{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JM5H6GAO7RCEZFWVL7JX2DLW6J","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":"2f9e34e945ef377dd5140e1c58699ba8e052e6766d6078953e364609fba0d804","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T17:27:52Z","title_canon_sha256":"459556c091f920966d0c1401bef67448177b80cc0a68b578877bd55ba45b5c50"},"schema_version":"1.0","source":{"id":"2407.14477","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14477","created_at":"2026-07-05T11:36:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14477v4","created_at":"2026-07-05T11:36:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14477","created_at":"2026-07-05T11:36:21Z"},{"alias_kind":"pith_short_12","alias_value":"JM5H6GAO7RCE","created_at":"2026-07-05T11:36:21Z"},{"alias_kind":"pith_short_16","alias_value":"JM5H6GAO7RCEZFWV","created_at":"2026-07-05T11:36:21Z"},{"alias_kind":"pith_short_8","alias_value":"JM5H6GAO","created_at":"2026-07-05T11:36:21Z"}],"graph_snapshots":[{"event_id":"sha256:ce4245cce214c7c01efaffa79189520ae4a6cec94c4eeb915c47fb78dcef75e5","target":"graph","created_at":"2026-07-05T11:36:21Z","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/2407.14477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is chosen over another for a given prompt. However, standard preference datasets often lack explicit information on why a particular choice was made, presenting an ambiguity that can hinder efficient learning and robust alignment, especially given the high cost of acquiring extensive human annotations. While many studies focus on algorithmic improvements, this wo","authors_text":"Anit Sahu, Hoang Anh Just, Huy Phan, Ming Jin, Ruoxi Jia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T17:27:52Z","title":"Data-Centric Human Preference with Rationales for Direct Preference Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14477","kind":"arxiv","version":4},"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:c956dbf32ab9e5769f32c00285e4b6780f49e063757fc53a28f607bec05e8713","target":"record","created_at":"2026-07-05T11:36:21Z","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":"2f9e34e945ef377dd5140e1c58699ba8e052e6766d6078953e364609fba0d804","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T17:27:52Z","title_canon_sha256":"459556c091f920966d0c1401bef67448177b80cc0a68b578877bd55ba45b5c50"},"schema_version":"1.0","source":{"id":"2407.14477","kind":"arxiv","version":4}},"canonical_sha256":"4b3a7f180efc444c96d55fd37d0d76f27587038b8071106da6425e6df7969233","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b3a7f180efc444c96d55fd37d0d76f27587038b8071106da6425e6df7969233","first_computed_at":"2026-07-05T11:36:21.062049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:21.062049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vYgrYWyCFntXzKtqIFotExdkaKBKiqyR9wKP7Qnvzd9ioD+bN2zUYLVcoFf5Al+vX91OABZNXOFGQuElEPGkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:21.062532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14477","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c956dbf32ab9e5769f32c00285e4b6780f49e063757fc53a28f607bec05e8713","sha256:ce4245cce214c7c01efaffa79189520ae4a6cec94c4eeb915c47fb78dcef75e5"],"state_sha256":"c74a42e9fef23cbef348c042a0f190b5853dc9c8d8a7a15639ac60f18134192c"}