{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BWSHQW4XEE2OK4FPWTYV2HNSUL","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":"70aadf2f264a441e5e67d1236bdd84fd3121e540b45e7e936544905fa80bf113","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T11:42:31Z","title_canon_sha256":"a48156eb0fe0b4d429b0ee37254b5321043a6a5691a1675dfee857a519a9db0d"},"schema_version":"1.0","source":{"id":"2505.05968","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05968","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05968v3","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05968","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"BWSHQW4XEE2O","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"BWSHQW4XEE2OK4FP","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"BWSHQW4X","created_at":"2026-05-29T01:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:54cd6d69cffb442ce1ec9bce7dcede3906330e3da516779f9b023ac4d39e118a","target":"graph","created_at":"2026-05-29T01:04:53Z","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/2505.05968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts, particularly stemming from the high dimensionality of joint action spaces and the presence of out-of-distribution joint action selections. In this work, we highlight that a fundamental challenge in offline MARL arises from the multi-equilibrium nature of cooperative tasks, which induces a highly multimodal joint behavior policy space coupled with heterogeneous-quality behavior data. This makes it difficult for individual policy regularization to align with a consistent coordinati","authors_text":"Baoxiang Wang, Dan Qiao, Hongyuan Zha, Shanchao Yang, Wenhao Li","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T11:42:31Z","title":"Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05968","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":"sha256:7dce9044f6265c10613c66e062a9e722a6fd64b186586cde2a29b103becc66a8","target":"record","created_at":"2026-05-29T01:04:53Z","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":"70aadf2f264a441e5e67d1236bdd84fd3121e540b45e7e936544905fa80bf113","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T11:42:31Z","title_canon_sha256":"a48156eb0fe0b4d429b0ee37254b5321043a6a5691a1675dfee857a519a9db0d"},"schema_version":"1.0","source":{"id":"2505.05968","kind":"arxiv","version":3}},"canonical_sha256":"0da4785b972134e570afb4f15d1db2a2e442900f5dc2a25ae789140db90e5400","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0da4785b972134e570afb4f15d1db2a2e442900f5dc2a25ae789140db90e5400","first_computed_at":"2026-05-29T01:04:53.140062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:53.140062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aKOsLKN5NJh8MmbuPIeiWQ90xnlwDqS0lpkU020kioWrhvG9DLx42gfvllCKVjmRYZApIyVBvA9EoOabs9jrCQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:53.140563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05968","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dce9044f6265c10613c66e062a9e722a6fd64b186586cde2a29b103becc66a8","sha256:54cd6d69cffb442ce1ec9bce7dcede3906330e3da516779f9b023ac4d39e118a"],"state_sha256":"6274ddcb16013db2cb3f79c2156e80b983f409d4e455d6a777b58b250e4ae993"}