{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NCHXKQIPBKKQ2MZVIMZFCJ3HLV","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":"c8fe6206809e9d0592543acff461071f6376d3fa742d3f105575e1d51ebd96e5","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T04:52:22Z","title_canon_sha256":"ede4bd9ed23cdc642146b472fa104a9c54b8529a584bd2ea310cf860f85f3392"},"schema_version":"1.0","source":{"id":"2604.13472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.13472","created_at":"2026-07-28T02:23:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.13472v2","created_at":"2026-07-28T02:23:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13472","created_at":"2026-07-28T02:23:30Z"},{"alias_kind":"pith_short_12","alias_value":"NCHXKQIPBKKQ","created_at":"2026-07-28T02:23:30Z"},{"alias_kind":"pith_short_16","alias_value":"NCHXKQIPBKKQ2MZV","created_at":"2026-07-28T02:23:30Z"},{"alias_kind":"pith_short_8","alias_value":"NCHXKQIP","created_at":"2026-07-28T02:23:30Z"}],"graph_snapshots":[{"event_id":"sha256:4691942b0bbe4908445e2cbb1fb4774d9e301376c867c8ff22c1b78180c58000","target":"graph","created_at":"2026-07-28T02:23:30Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CMAT bridges cooperative MARL to a hierarchical SARL formulation by autoregressively generating a high-level consensus vector that conditions simultaneous, order-independent action generation, allowing optimization with single-agent PPO while achieving superior performance on StarCraft II, Multi-Agent MuJoCo, and Google Research Football benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The latent consensus vector produced by the transformer decoder actually captures sufficient coordination information to replace explicit agent-to-agent communication or centralized critics without loss of expressivity; this is assumed rather than proven and is only supported by empirical wins on the chosen benchmarks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CMAT uses a transformer decoder to produce a high-level consensus vector in latent space, enabling simultaneous order-independent actions by all agents and optimization via single-agent PPO, with superior results on StarCraft II, Multi-Agent MuJoCo, and Google Research Football."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CMAT reformulates cooperative MARL as hierarchical SARL by generating a latent consensus vector that conditions simultaneous order-independent actions."}],"snapshot_sha256":"32da2ca73a9024407380f65588279b58e41459d34d6de064af125d9e6a8d1187"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.13472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple interacting agents. However, such decomposition often introduces additional challenges, including non-stationarity, unstable training, weak coordination, and limited theoretical guarantees. In this paper, we propose the Consensus Multi-Agent Transformer (CMAT), a centralized framework that bridges cooperative MARL to a hierarchical single-agent reinforcement learning (SARL) formulation. CMAT treats all agents as a u","authors_text":"Jing Gao, Sen Li, Zijian Zhao","cross_cats":["cs.AI","cs.MA"],"headline":"CMAT reformulates cooperative MARL as hierarchical SARL by generating a latent consensus vector that conditions simultaneous order-independent actions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T04:52:22Z","title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.13472","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T13:37:34.576192Z","id":"8b1eb208-6b17-4a2e-815a-e7433c534e05","model_set":{"reader":"grok-4.3"},"one_line_summary":"CMAT uses a transformer decoder to produce a high-level consensus vector in latent space, enabling simultaneous order-independent actions by all agents and optimization via single-agent PPO, with superior results on StarCraft II, Multi-Agent MuJoCo, and Google Research Football.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CMAT reformulates cooperative MARL as hierarchical SARL by generating a latent consensus vector that conditions simultaneous order-independent actions.","strongest_claim":"CMAT bridges cooperative MARL to a hierarchical SARL formulation by autoregressively generating a high-level consensus vector that conditions simultaneous, order-independent action generation, allowing optimization with single-agent PPO while achieving superior performance on StarCraft II, Multi-Agent MuJoCo, and Google Research Football benchmarks.","weakest_assumption":"The latent consensus vector produced by the transformer decoder actually captures sufficient coordination information to replace explicit agent-to-agent communication or centralized critics without loss of expressivity; this is assumed rather than proven and is only supported by empirical wins on the chosen benchmarks."}},"verdict_id":"8b1eb208-6b17-4a2e-815a-e7433c534e05"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f90d08f8a99b23934e7c643344efdb149076dbd1ebc5a25206079e6309fcb737","target":"record","created_at":"2026-07-28T02:23:30Z","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":"c8fe6206809e9d0592543acff461071f6376d3fa742d3f105575e1d51ebd96e5","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T04:52:22Z","title_canon_sha256":"ede4bd9ed23cdc642146b472fa104a9c54b8529a584bd2ea310cf860f85f3392"},"schema_version":"1.0","source":{"id":"2604.13472","kind":"arxiv","version":2}},"canonical_sha256":"688f75410f0a950d333543325127675d4f1d326dc435782cec945c873fdd2ab7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"688f75410f0a950d333543325127675d4f1d326dc435782cec945c873fdd2ab7","first_computed_at":"2026-07-28T02:23:30.267577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:23:30.267577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EJ2T/NoxThXXZaLUpbqCzqCx2EgcWNeBkVEvvUvtRYfwRdVtaYb0W1FnjNGv2b2JdPZ7LgrCSaJsQgmwEJ9XBw==","signature_status":"signed_v1","signed_at":"2026-07-28T02:23:30.268544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.13472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f90d08f8a99b23934e7c643344efdb149076dbd1ebc5a25206079e6309fcb737","sha256:4691942b0bbe4908445e2cbb1fb4774d9e301376c867c8ff22c1b78180c58000"],"state_sha256":"6d2b095e83fd5f2fa1123baa5867a29f3299d6c32a08219e80b45bb005c50d3d"}