{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F22CO2NGPFAFN7MQNIVMTAHV6T","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":"60ad1e61578574f91cbf0f509033fb84e85ded7bd01d6f5cfb9c431f15bd081d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T12:47:13Z","title_canon_sha256":"43dd403520cfb25f6110b9815ff8c47f30fdf9950d3c016ff8dd200215065cbd"},"schema_version":"1.0","source":{"id":"2205.11275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11275","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11275v2","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11275","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"pith_short_12","alias_value":"F22CO2NGPFAF","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"pith_short_16","alias_value":"F22CO2NGPFAFN7MQ","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"pith_short_8","alias_value":"F22CO2NG","created_at":"2026-07-05T05:08:52Z"}],"graph_snapshots":[{"event_id":"sha256:10a14c21bef8d87483882e017e13d439fde8e186688c251f026279010ab8c891","target":"graph","created_at":"2026-07-05T05:08:52Z","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/2205.11275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is frequently employed in fine-tuning large language models (LMs), such as GPT-3, to penalize them for undesirable features of generated sequences, such as offensiveness, social bias, harmfulness or falsehood. The RL formulation involves treating the LM as a policy and updating it to maximise the expected value of a reward function which captures human preferences, such as non-offensiveness. In this paper, we analyze challenges associated with treating a language model as an RL policy and show how avoiding those challenges requires moving beyond the RL paradigm. We ","authors_text":"Christopher L Buckley, Ethan Perez, Tomasz Korbak","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T12:47:13Z","title":"RL with KL penalties is better viewed as Bayesian inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11275","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":"sha256:7500dc3d1cb3912c27b349c52d75ad2291e018f1cd52cf7946aed01c3d0756ba","target":"record","created_at":"2026-07-05T05:08:52Z","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":"60ad1e61578574f91cbf0f509033fb84e85ded7bd01d6f5cfb9c431f15bd081d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T12:47:13Z","title_canon_sha256":"43dd403520cfb25f6110b9815ff8c47f30fdf9950d3c016ff8dd200215065cbd"},"schema_version":"1.0","source":{"id":"2205.11275","kind":"arxiv","version":2}},"canonical_sha256":"2eb42769a6794056fd906a2ac980f5f4cbfc8200fa2d6daa52854dfabce69fdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2eb42769a6794056fd906a2ac980f5f4cbfc8200fa2d6daa52854dfabce69fdd","first_computed_at":"2026-07-05T05:08:52.043624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:52.043624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2z3OpCwjJADnUGeOhRyvt4XGPqpfQxhb720hO1pqivap8FSJeiVdrC7G3x2pDo6hf6XChpQ6zzyYIdZzyEFeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:52.044120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7500dc3d1cb3912c27b349c52d75ad2291e018f1cd52cf7946aed01c3d0756ba","sha256:10a14c21bef8d87483882e017e13d439fde8e186688c251f026279010ab8c891"],"state_sha256":"b0f083c74505b8073d3aa9adf64bacefaacbb93bf95f5133cc1d6be1e21d22e6"}