{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3DC5IO76XXOBUFMSD37UMWQKD2","short_pith_number":"pith:3DC5IO76","canonical_record":{"source":{"id":"2410.01954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T18:56:10Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"71e2035bb923a98f3ee0d7d8b767202f23b5471ee314d74c093459b64c54ab17","abstract_canon_sha256":"7a9eef75cf905e389aaa8c43d8a5db4b01eb408878abde5c96635913fcd6c94e"},"schema_version":"1.0"},"canonical_sha256":"d8c5d43bfebddc1a15921eff465a0a1e834c182d0b16e29715cf09ba3c5da2c7","source":{"kind":"arxiv","id":"2410.01954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01954","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01954v1","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01954","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"3DC5IO76XXOB","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"pith_short_16","alias_value":"3DC5IO76XXOBUFMS","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"pith_short_8","alias_value":"3DC5IO76","created_at":"2026-07-05T09:14:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3DC5IO76XXOBUFMSD37UMWQKD2","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T18:56:10Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"71e2035bb923a98f3ee0d7d8b767202f23b5471ee314d74c093459b64c54ab17","abstract_canon_sha256":"7a9eef75cf905e389aaa8c43d8a5db4b01eb408878abde5c96635913fcd6c94e"},"schema_version":"1.0"},"canonical_sha256":"d8c5d43bfebddc1a15921eff465a0a1e834c182d0b16e29715cf09ba3c5da2c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:58.200947Z","signature_b64":"w7SsbjZPvmYeYAPjNsA+FFnmItQLVVSpcBOh550+i42seJ4+lAEPnOv07r4y8PMUu8JjhN79VC3vw2GPY0j0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8c5d43bfebddc1a15921eff465a0a1e834c182d0b16e29715cf09ba3c5da2c7","last_reissued_at":"2026-07-05T09:14:58.200510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:58.200510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01954","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUkUAoqV4u2oF9usoaLClnTfBAD2KIZzT1srOXyTYjGpfz0laGrOb/3+RkUzem7RI61BU9t0YE7GFrRNZNOyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:39:57.958732Z"},"content_sha256":"457587d661c716c88e0cc330a2c12346d04191ebd7458a7f51fe9d9d6276a761","schema_version":"1.0","event_id":"sha256:457587d661c716c88e0cc330a2c12346d04191ebd7458a7f51fe9d9d6276a761"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3DC5IO76XXOBUFMSD37UMWQKD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Thanh Hong Nguyen, The Viet Bui, Tien Mai","submitted_at":"2024-10-02T18:56:10Z","abstract_excerpt":"Offline reinforcement learning (RL) has garnered significant attention for its ability to learn effective policies from pre-collected datasets without the need for further environmental interactions. While promising results have been demonstrated in single-agent settings, offline multi-agent reinforcement learning (MARL) presents additional challenges due to the large joint state-action space and the complexity of multi-agent behaviors. A key issue in offline RL is the distributional shift, which arises when the target policy being optimized deviates from the behavior policy that generated the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01954","kind":"arxiv","version":1},"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/2410.01954/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":"2026-07-05T09:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2vfsO1S/ZqNO55/hyBC1xrauywUSz622D1wSgu4HgxAcxFJBvGxWsDhBspyzqJ7gc2l9ajgYbvMn8O4Ut+wAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:39:57.959106Z"},"content_sha256":"0d6ea4350b7b08b8758d5acceadd0ba3f7757ae54dbee439d1228a8066659ee9","schema_version":"1.0","event_id":"sha256:0d6ea4350b7b08b8758d5acceadd0ba3f7757ae54dbee439d1228a8066659ee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DC5IO76XXOBUFMSD37UMWQKD2/bundle.json","state_url":"https://pith.science/pith/3DC5IO76XXOBUFMSD37UMWQKD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DC5IO76XXOBUFMSD37UMWQKD2/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":"2026-07-07T13:39:57Z","links":{"resolver":"https://pith.science/pith/3DC5IO76XXOBUFMSD37UMWQKD2","bundle":"https://pith.science/pith/3DC5IO76XXOBUFMSD37UMWQKD2/bundle.json","state":"https://pith.science/pith/3DC5IO76XXOBUFMSD37UMWQKD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DC5IO76XXOBUFMSD37UMWQKD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3DC5IO76XXOBUFMSD37UMWQKD2","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":"7a9eef75cf905e389aaa8c43d8a5db4b01eb408878abde5c96635913fcd6c94e","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T18:56:10Z","title_canon_sha256":"71e2035bb923a98f3ee0d7d8b767202f23b5471ee314d74c093459b64c54ab17"},"schema_version":"1.0","source":{"id":"2410.01954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01954","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01954v1","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01954","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"3DC5IO76XXOB","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"pith_short_16","alias_value":"3DC5IO76XXOBUFMS","created_at":"2026-07-05T09:14:58Z"},{"alias_kind":"pith_short_8","alias_value":"3DC5IO76","created_at":"2026-07-05T09:14:58Z"}],"graph_snapshots":[{"event_id":"sha256:0d6ea4350b7b08b8758d5acceadd0ba3f7757ae54dbee439d1228a8066659ee9","target":"graph","created_at":"2026-07-05T09:14:58Z","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/2410.01954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) has garnered significant attention for its ability to learn effective policies from pre-collected datasets without the need for further environmental interactions. While promising results have been demonstrated in single-agent settings, offline multi-agent reinforcement learning (MARL) presents additional challenges due to the large joint state-action space and the complexity of multi-agent behaviors. A key issue in offline RL is the distributional shift, which arises when the target policy being optimized deviates from the behavior policy that generated the","authors_text":"Thanh Hong Nguyen, The Viet Bui, Tien Mai","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T18:56:10Z","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01954","kind":"arxiv","version":1},"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":"sha256:457587d661c716c88e0cc330a2c12346d04191ebd7458a7f51fe9d9d6276a761","target":"record","created_at":"2026-07-05T09:14:58Z","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":"7a9eef75cf905e389aaa8c43d8a5db4b01eb408878abde5c96635913fcd6c94e","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T18:56:10Z","title_canon_sha256":"71e2035bb923a98f3ee0d7d8b767202f23b5471ee314d74c093459b64c54ab17"},"schema_version":"1.0","source":{"id":"2410.01954","kind":"arxiv","version":1}},"canonical_sha256":"d8c5d43bfebddc1a15921eff465a0a1e834c182d0b16e29715cf09ba3c5da2c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8c5d43bfebddc1a15921eff465a0a1e834c182d0b16e29715cf09ba3c5da2c7","first_computed_at":"2026-07-05T09:14:58.200510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:58.200510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w7SsbjZPvmYeYAPjNsA+FFnmItQLVVSpcBOh550+i42seJ4+lAEPnOv07r4y8PMUu8JjhN79VC3vw2GPY0j0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:58.200947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:457587d661c716c88e0cc330a2c12346d04191ebd7458a7f51fe9d9d6276a761","sha256:0d6ea4350b7b08b8758d5acceadd0ba3f7757ae54dbee439d1228a8066659ee9"],"state_sha256":"23159fde4db87a1110ee05ee392661115c32b776333f2769ea6d649f26da72a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dC1UdunaDJyT8qqoitGGTvBF5lk20bbExGVloFSkQNsDH//MmYEiTywQoDlQh7dayB1J8RMW/+zmhHuhz6Y0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:39:57.961066Z","bundle_sha256":"d6fdf975c5721392cb85ade27269aacfa8d8504433617789db1de95ea5c99104"}}