{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CX5CVEILA5PMWEJ4W3LP5KKCNY","short_pith_number":"pith:CX5CVEIL","schema_version":"1.0","canonical_sha256":"15fa2a910b075ecb113cb6d6fea9426e18eb85a10282bfbac50d6ee47139b40b","source":{"kind":"arxiv","id":"2502.12189","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Attribute-aware Dynamic Preference Ranking Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongyu Yang, Qi Zhao, Rui Li, Zhenhua Hu","submitted_at":"2025-02-15T08:20:42Z","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,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.12189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T08:20:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"299aba3886c1a08bc20817e32cafb7842906d5f1fa02abe4b98fe83318bbe993","abstract_canon_sha256":"06b6aaa0cfb9ce9d0f1dbe775087c3b614695c31761d61c81bfe8687590c2160"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:51.574749Z","signature_b64":"lCoJAFEG9wTVOQXolTmGGKLxj4LLB2Q/Pg9qamWhSYTuqrw1jXwjrI5C8rJhsJ3nPSvFq+dAWIcqhgcoXADsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15fa2a910b075ecb113cb6d6fea9426e18eb85a10282bfbac50d6ee47139b40b","last_reissued_at":"2026-07-05T10:15:51.574251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:51.574251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Attribute-aware Dynamic Preference Ranking Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongyu Yang, Qi Zhao, Rui Li, Zhenhua Hu","submitted_at":"2025-02-15T08:20:42Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12189","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.12189/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.12189","created_at":"2026-07-05T10:15:51.574309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12189v1","created_at":"2026-07-05T10:15:51.574309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12189","created_at":"2026-07-05T10:15:51.574309+00:00"},{"alias_kind":"pith_short_12","alias_value":"CX5CVEILA5PM","created_at":"2026-07-05T10:15:51.574309+00:00"},{"alias_kind":"pith_short_16","alias_value":"CX5CVEILA5PMWEJ4","created_at":"2026-07-05T10:15:51.574309+00:00"},{"alias_kind":"pith_short_8","alias_value":"CX5CVEIL","created_at":"2026-07-05T10:15:51.574309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY","json":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY.json","graph_json":"https://pith.science/api/pith-number/CX5CVEILA5PMWEJ4W3LP5KKCNY/graph.json","events_json":"https://pith.science/api/pith-number/CX5CVEILA5PMWEJ4W3LP5KKCNY/events.json","paper":"https://pith.science/paper/CX5CVEIL"},"agent_actions":{"view_html":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY","download_json":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY.json","view_paper":"https://pith.science/paper/CX5CVEIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12189&json=true","fetch_graph":"https://pith.science/api/pith-number/CX5CVEILA5PMWEJ4W3LP5KKCNY/graph.json","fetch_events":"https://pith.science/api/pith-number/CX5CVEILA5PMWEJ4W3LP5KKCNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY/action/storage_attestation","attest_author":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY/action/author_attestation","sign_citation":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY/action/citation_signature","submit_replication":"https://pith.science/pith/CX5CVEILA5PMWEJ4W3LP5KKCNY/action/replication_record"}},"created_at":"2026-07-05T10:15:51.574309+00:00","updated_at":"2026-07-05T10:15:51.574309+00:00"}