{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I357OBIZ2VLQ7MT4EW6TMB5ZCT","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":"6e9b50940bb2200911c2b019cc3bf6269b21e0bda602cdca7325926940e5ef83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T14:48:28Z","title_canon_sha256":"271ff9797797694c1112032cedcca538d0715553743a1c1f4d7e92df506630ac"},"schema_version":"1.0","source":{"id":"2410.04503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04503","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04503v1","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04503","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"I357OBIZ2VLQ","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"I357OBIZ2VLQ7MT4","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"I357OBIZ","created_at":"2026-07-05T09:16:35Z"}],"graph_snapshots":[{"event_id":"sha256:2b47e90799d5c6b6e604ad686e5efbada40fc28921c2e8e5fb4ae52a371ffb3c","target":"graph","created_at":"2026-07-05T09:16:35Z","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/2410.04503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To improve human-preference alignment training, current research has developed numerous preference datasets consisting of preference pairs labeled as \"preferred\" or \"dispreferred\". These preference pairs are typically used to encode human preferences into a single numerical value through reward modeling, which acts as a reward signal during reinforcement learning from human feedback (RLHF). However, representing these human preferences as a numerical value complicates the analysis of these preferences and restricts their broader applications other than RLHF. In contrast, in this work, we intro","authors_text":"Chenglong Wang, Chunliang Zhang, Jingbo Zhu, Murun Yang, Qiaozhi He, Tongran Liu, Tong Xiao, Yang Gan, Yifu Huo, Yongyu Mu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T14:48:28Z","title":"LRHP: Learning Representations for Human Preferences via Preference Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04503","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":"sha256:5c3b4b25a8e067ac249a79e4e5c36bc95a41d13e36b6d691552f278a5c5cddbf","target":"record","created_at":"2026-07-05T09:16:35Z","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":"6e9b50940bb2200911c2b019cc3bf6269b21e0bda602cdca7325926940e5ef83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T14:48:28Z","title_canon_sha256":"271ff9797797694c1112032cedcca538d0715553743a1c1f4d7e92df506630ac"},"schema_version":"1.0","source":{"id":"2410.04503","kind":"arxiv","version":1}},"canonical_sha256":"46fbf70519d5570fb27c25bd3607b914ec9dfcb300cd0ef05fb79f7c6e4879df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46fbf70519d5570fb27c25bd3607b914ec9dfcb300cd0ef05fb79f7c6e4879df","first_computed_at":"2026-07-05T09:16:35.161745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:35.161745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NghHXl/qCMRsPxQkQQ+hZK2lC9T6x/k4kJNhI04d5juHnxP4cp78+Y6e4R5gkpudcD2fZZfBF1eRcpqcLuqfBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:35.162218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c3b4b25a8e067ac249a79e4e5c36bc95a41d13e36b6d691552f278a5c5cddbf","sha256:2b47e90799d5c6b6e604ad686e5efbada40fc28921c2e8e5fb4ae52a371ffb3c"],"state_sha256":"2b9d459ced4644d39dec50e5dd83fedf8a973ff896ba5a32686e0fd4cd7ebf3d"}