{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XZREHQPHNVO5PMCKBTYKBZAZ6N","short_pith_number":"pith:XZREHQPH","schema_version":"1.0","canonical_sha256":"be6243c1e76d5dd7b04a0cf0a0e419f3652009274b5d0fedd1b70aa39496b9ea","source":{"kind":"arxiv","id":"2602.18291","version":2},"attestation_state":"computed","paper":{"title":"Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hai Zhong, Lihua Zhang, Longbo Huang, Qingxin Xia, Xun Wang, Zhuoran Li","submitted_at":"2026-02-20T15:38:02Z","abstract_excerpt":"Online Multi-Agent Reinforcement Learning (MARL) is a prominent framework for efficient agent coordination. Crucially, enhancing policy expressiveness is pivotal for achieving superior performance. Diffusion-based generative models are well-positioned to meet this demand, having demonstrated remarkable expressiveness and multimodal representation in image generation and offline settings. Yet, their potential in online MARL remains largely under-explored. A major obstacle is that the intractable likelihoods of diffusion models impede entropy-based exploration and coordination. To tackle this ch"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.18291","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-20T15:38:02Z","cross_cats_sorted":[],"title_canon_sha256":"3ac9b89c32b0416b00110d3e954d40a52e39a13362a6348b74a416a62df976ba","abstract_canon_sha256":"397a66e54ad289c88c74d8dbfaae4d3e168602e6bb76c4bb5bf066f36d0ef34a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:30.819567Z","signature_b64":"nYK0uQ6XM6Oh16ditVMO9pVdfYU3SMM6t70B5avPQ+t/F2d7n8AdChjnZ6LIzSH0dkIpBnITpN3ZSlc6/xI1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be6243c1e76d5dd7b04a0cf0a0e419f3652009274b5d0fedd1b70aa39496b9ea","last_reissued_at":"2026-06-11T01:09:30.818653Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:30.818653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hai Zhong, Lihua Zhang, Longbo Huang, Qingxin Xia, Xun Wang, Zhuoran Li","submitted_at":"2026-02-20T15:38:02Z","abstract_excerpt":"Online Multi-Agent Reinforcement Learning (MARL) is a prominent framework for efficient agent coordination. Crucially, enhancing policy expressiveness is pivotal for achieving superior performance. Diffusion-based generative models are well-positioned to meet this demand, having demonstrated remarkable expressiveness and multimodal representation in image generation and offline settings. Yet, their potential in online MARL remains largely under-explored. A major obstacle is that the intractable likelihoods of diffusion models impede entropy-based exploration and coordination. To tackle this ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18291","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.18291/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.18291","created_at":"2026-06-11T01:09:30.818797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18291v2","created_at":"2026-06-11T01:09:30.818797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18291","created_at":"2026-06-11T01:09:30.818797+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZREHQPHNVO5","created_at":"2026-06-11T01:09:30.818797+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZREHQPHNVO5PMCK","created_at":"2026-06-11T01:09:30.818797+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZREHQPH","created_at":"2026-06-11T01:09:30.818797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.11485","citing_title":"Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N","json":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N.json","graph_json":"https://pith.science/api/pith-number/XZREHQPHNVO5PMCKBTYKBZAZ6N/graph.json","events_json":"https://pith.science/api/pith-number/XZREHQPHNVO5PMCKBTYKBZAZ6N/events.json","paper":"https://pith.science/paper/XZREHQPH"},"agent_actions":{"view_html":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N","download_json":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N.json","view_paper":"https://pith.science/paper/XZREHQPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18291&json=true","fetch_graph":"https://pith.science/api/pith-number/XZREHQPHNVO5PMCKBTYKBZAZ6N/graph.json","fetch_events":"https://pith.science/api/pith-number/XZREHQPHNVO5PMCKBTYKBZAZ6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N/action/storage_attestation","attest_author":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N/action/author_attestation","sign_citation":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N/action/citation_signature","submit_replication":"https://pith.science/pith/XZREHQPHNVO5PMCKBTYKBZAZ6N/action/replication_record"}},"created_at":"2026-06-11T01:09:30.818797+00:00","updated_at":"2026-06-11T01:09:30.818797+00:00"}