{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DIFWTZLUGIWN5BBP5AMRODX7Y6","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":"7c96a6d6ef28ec700958df9192a7ce2e495806840e3f10fa4450956814cee8bf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T18:37:36Z","title_canon_sha256":"c47e417c767a0ef1d2be356e4446dc852cec3a9f68110f8e142366affd34d4c1"},"schema_version":"1.0","source":{"id":"2406.15513","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15513","created_at":"2026-07-05T11:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15513v3","created_at":"2026-07-05T11:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15513","created_at":"2026-07-05T11:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"DIFWTZLUGIWN","created_at":"2026-07-05T11:21:33Z"},{"alias_kind":"pith_short_16","alias_value":"DIFWTZLUGIWN5BBP","created_at":"2026-07-05T11:21:33Z"},{"alias_kind":"pith_short_8","alias_value":"DIFWTZLU","created_at":"2026-07-05T11:21:33Z"}],"graph_snapshots":[{"event_id":"sha256:1780a71f0ffed7c5e0c5a430652aba68acfa1c1ce9fe133d0fd4e32b5241e02b","target":"graph","created_at":"2026-07-05T11:21:33Z","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/2406.15513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we introduce the safety human preference dataset, PKU-SafeRLHF, designed to promote research on safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and BeaverTails, we separate annotations of helpfulness and harmlessness for question-answering pairs, providing distinct perspectives on these coupled attributes. Overall, we provide 44.6k refined prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels ranging from minor to severe, with answers generated by Llama-family models. Based on this, we c","authors_text":"Boren Zheng, Borong Zhang, Boxuan Li, Boyuan Chen, Donghai Hong, Jiaming Ji, Jiayi Zhou, Juntao Dai, Kaile Wang, Sirui Han, Tianyi Qiu, Yaodong Yang, Yike Guo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T18:37:36Z","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15513","kind":"arxiv","version":3},"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":"sha256:1214a6051c012019b78b2db1dfbcd8b339fa579d194fbedd91635613fef8a5ab","target":"record","created_at":"2026-07-05T11:21:33Z","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":"7c96a6d6ef28ec700958df9192a7ce2e495806840e3f10fa4450956814cee8bf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T18:37:36Z","title_canon_sha256":"c47e417c767a0ef1d2be356e4446dc852cec3a9f68110f8e142366affd34d4c1"},"schema_version":"1.0","source":{"id":"2406.15513","kind":"arxiv","version":3}},"canonical_sha256":"1a0b69e574322cde842fe819170effc79657bbd7828125f3c72865f4b9972bee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a0b69e574322cde842fe819170effc79657bbd7828125f3c72865f4b9972bee","first_computed_at":"2026-07-05T11:21:33.638947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:33.638947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LU+RuOnK8w8ArZ6pstIsWoGicrWBInZ++XQdQ2utfwVuv4Zgk0im6KulURWckBkaZYSGfMW5npWvBz2SClaEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:33.639484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15513","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1214a6051c012019b78b2db1dfbcd8b339fa579d194fbedd91635613fef8a5ab","sha256:1780a71f0ffed7c5e0c5a430652aba68acfa1c1ce9fe133d0fd4e32b5241e02b"],"state_sha256":"895e07510b1b61b0de87f5f1c3cb8e865541e9799d22eb9193077cbdaf62048b"}