{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:W4XSS5IG3A5YYE6QH372RGY7LQ","short_pith_number":"pith:W4XSS5IG","canonical_record":{"source":{"id":"1803.11485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T14:23:39Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"b8966e267a018f4e59cafaff8614422d9e8aa88bbdd8f08bde3069ea0db27d1c","abstract_canon_sha256":"aa91bb62c75081d4a3636e5b253fb5be334bd57d3e6461768db0f002745f4aef"},"schema_version":"1.0"},"canonical_sha256":"b72f297506d83b8c13d03effa89b1f5c26604e1acc33f1cb91f7eb5d5771a7e9","source":{"kind":"arxiv","id":"1803.11485","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11485","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11485v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11485","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"W4XSS5IG3A5Y","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W4XSS5IG3A5YYE6Q","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W4XSS5IG","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:W4XSS5IG3A5YYE6QH372RGY7LQ","target":"record","payload":{"canonical_record":{"source":{"id":"1803.11485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T14:23:39Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"b8966e267a018f4e59cafaff8614422d9e8aa88bbdd8f08bde3069ea0db27d1c","abstract_canon_sha256":"aa91bb62c75081d4a3636e5b253fb5be334bd57d3e6461768db0f002745f4aef"},"schema_version":"1.0"},"canonical_sha256":"b72f297506d83b8c13d03effa89b1f5c26604e1acc33f1cb91f7eb5d5771a7e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.143704Z","signature_b64":"0mR2O6P0+oMp+5//ihEYSqzV0i5w5CN+gYqGRlMIIqAPsUJrcWsaEQV+rwKLZYYBgP34S6oteyyGqvsldhn7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72f297506d83b8c13d03effa89b1f5c26604e1acc33f1cb91f7eb5d5771a7e9","last_reissued_at":"2026-05-18T00:14:06.142938Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.142938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.11485","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVoKu7Xb8ss+DDOMDAQhE3wDpWy3STE0EbfAlCv4yC8tZm4Mjdb4IvZa+EaIddAUSqqjyPWVjI39TFqMOQ2QBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:55:59.072130Z"},"content_sha256":"8d6821dcb0ed0e0719df7ca53c51743c0b53c5c7e2c17e84364863ce5feabd67","schema_version":"1.0","event_id":"sha256:8d6821dcb0ed0e0719df7ca53c51743c0b53c5c7e2c17e84364863ce5feabd67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:W4XSS5IG3A5YYE6QH372RGY7LQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Mikayel Samvelyan, Shimon Whiteson, Tabish Rashid","submitted_at":"2018-03-30T14:23:39Z","abstract_excerpt":"In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11485","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":""},"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":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7rzsoQPHz+EyxQZaKVuZv2do+RKG0WmCaZMLbbRoHNGDtMr8UiZqJeslzFcIK0jG/BKAIjys3ook0HxhEEz4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:55:59.072787Z"},"content_sha256":"245cf8129495e603fefa0d469b80b41b9a9f5990c82d91d0a48688b050f9c798","schema_version":"1.0","event_id":"sha256:245cf8129495e603fefa0d469b80b41b9a9f5990c82d91d0a48688b050f9c798"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/bundle.json","state_url":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/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":"2026-05-25T22:55:59Z","links":{"resolver":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ","bundle":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/bundle.json","state":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:W4XSS5IG3A5YYE6QH372RGY7LQ","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":"aa91bb62c75081d4a3636e5b253fb5be334bd57d3e6461768db0f002745f4aef","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T14:23:39Z","title_canon_sha256":"b8966e267a018f4e59cafaff8614422d9e8aa88bbdd8f08bde3069ea0db27d1c"},"schema_version":"1.0","source":{"id":"1803.11485","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11485","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11485v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11485","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"W4XSS5IG3A5Y","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W4XSS5IG3A5YYE6Q","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W4XSS5IG","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:245cf8129495e603fefa0d469b80b41b9a9f5990c82d91d0a48688b050f9c798","target":"graph","created_at":"2026-05-18T00:14:06Z","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"},"paper":{"abstract_excerpt":"In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised ","authors_text":"Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Mikayel Samvelyan, Shimon Whiteson, Tabish Rashid","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T14:23:39Z","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11485","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":"sha256:8d6821dcb0ed0e0719df7ca53c51743c0b53c5c7e2c17e84364863ce5feabd67","target":"record","created_at":"2026-05-18T00:14:06Z","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":"aa91bb62c75081d4a3636e5b253fb5be334bd57d3e6461768db0f002745f4aef","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T14:23:39Z","title_canon_sha256":"b8966e267a018f4e59cafaff8614422d9e8aa88bbdd8f08bde3069ea0db27d1c"},"schema_version":"1.0","source":{"id":"1803.11485","kind":"arxiv","version":2}},"canonical_sha256":"b72f297506d83b8c13d03effa89b1f5c26604e1acc33f1cb91f7eb5d5771a7e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b72f297506d83b8c13d03effa89b1f5c26604e1acc33f1cb91f7eb5d5771a7e9","first_computed_at":"2026-05-18T00:14:06.142938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:06.142938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0mR2O6P0+oMp+5//ihEYSqzV0i5w5CN+gYqGRlMIIqAPsUJrcWsaEQV+rwKLZYYBgP34S6oteyyGqvsldhn7Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:06.143704Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.11485","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d6821dcb0ed0e0719df7ca53c51743c0b53c5c7e2c17e84364863ce5feabd67","sha256:245cf8129495e603fefa0d469b80b41b9a9f5990c82d91d0a48688b050f9c798"],"state_sha256":"5fc637e22b3a4f80900455b22a511df208ff83132403514e2ae8bd45dcff2f4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q6bXyHx985ARReJDmvmZ2D4VQ8dkVPJKqwT5Upg5rj9SgX7NfYcB7NmH43QuzQ3AygUkZ/TfletavkGIjHOkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:55:59.075976Z","bundle_sha256":"cef180ef34f863c49dfcfc7486515c72aa5a07e07f447810734840b5b5377cc7"}}