{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KRMWVYLX6BO73MKWT7GWQ7LET2","short_pith_number":"pith:KRMWVYLX","canonical_record":{"source":{"id":"2209.12681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T13:29:22Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"951d39726e355994c70880854cc590e23876c1d7d9c8706107b41c11b45bc1af","abstract_canon_sha256":"cd7ba38da678f48e520fc37c6c47a16e5f861473215d8bdef1055c2860801b06"},"schema_version":"1.0"},"canonical_sha256":"54596ae177f05dfdb1569fcd687d649ea622c8638d80bfa3ac0d6b370c1aed80","source":{"kind":"arxiv","id":"2209.12681","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12681","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12681v2","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12681","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_12","alias_value":"KRMWVYLX6BO7","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_16","alias_value":"KRMWVYLX6BO73MKW","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_8","alias_value":"KRMWVYLX","created_at":"2026-07-05T05:40:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KRMWVYLX6BO73MKWT7GWQ7LET2","target":"record","payload":{"canonical_record":{"source":{"id":"2209.12681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T13:29:22Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"951d39726e355994c70880854cc590e23876c1d7d9c8706107b41c11b45bc1af","abstract_canon_sha256":"cd7ba38da678f48e520fc37c6c47a16e5f861473215d8bdef1055c2860801b06"},"schema_version":"1.0"},"canonical_sha256":"54596ae177f05dfdb1569fcd687d649ea622c8638d80bfa3ac0d6b370c1aed80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:32.342231Z","signature_b64":"jHYMP+xVyp6F9R+ZXOSq2pPecE6XdSpQFiIDjyNMQrHiBDuRFIbMUaNDj2kvu1YtWzGP1Oqe4LTwC1E75D5GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54596ae177f05dfdb1569fcd687d649ea622c8638d80bfa3ac0d6b370c1aed80","last_reissued_at":"2026-07-05T05:40:32.341775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:32.341775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.12681","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":"2026-07-05T05:40:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sxrz/mHoDpTWVMyVQwgMtA6I+ntEc7swXindAimue9MBrTPG5VBLJxYyApNkF4czShmXVTbd2OY/alR//c+SDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:53:09.638453Z"},"content_sha256":"dcb5032195a233e1bff37c2b689b7e4a497a481d03ad61b4e83202c6355280d9","schema_version":"1.0","event_id":"sha256:dcb5032195a233e1bff37c2b689b7e4a497a481d03ad61b4e83202c6355280d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KRMWVYLX6BO73MKWT7GWQ7LET2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Deheng Ye, Jiangxing Wang, Zongqing Lu","submitted_at":"2022-09-26T13:29:22Z","abstract_excerpt":"In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for the partially observable environment. Given the goal of learning local policies that enable decentralized execution, agents are commonly assumed to be independent of each other, even in centralized training. However, such an assumption may prohibit agents from learning the optimal joint policy. To address this problem, we explicitly take the dependency among agents into centralized training. Although this leads to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12681","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/2209.12681/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":"2026-07-05T05:40:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cwE3FhVq6YvnU51LobUvoR5gA+/o98e/gzUeTvMgljbwSowXlrlYRCpwfqYgx6JCOU9nOLw1jxD8wlRP8tEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:53:09.639377Z"},"content_sha256":"2df671ce8feb48c1c1edee84b4cd383eb015971a213c8655eefbc690ce3d7953","schema_version":"1.0","event_id":"sha256:2df671ce8feb48c1c1edee84b4cd383eb015971a213c8655eefbc690ce3d7953"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KRMWVYLX6BO73MKWT7GWQ7LET2/bundle.json","state_url":"https://pith.science/pith/KRMWVYLX6BO73MKWT7GWQ7LET2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KRMWVYLX6BO73MKWT7GWQ7LET2/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":"2026-07-08T07:53:09Z","links":{"resolver":"https://pith.science/pith/KRMWVYLX6BO73MKWT7GWQ7LET2","bundle":"https://pith.science/pith/KRMWVYLX6BO73MKWT7GWQ7LET2/bundle.json","state":"https://pith.science/pith/KRMWVYLX6BO73MKWT7GWQ7LET2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KRMWVYLX6BO73MKWT7GWQ7LET2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KRMWVYLX6BO73MKWT7GWQ7LET2","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":"cd7ba38da678f48e520fc37c6c47a16e5f861473215d8bdef1055c2860801b06","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T13:29:22Z","title_canon_sha256":"951d39726e355994c70880854cc590e23876c1d7d9c8706107b41c11b45bc1af"},"schema_version":"1.0","source":{"id":"2209.12681","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12681","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12681v2","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12681","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_12","alias_value":"KRMWVYLX6BO7","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_16","alias_value":"KRMWVYLX6BO73MKW","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_8","alias_value":"KRMWVYLX","created_at":"2026-07-05T05:40:32Z"}],"graph_snapshots":[{"event_id":"sha256:2df671ce8feb48c1c1edee84b4cd383eb015971a213c8655eefbc690ce3d7953","target":"graph","created_at":"2026-07-05T05:40:32Z","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/2209.12681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for the partially observable environment. Given the goal of learning local policies that enable decentralized execution, agents are commonly assumed to be independent of each other, even in centralized training. However, such an assumption may prohibit agents from learning the optimal joint policy. To address this problem, we explicitly take the dependency among agents into centralized training. Although this leads to the","authors_text":"Deheng Ye, Jiangxing Wang, Zongqing Lu","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T13:29:22Z","title":"More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12681","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:dcb5032195a233e1bff37c2b689b7e4a497a481d03ad61b4e83202c6355280d9","target":"record","created_at":"2026-07-05T05:40:32Z","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":"cd7ba38da678f48e520fc37c6c47a16e5f861473215d8bdef1055c2860801b06","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T13:29:22Z","title_canon_sha256":"951d39726e355994c70880854cc590e23876c1d7d9c8706107b41c11b45bc1af"},"schema_version":"1.0","source":{"id":"2209.12681","kind":"arxiv","version":2}},"canonical_sha256":"54596ae177f05dfdb1569fcd687d649ea622c8638d80bfa3ac0d6b370c1aed80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54596ae177f05dfdb1569fcd687d649ea622c8638d80bfa3ac0d6b370c1aed80","first_computed_at":"2026-07-05T05:40:32.341775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:32.341775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jHYMP+xVyp6F9R+ZXOSq2pPecE6XdSpQFiIDjyNMQrHiBDuRFIbMUaNDj2kvu1YtWzGP1Oqe4LTwC1E75D5GAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:32.342231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.12681","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcb5032195a233e1bff37c2b689b7e4a497a481d03ad61b4e83202c6355280d9","sha256:2df671ce8feb48c1c1edee84b4cd383eb015971a213c8655eefbc690ce3d7953"],"state_sha256":"f4a61709c6344f4ce4292e69b6c89c94c4fcb3db2df379d06035ed355767e3b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T65wJLcj+MGwawaq8THgqUdt17utt8ntS4mWidG1+yRHn6lzDc1u4zHPcTPiuc9UKwUSoME6mQD02rhlU3CuBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:53:09.643197Z","bundle_sha256":"900a297f9551b332379d535a9baa16546b52cf65f6cfcdfddc4f0ab023130d15"}}