{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5VMG3SBSKTB3BMBZWL2NWG2BKK","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":"136096e986e16997f681b34eba483618d06465835ab66bac670669358c6c960c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T17:55:02Z","title_canon_sha256":"e395bb89826f06e3b0bb9141a3f4d92dc409243a8ad590b70e54c95390cbeeb4"},"schema_version":"1.0","source":{"id":"2401.04056","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04056","created_at":"2026-07-05T08:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04056v2","created_at":"2026-07-05T08:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04056","created_at":"2026-07-05T08:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"5VMG3SBSKTB3","created_at":"2026-07-05T08:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"5VMG3SBSKTB3BMBZ","created_at":"2026-07-05T08:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"5VMG3SBS","created_at":"2026-07-05T08:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:c2e284a04029d5a03f45248ec0044599b4704c592377402ee773b4bc908f4014","target":"graph","created_at":"2026-07-05T08:31:10Z","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/2401.04056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training and is therefore rather simple to implement. Our approach is maximalist in that it provably handles non-Markovian, intransitive, and stochastic preferences while being robust to the compounding errors that plague offline approaches to sequential prediction. To achieve the preceding qualities, we build upon the concept of a Minimax Winner (MW), a notion of preference aggre","authors_text":"Alekh Agarwal, Christoph Dann, Gokul Swamy, Rahul Kidambi, Zhiwei Steven Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T17:55:02Z","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04056","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":"sha256:0f325457a584f8a9a05cefcc3c3102b1d440ad326c55893bb68b0016f9115ff8","target":"record","created_at":"2026-07-05T08:31:10Z","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":"136096e986e16997f681b34eba483618d06465835ab66bac670669358c6c960c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T17:55:02Z","title_canon_sha256":"e395bb89826f06e3b0bb9141a3f4d92dc409243a8ad590b70e54c95390cbeeb4"},"schema_version":"1.0","source":{"id":"2401.04056","kind":"arxiv","version":2}},"canonical_sha256":"ed586dc83254c3b0b039b2f4db1b415280cac033eebf04d0c52eb011fc32a2c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed586dc83254c3b0b039b2f4db1b415280cac033eebf04d0c52eb011fc32a2c9","first_computed_at":"2026-07-05T08:31:10.441380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:10.441380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g4S4B7xdV05s82vnJZ+q6qYp9jD55a6IJcb4bmE1oeGckzYjTwMX0PpCPwIZF2fV8UO9Ag7qj6UybaT1PSbNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:10.441843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.04056","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f325457a584f8a9a05cefcc3c3102b1d440ad326c55893bb68b0016f9115ff8","sha256:c2e284a04029d5a03f45248ec0044599b4704c592377402ee773b4bc908f4014"],"state_sha256":"557a51c67c8bdcc5a143e8faf627ca352c45c1bcba5a39f631e9c42e166464e1"}