{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NPZYGKO2XDPT5FVPQ3WN3MU3JH","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":"304b22665ec25440f3539095375c5cb70c1d98ee0f7d611c940d3b78d31e0e8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T10:04:15Z","title_canon_sha256":"55cf320bd1d7ab32cd0d4587729db756e71415fc1bc9c1d12b710772f0bb5ca3"},"schema_version":"1.0","source":{"id":"2606.30072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30072","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30072v1","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30072","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"NPZYGKO2XDPT","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"NPZYGKO2XDPT5FVP","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"NPZYGKO2","created_at":"2026-06-30T02:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:335f2068c549ad8247894ce5d60e222c5dc45a474440936300b0a05bc2f04482","target":"graph","created_at":"2026-06-30T02:17:48Z","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/2606.30072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training with Decentralized Execution (CTDE) paradigm, policy gradients have remained difficult to compute directly. Prior methods largely follow two approaches: independent factorized updates with centralized critics, which lack general joint-improvement guarantees without value decomposition assumptions, or alternating best-response updates, which can converge to suboptimal Nash Equilibria. In this paper, we show the joint policy gradient admits an exa","authors_text":"Daiki E. Matsunaga, Jongmin Lee, Junho Na, Kee-Eung Kim, Pascal Poupart, Scott Sanner, Tri Wahyu Guntara","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T10:04:15Z","title":"ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30072","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:f5b55d79c523823cff97371acdeac1e1099be1962fee43b250b13d1701624783","target":"record","created_at":"2026-06-30T02:17:48Z","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":"304b22665ec25440f3539095375c5cb70c1d98ee0f7d611c940d3b78d31e0e8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T10:04:15Z","title_canon_sha256":"55cf320bd1d7ab32cd0d4587729db756e71415fc1bc9c1d12b710772f0bb5ca3"},"schema_version":"1.0","source":{"id":"2606.30072","kind":"arxiv","version":1}},"canonical_sha256":"6bf38329dab8df3e96af86ecddb29b49d3ea21c71f4dd9119716ff385697284c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bf38329dab8df3e96af86ecddb29b49d3ea21c71f4dd9119716ff385697284c","first_computed_at":"2026-06-30T02:17:48.351990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:48.351990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rTCNkqY06EPyfPcgCJAIAt5XFw+PCIUT7M7oz7KUO7oD59EdQfa5TSSOP1im2OrnefY66L0LFcp/wp/qOIizDQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:48.352525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5b55d79c523823cff97371acdeac1e1099be1962fee43b250b13d1701624783","sha256:335f2068c549ad8247894ce5d60e222c5dc45a474440936300b0a05bc2f04482"],"state_sha256":"d26fe4651b6d55f97a894a0cb8c3737ee4b6bf9ecbbe26066687b66eb6a07224"}