{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LSJZ5I7MRWVVKWCEFBMDSBS4UN","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":"854d3c58af5cb454ed6da03984c14ea4273f040697a1916bebbfda3ca9f0ecb8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T15:51:04Z","title_canon_sha256":"9932f72194202b8d7dd89d5356f175e454a4ac629dc27c81c761c15f5750a3d0"},"schema_version":"1.0","source":{"id":"2406.01462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01462","created_at":"2026-07-05T08:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01462v2","created_at":"2026-07-05T08:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01462","created_at":"2026-07-05T08:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"LSJZ5I7MRWVV","created_at":"2026-07-05T08:44:38Z"},{"alias_kind":"pith_short_16","alias_value":"LSJZ5I7MRWVVKWCE","created_at":"2026-07-05T08:44:38Z"},{"alias_kind":"pith_short_8","alias_value":"LSJZ5I7M","created_at":"2026-07-05T08:44:38Z"}],"graph_snapshots":[{"event_id":"sha256:2d955c45601c0d40f0c503c85db77ae25d9aaeafe613022d944694530d7cbb5b","target":"graph","created_at":"2026-07-05T08:44:38Z","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/2406.01462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from human preference data has emerged as the dominant paradigm for fine-tuning large language models (LLMs). The two most common families of techniques -- online reinforcement learning (RL) such as Proximal Policy Optimization (PPO) and offline contrastive methods such as Direct Preference Optimization (DPO) -- were positioned as equivalent in prior work due to the fact that both have to start from the same offline preference dataset. To further expand our theoretical understanding of the similarities and differences between online and offline techniques for preference fine-tuning, w","authors_text":"Aarti Singh, Gokul Swamy, J. Andrew Bagnell, Wen Sun, Yuda Song","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T15:51:04Z","title":"The Importance of Online Data: Understanding Preference Fine-tuning via Coverage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01462","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":"sha256:80b54a705d43c99547ef7b7aebf860e61e7dc0921335192909e7014ea106d61e","target":"record","created_at":"2026-07-05T08:44:38Z","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":"854d3c58af5cb454ed6da03984c14ea4273f040697a1916bebbfda3ca9f0ecb8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T15:51:04Z","title_canon_sha256":"9932f72194202b8d7dd89d5356f175e454a4ac629dc27c81c761c15f5750a3d0"},"schema_version":"1.0","source":{"id":"2406.01462","kind":"arxiv","version":2}},"canonical_sha256":"5c939ea3ec8dab555844285839065ca37c00fe5e9a3677ec1af721f536c6c09f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c939ea3ec8dab555844285839065ca37c00fe5e9a3677ec1af721f536c6c09f","first_computed_at":"2026-07-05T08:44:38.949668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:38.949668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gInsAOnvxwlrlt91PVr8DIPlh66oj0lcGNHp8CM0JPoOSEZ3Uaj9XyUWQMnQvhLy6pAHPaCrfccgjMiBuI3GAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:38.950215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80b54a705d43c99547ef7b7aebf860e61e7dc0921335192909e7014ea106d61e","sha256:2d955c45601c0d40f0c503c85db77ae25d9aaeafe613022d944694530d7cbb5b"],"state_sha256":"3804d00f7ef3858b3edf8b87b8fb9cc97c8b740acf9cdd7fc2cb413292cc58c7"}