{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MD2XWLEXXVEACL7G7E7HQBH4LJ","short_pith_number":"pith:MD2XWLEX","canonical_record":{"source":{"id":"2305.17330","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-27T02:14:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3a576f2344d0d768ec6332e6bc2c5bfc8648ab58b5cd263be0bc3da32a1ccb8b","abstract_canon_sha256":"b7a735ff8ef4e73df77d5a8c6a0db04d190a7ed45d1ffa17d1a979ac427c6a54"},"schema_version":"1.0"},"canonical_sha256":"60f57b2c97bd48012fe6f93e7804fc5a7286c05b0657ae131a551af71229c4c8","source":{"kind":"arxiv","id":"2305.17330","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17330","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17330v5","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17330","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"MD2XWLEXXVEA","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"pith_short_16","alias_value":"MD2XWLEXXVEACL7G","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"pith_short_8","alias_value":"MD2XWLEX","created_at":"2026-07-05T09:55:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MD2XWLEXXVEACL7G7E7HQBH4LJ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17330","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-27T02:14:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3a576f2344d0d768ec6332e6bc2c5bfc8648ab58b5cd263be0bc3da32a1ccb8b","abstract_canon_sha256":"b7a735ff8ef4e73df77d5a8c6a0db04d190a7ed45d1ffa17d1a979ac427c6a54"},"schema_version":"1.0"},"canonical_sha256":"60f57b2c97bd48012fe6f93e7804fc5a7286c05b0657ae131a551af71229c4c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:52.041781Z","signature_b64":"hayjBKibfxQAICvLwJWzGbsOil8AYETyrfIXeebkeHm0tgv+wEsYMAXsuy8nSubtaTLnQZKkzE0+2NBj1WEPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60f57b2c97bd48012fe6f93e7804fc5a7286c05b0657ae131a551af71229c4c8","last_reissued_at":"2026-07-05T09:55:52.041251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:52.041251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17330","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCz8hIpqIfK+yOVn6sVOobrISgADF8K+y6E8ebiHTrQcQuVDedrSKr1JWHCg24Tu4EEQn+GKiK15sueVtV18DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T20:37:45.119994Z"},"content_sha256":"814ddd565a27da130e35faaffe9e2f09141284bec69694db0baa290a12777c43","schema_version":"1.0","event_id":"sha256:814ddd565a27da130e35faaffe9e2f09141284bec69694db0baa290a12777c43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MD2XWLEXXVEACL7G7E7HQBH4LJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MADiff: Offline Multi-agent Learning with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bingyi Kang, Liyuan Mao, Minghuan Liu, Minkai Xu, Stefano Ermon, Weinan Zhang, Yong Yu, Zhengbang Zhu","submitted_at":"2023-05-27T02:14:09Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to learn policies from pre-existing datasets without further interactions, making it a challenging task. Q-learning algorithms struggle with extrapolation errors in offline settings, while supervised learning methods are constrained by model expressiveness. Recently, diffusion models (DMs) have shown promise in overcoming these limitations in single-agent learning, but their application in multi-agent scenarios remains unclear. Generating trajectories for each agent with independent DMs may impede coordination, while concatenating all agents' informatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17330","kind":"arxiv","version":5},"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/2305.17330/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6BtXhSU5AEWTluyVqwPtn/xTssZ98Fb6xN6hK/ogbHycEakBHJai+MwcSuPZJAPAhry2iNR+Hfy/8EKrcYgPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T20:37:45.120389Z"},"content_sha256":"81b40283f4ea584af493cfac6ed8f3cbc12bfa07fb01027a1daf0f241dd93f13","schema_version":"1.0","event_id":"sha256:81b40283f4ea584af493cfac6ed8f3cbc12bfa07fb01027a1daf0f241dd93f13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MD2XWLEXXVEACL7G7E7HQBH4LJ/bundle.json","state_url":"https://pith.science/pith/MD2XWLEXXVEACL7G7E7HQBH4LJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MD2XWLEXXVEACL7G7E7HQBH4LJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T20:37:45Z","links":{"resolver":"https://pith.science/pith/MD2XWLEXXVEACL7G7E7HQBH4LJ","bundle":"https://pith.science/pith/MD2XWLEXXVEACL7G7E7HQBH4LJ/bundle.json","state":"https://pith.science/pith/MD2XWLEXXVEACL7G7E7HQBH4LJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MD2XWLEXXVEACL7G7E7HQBH4LJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MD2XWLEXXVEACL7G7E7HQBH4LJ","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":"b7a735ff8ef4e73df77d5a8c6a0db04d190a7ed45d1ffa17d1a979ac427c6a54","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-27T02:14:09Z","title_canon_sha256":"3a576f2344d0d768ec6332e6bc2c5bfc8648ab58b5cd263be0bc3da32a1ccb8b"},"schema_version":"1.0","source":{"id":"2305.17330","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17330","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17330v5","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17330","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"MD2XWLEXXVEA","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"pith_short_16","alias_value":"MD2XWLEXXVEACL7G","created_at":"2026-07-05T09:55:52Z"},{"alias_kind":"pith_short_8","alias_value":"MD2XWLEX","created_at":"2026-07-05T09:55:52Z"}],"graph_snapshots":[{"event_id":"sha256:81b40283f4ea584af493cfac6ed8f3cbc12bfa07fb01027a1daf0f241dd93f13","target":"graph","created_at":"2026-07-05T09:55:52Z","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/2305.17330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to learn policies from pre-existing datasets without further interactions, making it a challenging task. Q-learning algorithms struggle with extrapolation errors in offline settings, while supervised learning methods are constrained by model expressiveness. Recently, diffusion models (DMs) have shown promise in overcoming these limitations in single-agent learning, but their application in multi-agent scenarios remains unclear. Generating trajectories for each agent with independent DMs may impede coordination, while concatenating all agents' informatio","authors_text":"Bingyi Kang, Liyuan Mao, Minghuan Liu, Minkai Xu, Stefano Ermon, Weinan Zhang, Yong Yu, Zhengbang Zhu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-27T02:14:09Z","title":"MADiff: Offline Multi-agent Learning with Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17330","kind":"arxiv","version":5},"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":"sha256:814ddd565a27da130e35faaffe9e2f09141284bec69694db0baa290a12777c43","target":"record","created_at":"2026-07-05T09:55:52Z","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":"b7a735ff8ef4e73df77d5a8c6a0db04d190a7ed45d1ffa17d1a979ac427c6a54","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-27T02:14:09Z","title_canon_sha256":"3a576f2344d0d768ec6332e6bc2c5bfc8648ab58b5cd263be0bc3da32a1ccb8b"},"schema_version":"1.0","source":{"id":"2305.17330","kind":"arxiv","version":5}},"canonical_sha256":"60f57b2c97bd48012fe6f93e7804fc5a7286c05b0657ae131a551af71229c4c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60f57b2c97bd48012fe6f93e7804fc5a7286c05b0657ae131a551af71229c4c8","first_computed_at":"2026-07-05T09:55:52.041251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:52.041251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hayjBKibfxQAICvLwJWzGbsOil8AYETyrfIXeebkeHm0tgv+wEsYMAXsuy8nSubtaTLnQZKkzE0+2NBj1WEPDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:52.041781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17330","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:814ddd565a27da130e35faaffe9e2f09141284bec69694db0baa290a12777c43","sha256:81b40283f4ea584af493cfac6ed8f3cbc12bfa07fb01027a1daf0f241dd93f13"],"state_sha256":"87bb3fa434b0800ee6ac7bfda5e36dcaa8b3f3b78a8498e36cde5a522e56196b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6a4Y544SxhHo9L1cTCn2PU54UVu1+qOtanhE8LhDNvZ5FjzHVDLPrCWJmPZqye7RaVRxQAody1OVhS2t2jKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T20:37:45.122936Z","bundle_sha256":"4f9d35761fc8a71f08a5ecbafbf5e50cb5cad175bd2f13a318c94e963b98cdb5"}}