{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SPCWOQ7BUGJKTBI77APJ5Y5XUK","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":"4288ca0e5f408eb0a4707a88f26873c458b51a4b6305a9f67d7b6e047ac30829","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T14:50:25Z","title_canon_sha256":"f4eb5083672343c86a764accb285acaa4855c916de1d3734fa81b23e26d51a63"},"schema_version":"1.0","source":{"id":"2502.00814","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00814","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00814v2","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00814","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"SPCWOQ7BUGJK","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"SPCWOQ7BUGJKTBI7","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"SPCWOQ7B","created_at":"2026-07-05T11:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:9cb97df2dc0c77c8e1560b1cbb1029f971aa9eebbbb811c27ec01c4e7a257a35","target":"graph","created_at":"2026-07-05T11:04:44Z","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/2502.00814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward model and employing a reinforcement learning algorithm to maximize the reward model's scores. However, these reward models are susceptible to exploitation through various superficial confounding factors, with length bias emerging as a particularly significant concern. Moreover, while the pronounced impact of length bias on preference modeling suggests that LLMs possess an inherent sensitivity to length perception, our","authors_text":"Houqiang Li, Jianfeng Cai, Jinhua Zhu, Li Li, Ruopei Sun, Wengang Zhou, Yue Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T14:50:25Z","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00814","kind":"arxiv","version":2},"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":"sha256:8b5d501652d2c34a1ee629fbdd9bf4e40d61f89dd762fd66efcced0672f5d3fa","target":"record","created_at":"2026-07-05T11:04:44Z","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":"4288ca0e5f408eb0a4707a88f26873c458b51a4b6305a9f67d7b6e047ac30829","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T14:50:25Z","title_canon_sha256":"f4eb5083672343c86a764accb285acaa4855c916de1d3734fa81b23e26d51a63"},"schema_version":"1.0","source":{"id":"2502.00814","kind":"arxiv","version":2}},"canonical_sha256":"93c56743e1a192a9851ff81e9ee3b7a2b485db1d47a10060d0805b04a75ade0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93c56743e1a192a9851ff81e9ee3b7a2b485db1d47a10060d0805b04a75ade0c","first_computed_at":"2026-07-05T11:04:44.909305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:44.909305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wBSOh2Hy2e+0xerIf515AqxPFf3uYmJuutmtNbk5JyAwKCaj56eL7xidzv6aB2YwUM0qTQiD67YnUoQMH8pWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:44.909817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00814","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b5d501652d2c34a1ee629fbdd9bf4e40d61f89dd762fd66efcced0672f5d3fa","sha256:9cb97df2dc0c77c8e1560b1cbb1029f971aa9eebbbb811c27ec01c4e7a257a35"],"state_sha256":"8866bbcbb48d4b806e04db46854b69c9d37c2584f28eef0c2790186d40069466"}