"alias_kind":"pith_short_16","alias_value":"ROICRIYVT7Z27WGR","created_at":"2026-07-05T09:53:15Z"},{"alias_kind":"pith_short_8","alias_value":"ROICRIYV","created_at":"2026-07-05T09:53:15Z"}],"graph_snapshots":[{"event_id":"sha256:0f973e064d3ba9fba9db6f43d6e1e837c8c3d2aba9d26326417ead2d5c68b28f","target":"graph","created_at":"2026-07-05T09:53:15Z","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/2412.16974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of hallucinations in particular. These behaviors are learned during post-training, especially in instruction fine-tuning (IFT) and reinforcement learning from human feedback (RLHF). However, existing taxonomies and evaluation datasets for refusals are inadequate, often focusing solely on should-not-related (instead of cannot-related) categories, and lacking tools for auditing refusal content in black-box LLM outputs.\n ","authors_text":"Alexander von Recum, Christoph Schnabl, Gabor Hollbeck, Marvin Von Hagen, Philip Blinde, Silas Alberti","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-22T11:16:53Z","title":"Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16974","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:cdec4b2f7b75533994272cffc6c337af11e12ea46345af0d1399cf74896e68e3","target":"record","created_at":"2026-07-05T09:53:15Z","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":"ea628424a5c0183e1ed2e8a840290997eeec92ab831febb8c473eb9e604e029e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-22T11:16:53Z","title_canon_sha256":"4aa2cdddca48481f3b02691cd36de3b853b31c803f01296e95aa90363627975e"},"schema_version":"1.0","source":{"id":"2412.16974","kind":"arxiv","version":1}},"canonical_sha256":"8b9028a3159ff3afd8d152bfb77f0946b345f1262c1ac3024ec7b5adbd4a2bd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b9028a3159ff3afd8d152bfb77f0946b345f1262c1ac3024ec7b5adbd4a2bd7","first_computed_at":"2026-07-05T09:53:15.771653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:15.771653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VAadf3Gwl+Ea6v+o8ie4k0+9N1zlprGM4Cy2HEygt9Yr3CI+FfGiMbcVy+T0unRWk0q0j0v0SxZnz6HCCVG9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:15.772149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16974","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdec4b2f7b75533994272cffc6c337af11e12ea46345af0d1399cf74896e68e3","sha256:0f973e064d3ba9fba9db6f43d6e1e837c8c3d2aba9d26326417ead2d5c68b28f"],"state_sha256":"11577991871b60de22d6fb698990e7e0e2c90cc47e6782bd61e3a42c4c1849af"}