{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XHED7ZH4CVCKIOPSDCL4BT5NJV","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":"1a4c5877b5736f2a708e99e01f080a8fcf2ee6077e62de62349d5c91059bb718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T17:11:37Z","title_canon_sha256":"2af15a2d0e8ab8c746885e80d4d81c0aeed32c07892d205b00226f1dba36caed"},"schema_version":"1.0","source":{"id":"2306.01693","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01693","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01693v2","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01693","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"XHED7ZH4CVCK","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"XHED7ZH4CVCKIOPS","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"XHED7ZH4","created_at":"2026-07-05T07:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:e086960b4e816287dd2bacb230b6985f60f1ab41cb7183c14da54d2963e505c5","target":"graph","created_at":"2026-07-05T07:06:29Z","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/2306.01693/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are transformed into a learning signal - has recently shown promise in addressing these issues. However, such holistic feedback conveys limited information on long text outputs; it does not indicate which aspects of the outputs influenced user preference; e.g., which parts contain what type(s) of errors. In this paper, we use fine-grained human feedback (e.g., which","authors_text":"Alane Suhr, Hannaneh Hajishirzi, Mari Ostendorf, Noah A. Smith, Nouha Dziri, Prithviraj Ammanabrolu, Weijia Shi, Yushi Hu, Zeqiu Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T17:11:37Z","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01693","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:d6b50ec40f97012a22053bd27d2785c3a063540f943c60c289095ca9b57847b9","target":"record","created_at":"2026-07-05T07:06:29Z","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":"1a4c5877b5736f2a708e99e01f080a8fcf2ee6077e62de62349d5c91059bb718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T17:11:37Z","title_canon_sha256":"2af15a2d0e8ab8c746885e80d4d81c0aeed32c07892d205b00226f1dba36caed"},"schema_version":"1.0","source":{"id":"2306.01693","kind":"arxiv","version":2}},"canonical_sha256":"b9c83fe4fc1544a439f21897c0cfad4d716d2c31f923c2d3715de71dc0325558","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9c83fe4fc1544a439f21897c0cfad4d716d2c31f923c2d3715de71dc0325558","first_computed_at":"2026-07-05T07:06:29.170613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:29.170613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U0Y6AFh72y9OfjyqyO7YLixa8IQkP9SxjZlPVhgLjkBR6Dl4FN1ou/Kmj92pdhE1KuqT+06iC2h5gGb6bIEZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:29.171094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01693","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6b50ec40f97012a22053bd27d2785c3a063540f943c60c289095ca9b57847b9","sha256:e086960b4e816287dd2bacb230b6985f60f1ab41cb7183c14da54d2963e505c5"],"state_sha256":"5e9dfc49ef44f97004c0e16fccbdbae308f72d12b19f29b94e644f33737afa40"}