{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CX5CVEILA5PMWEJ4W3LP5KKCNY","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":"06b6aaa0cfb9ce9d0f1dbe775087c3b614695c31761d61c81bfe8687590c2160","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T08:20:42Z","title_canon_sha256":"299aba3886c1a08bc20817e32cafb7842906d5f1fa02abe4b98fe83318bbe993"},"schema_version":"1.0","source":{"id":"2502.12189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12189","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12189v1","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12189","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"CX5CVEILA5PM","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"CX5CVEILA5PMWEJ4","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"CX5CVEIL","created_at":"2026-07-05T10:15:51Z"}],"graph_snapshots":[{"event_id":"sha256:0c7c494a334a0537adf97b4b9a463a47fb55a93b2d0b1d95f5d6018aaec2d567","target":"graph","created_at":"2026-07-05T10:15:51Z","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/2502.12189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback and its variants excel in aligning with human intentions to generate helpful, harmless, and honest responses. However, most of them rely on costly human-annotated pairwise comparisons for supervised alignment, which is not suitable for list-level scenarios, such as community question answering. Additionally, human preferences are influenced by multiple intrinsic factors in responses, leading to decision-making inconsistencies. Therefore, we propose \\textbf{Se}lf-supervised \\textbf{A}ttribute-aware \\textbf{d}ynamic \\textbf{p}reference \\textbf{ra}nking,","authors_text":"Hongyu Yang, Qi Zhao, Rui Li, Zhenhua Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T08:20:42Z","title":"Self-supervised Attribute-aware Dynamic Preference Ranking Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12189","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":"sha256:48a0af0c450149a0591838b337d91344afe85275e5f65d782d899996d35887f8","target":"record","created_at":"2026-07-05T10:15:51Z","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":"06b6aaa0cfb9ce9d0f1dbe775087c3b614695c31761d61c81bfe8687590c2160","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T08:20:42Z","title_canon_sha256":"299aba3886c1a08bc20817e32cafb7842906d5f1fa02abe4b98fe83318bbe993"},"schema_version":"1.0","source":{"id":"2502.12189","kind":"arxiv","version":1}},"canonical_sha256":"15fa2a910b075ecb113cb6d6fea9426e18eb85a10282bfbac50d6ee47139b40b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15fa2a910b075ecb113cb6d6fea9426e18eb85a10282bfbac50d6ee47139b40b","first_computed_at":"2026-07-05T10:15:51.574251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:51.574251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lCoJAFEG9wTVOQXolTmGGKLxj4LLB2Q/Pg9qamWhSYTuqrw1jXwjrI5C8rJhsJ3nPSvFq+dAWIcqhgcoXADsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:51.574749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48a0af0c450149a0591838b337d91344afe85275e5f65d782d899996d35887f8","sha256:0c7c494a334a0537adf97b4b9a463a47fb55a93b2d0b1d95f5d6018aaec2d567"],"state_sha256":"264dbc6021ebf3f68cb930012dd3781bb2f20b9b6cb55e7f904fb0cb816d7ef1"}