{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2LPLKVGTVT425IORBIYTBYB3NA","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":"22ac963621ca784df0bb899803a79787833f4e01b6e4136604344979e95b34c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T02:45:21Z","title_canon_sha256":"e5acba440d9e98e9efb668039ba3a62991f0b6c27f3fc6d6cd7c04d8a5873b0e"},"schema_version":"1.0","source":{"id":"2411.08302","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08302","created_at":"2026-07-05T12:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08302v2","created_at":"2026-07-05T12:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08302","created_at":"2026-07-05T12:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"2LPLKVGTVT42","created_at":"2026-07-05T12:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"2LPLKVGTVT425IOR","created_at":"2026-07-05T12:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"2LPLKVGT","created_at":"2026-07-05T12:09:11Z"}],"graph_snapshots":[{"event_id":"sha256:58914f6c405c9ab8289ee8ef3ea8079fdd4ee7f1197d13774a9fe1118c20adcf","target":"graph","created_at":"2026-07-05T12:09:11Z","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/2411.08302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) offers a promising approach to aligning large language models (LLMs) with human preferences. Typically, a reward model is trained or supplied to act as a proxy for humans in evaluating generated responses during the reinforcement training phase. However, current reward models operate as sequence-to-one models, allocating a single, sparse, and delayed reward to an entire output sequence. This approach may overlook the significant contributions of individual tokens toward the desired outcome. To this end, we propose a more fine-grained, token-lev","authors_text":"Cheng Yang, Jiahui Li, Jun Zhou, Kun Kuang, Lin Li, Long Chen, Tai-Wei Chang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T02:45:21Z","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08302","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":"sha256:4d76ade5e5fecf65edb20f413448ac307516525f21383b8cdf03e860fdff211c","target":"record","created_at":"2026-07-05T12:09:11Z","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":"22ac963621ca784df0bb899803a79787833f4e01b6e4136604344979e95b34c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T02:45:21Z","title_canon_sha256":"e5acba440d9e98e9efb668039ba3a62991f0b6c27f3fc6d6cd7c04d8a5873b0e"},"schema_version":"1.0","source":{"id":"2411.08302","kind":"arxiv","version":2}},"canonical_sha256":"d2deb554d3acf9aea1d10a3130e03b6820eff0653a7bb5c38a1de9f49faab699","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2deb554d3acf9aea1d10a3130e03b6820eff0653a7bb5c38a1de9f49faab699","first_computed_at":"2026-07-05T12:09:11.411236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:11.411236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l1qe52xlbQ9ExqRvy0yk/2RJuN1Uq70QRmsdxQN2Y8QqaizbJiXU836i3jwyu6gWqwlVAkjEeqv3TbPlBFqrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:11.411725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08302","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d76ade5e5fecf65edb20f413448ac307516525f21383b8cdf03e860fdff211c","sha256:58914f6c405c9ab8289ee8ef3ea8079fdd4ee7f1197d13774a9fe1118c20adcf"],"state_sha256":"0c0c07f6110d138ef9280bbd9b3f479ba09306972a092c025c6a7b8d76f869fb"}