{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SP4U6PAK2O5HGN2ZVGFHQGORRT","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":"138e00ccd9e1e58c2ba4456b1a4c3010d6b2a4b19252fdd1710a836793a59a99","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-01T13:14:41Z","title_canon_sha256":"c6cc578ebfca8a50415cc6d7850c44e36aaea28375d0fe43f9c6d14571e67531"},"schema_version":"1.0","source":{"id":"2409.00717","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00717","created_at":"2026-07-05T09:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00717v3","created_at":"2026-07-05T09:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00717","created_at":"2026-07-05T09:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"SP4U6PAK2O5H","created_at":"2026-07-05T09:58:59Z"},{"alias_kind":"pith_short_16","alias_value":"SP4U6PAK2O5HGN2Z","created_at":"2026-07-05T09:58:59Z"},{"alias_kind":"pith_short_8","alias_value":"SP4U6PAK","created_at":"2026-07-05T09:58:59Z"}],"graph_snapshots":[{"event_id":"sha256:c5497ca0e0341ea7b876d7facb07a7659d52a09e5e886dba555486608f9cbaf2","target":"graph","created_at":"2026-07-05T09:58:59Z","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/2409.00717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We initiate the study of Preference-Based Multi-Agent Reinforcement Learning (PbMARL), exploring both theoretical foundations and empirical validations. We define the task as identifying the Nash equilibrium from a preference-only offline dataset in general-sum games, a problem marked by the challenge of sparse feedback signals. Our theory establishes the upper complexity bounds for Nash Equilibrium in effective PbMARL, demonstrating that single-policy coverage is inadequate and highlighting the importance of unilateral dataset coverage. These theoretical insights are verified through comprehe","authors_text":"Natalia Zhang, Qiwen Cui, Runlong Zhou, Sham M. Kakade, Simon S. Du, Xinqi Wang","cross_cats":["cs.AI","cs.GT","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-01T13:14:41Z","title":"Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00717","kind":"arxiv","version":3},"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":"sha256:1b366c5f1c4f4f584319f0cd8d04fc4f52c8eadffbf768b75f858f2ff3a35df5","target":"record","created_at":"2026-07-05T09:58:59Z","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":"138e00ccd9e1e58c2ba4456b1a4c3010d6b2a4b19252fdd1710a836793a59a99","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-01T13:14:41Z","title_canon_sha256":"c6cc578ebfca8a50415cc6d7850c44e36aaea28375d0fe43f9c6d14571e67531"},"schema_version":"1.0","source":{"id":"2409.00717","kind":"arxiv","version":3}},"canonical_sha256":"93f94f3c0ad3ba733759a98a7819d18cd0203f2f5e773997c31de220a532524c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93f94f3c0ad3ba733759a98a7819d18cd0203f2f5e773997c31de220a532524c","first_computed_at":"2026-07-05T09:58:59.569222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:59.569222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v7l9aTcsMzMUqVKv2LS1DHvMZHDtbUFErLaYewu3BvT1uf3ZcB0rMALgOPtCMjmIPN65KEL5Y3UJSUOeygseDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:59.569702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00717","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b366c5f1c4f4f584319f0cd8d04fc4f52c8eadffbf768b75f858f2ff3a35df5","sha256:c5497ca0e0341ea7b876d7facb07a7659d52a09e5e886dba555486608f9cbaf2"],"state_sha256":"2602c0c745d2ef5aba6e140f0d276e0a77757947269dec5cb7f2efc642877ae8"}