{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2FVU3K2AMPMXA5RS7B4HTTV4UB","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":"65fe16116269fecf80c8ec9dfba767fdb56b63b7c6de2f4ef896ab2212692dcf","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-04T04:40:54Z","title_canon_sha256":"b2d9982207b13e736eef8530710898e9f135a022e13fa29d0c004446540e95f5"},"schema_version":"1.0","source":{"id":"2307.01472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01472","created_at":"2026-06-11T01:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01472v2","created_at":"2026-06-11T01:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01472","created_at":"2026-06-11T01:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"2FVU3K2AMPMX","created_at":"2026-06-11T01:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"2FVU3K2AMPMXA5RS","created_at":"2026-06-11T01:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"2FVU3K2A","created_at":"2026-06-11T01:09:07Z"}],"graph_snapshots":[{"event_id":"sha256:99208ebaeabe822601e1d34e56b423c6678839eb358ccb0874da8c4b35b7aaa6","target":"graph","created_at":"2026-06-11T01:09:07Z","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/2307.01472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on conservatism in policy design, DOM2 enhances policy expressiveness and diversity based on diffusion model. Specifically, we incorporate a diffusion model into the policy network and propose a trajectory-based data-reweighting scheme in training. These key ingredients significantly improve algorithm robustness against environment changes and achieve significant improvements in performance, generalization and data-efficiency. ","authors_text":"Jiatai Huang, Ling Pan, Longbo Huang, Zhuoran Li","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-04T04:40:54Z","title":"Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01472","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":"sha256:33681fd61c5e4c03e6291ce7466ba86bcef920311a18684b7ed2e1417abf0929","target":"record","created_at":"2026-06-11T01:09:07Z","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":"65fe16116269fecf80c8ec9dfba767fdb56b63b7c6de2f4ef896ab2212692dcf","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-04T04:40:54Z","title_canon_sha256":"b2d9982207b13e736eef8530710898e9f135a022e13fa29d0c004446540e95f5"},"schema_version":"1.0","source":{"id":"2307.01472","kind":"arxiv","version":2}},"canonical_sha256":"d16b4dab4063d9707632f87879cebca04bc2cdc6255544ec6685f4d2850caae8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d16b4dab4063d9707632f87879cebca04bc2cdc6255544ec6685f4d2850caae8","first_computed_at":"2026-06-11T01:09:07.164037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:07.164037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KQW7aPVaEf1wgRpLeCo1C6eJr9RUItmPFO2FRjZnFTdmwJi2a2ttUCYfQSZvXQPuqi7jJzGsQ3Dc2HKFxvTeCg==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:07.164971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33681fd61c5e4c03e6291ce7466ba86bcef920311a18684b7ed2e1417abf0929","sha256:99208ebaeabe822601e1d34e56b423c6678839eb358ccb0874da8c4b35b7aaa6"],"state_sha256":"473fa6c4eeb1357dcd97649e6d405048817d798a97e5b9e5fda67ee7814c571c"}