{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SGNGAQJ62EBBZ5GOXAJ4Z7K33J","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":"52f22efbb3828268e197985c4080609384c3416143399d03b95b1f09049bf555","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-06T06:17:56Z","title_canon_sha256":"87e1bd669244c78947c89f0a9e1bcda26b6c7cf3e909b5030129a4a3aec8fa4b"},"schema_version":"1.0","source":{"id":"2501.02790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02790","created_at":"2026-07-05T09:57:12Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02790v1","created_at":"2026-07-05T09:57:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02790","created_at":"2026-07-05T09:57:12Z"},{"alias_kind":"pith_short_12","alias_value":"SGNGAQJ62EBB","created_at":"2026-07-05T09:57:12Z"},{"alias_kind":"pith_short_16","alias_value":"SGNGAQJ62EBBZ5GO","created_at":"2026-07-05T09:57:12Z"},{"alias_kind":"pith_short_8","alias_value":"SGNGAQJ6","created_at":"2026-07-05T09:57:12Z"}],"graph_snapshots":[{"event_id":"sha256:6ee44eca4c4244f75de91bb0d675c360ae61571be668143a3c5173e194c041d6","target":"graph","created_at":"2026-07-05T09:57:12Z","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/2501.02790/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 been widely adopted to align language models (LMs) with human preference. Prior RLHF works typically take a bandit formulation, which, though intuitive, ignores the sequential nature of LM generation and can suffer from the sparse reward issue. While recent works propose dense token-level RLHF, treating each token as an action may be oversubtle to proper reward assignment. In this paper, we seek to get the best of both by training and utilizing a segment-level reward model, which assigns a reward to each semantically complete text segment t","authors_text":"Hany Awadalla, Mingyuan Zhou, Shentao Yang, Weizhu Chen, Yueqin Yin, Yujia Xie, Yuting Sun, Ziyi Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-06T06:17:56Z","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02790","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:a44c649e0b7b38504667442e2f825768758268113d7bc0fa256de09ce61a8062","target":"record","created_at":"2026-07-05T09:57:12Z","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":"52f22efbb3828268e197985c4080609384c3416143399d03b95b1f09049bf555","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-06T06:17:56Z","title_canon_sha256":"87e1bd669244c78947c89f0a9e1bcda26b6c7cf3e909b5030129a4a3aec8fa4b"},"schema_version":"1.0","source":{"id":"2501.02790","kind":"arxiv","version":1}},"canonical_sha256":"919a60413ed1021cf4ceb813ccfd5bda4f4fde2eada897c6b612f4d0b8cb9cef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"919a60413ed1021cf4ceb813ccfd5bda4f4fde2eada897c6b612f4d0b8cb9cef","first_computed_at":"2026-07-05T09:57:12.270516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:12.270516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0QSuQ8OTAAoIdoqw0n++276KYKGkn5jOw68mORkmInp+9rgn1X04HLUjyWunaG2Gb8Y7cESL+0ql4F3DjOdjDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:12.270959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a44c649e0b7b38504667442e2f825768758268113d7bc0fa256de09ce61a8062","sha256:6ee44eca4c4244f75de91bb0d675c360ae61571be668143a3c5173e194c041d6"],"state_sha256":"bd67bb2376f3d216bdfa0a05271236e153643b0384d429aafe7acd839162f6c9"}