{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5HP625FJU3ANV27V6W24ETO2D4","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":"b70ba21c1f381fcfdaccbacd48d7271231305e8111352645c5a3a80aa22608c0","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-13T18:22:40Z","title_canon_sha256":"cda46f3f425ff394de639b2596e3220cbda0f3272a044a773f6d4ba221f2320f"},"schema_version":"1.0","source":{"id":"2304.06767","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06767","created_at":"2026-05-18T00:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06767v4","created_at":"2026-05-18T00:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06767","created_at":"2026-05-18T00:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"5HP625FJU3AN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"5HP625FJU3ANV27V","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"5HP625FJ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:e475454f9216da316fa35b04783c06d0bafba137fb248cf79962e262bf6e743c","target":"graph","created_at":"2026-05-18T00:40:50Z","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"},"paper":{"abstract_excerpt":"Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences. Consequently, aligning these models with human ethics and preferences is an essential step toward ensuring their responsible and effective deployment in real-world applications. Prior research has primarily employed Reinforcement Learning from Human Feedback (RLHF) to address this problem, where generative models are fine-tuned with RL algorithms guided by a h","authors_text":"Deepanshu Goyal, HanZe Dong, Jipeng Zhang, Kashun Shum, Rui Pan, Shizhe Diao, Tong Zhang, Wei Xiong, Winnie Chow, Yihan Zhang","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-13T18:22:40Z","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06767","kind":"arxiv","version":4},"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":"sha256:05c8464b09f9ba29d8cc2e74087b2c802f470df1db81fbd7cb9956c36d7587d6","target":"record","created_at":"2026-05-18T00:40:50Z","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":"b70ba21c1f381fcfdaccbacd48d7271231305e8111352645c5a3a80aa22608c0","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-13T18:22:40Z","title_canon_sha256":"cda46f3f425ff394de639b2596e3220cbda0f3272a044a773f6d4ba221f2320f"},"schema_version":"1.0","source":{"id":"2304.06767","kind":"arxiv","version":4}},"canonical_sha256":"e9dfed74a9a6c0daebf5f5b5c24dda1f2a3a6685a31d755e1d7dd90bdb3bdbf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9dfed74a9a6c0daebf5f5b5c24dda1f2a3a6685a31d755e1d7dd90bdb3bdbf5","first_computed_at":"2026-05-18T00:40:50.256710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:50.256710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qWLEcZlVG1N4dLsiwhKuyUt++UzaRRIOZB1vawZ/in7LlfSM7ZM1zk1W33wWc1etap32/aUxplq/HNn2wXS8Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:50.257453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.06767","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05c8464b09f9ba29d8cc2e74087b2c802f470df1db81fbd7cb9956c36d7587d6","sha256:e475454f9216da316fa35b04783c06d0bafba137fb248cf79962e262bf6e743c"],"state_sha256":"1e437ec343b96e6b47a99ffca292d6aea645a9398c2e4210090c41a9f0b9dd80"}