{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HFN4DNYS4Q2AKQMW5XFUIMPL27","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":"6cd5370911563d6dc078bf4d4e3c96ae19fab0acfcba50031fd509450b966db3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-07-20T22:41:43Z","title_canon_sha256":"b3f3ff74ba54d7c0ac9b9516d7d1bec35a5770c984b87274ffaf37fb1136c7f7"},"schema_version":"1.0","source":{"id":"2607.18554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18554","created_at":"2026-07-22T00:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18554v1","created_at":"2026-07-22T00:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18554","created_at":"2026-07-22T00:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"HFN4DNYS4Q2A","created_at":"2026-07-22T00:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"HFN4DNYS4Q2AKQMW","created_at":"2026-07-22T00:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"HFN4DNYS","created_at":"2026-07-22T00:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:14fa14aad09ba28c867ae8301d86d2dbf0fa9c7f0459415f4847e23be84f1454","target":"graph","created_at":"2026-07-22T00:22:54Z","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/2607.18554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We develop the Continuous Distributed Coupled Policy Gradient (CDCPG) algorithm for cooperative reinforcement learning in networked Markov decision processes with continuous state and action spaces. Each agent maintains a local actor over a bounded graph neighborhood, and a localized least-squares temporal-difference critic evaluates a truncated action-value function through a spectral random-feature representation of the local transition kernel. The analysis makes four contributions. First, the truncated action-value function is constructed as a conditional expectation over the neighborhood, ","authors_text":"Dongming Wang, Pengcheng Dai, Wei Ren, Wenwu Yu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-07-20T22:41:43Z","title":"Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18554","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":"sha256:1f827f2688f98389d04c5470a2b257bdf31d7ad07c81076508c90e2de9c34aff","target":"record","created_at":"2026-07-22T00:22:54Z","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":"6cd5370911563d6dc078bf4d4e3c96ae19fab0acfcba50031fd509450b966db3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-07-20T22:41:43Z","title_canon_sha256":"b3f3ff74ba54d7c0ac9b9516d7d1bec35a5770c984b87274ffaf37fb1136c7f7"},"schema_version":"1.0","source":{"id":"2607.18554","kind":"arxiv","version":1}},"canonical_sha256":"395bc1b712e434054196edcb4431ebd7c8d5b50cbb4b4eda1675b54e5a21c52b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"395bc1b712e434054196edcb4431ebd7c8d5b50cbb4b4eda1675b54e5a21c52b","first_computed_at":"2026-07-22T00:22:54.090390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:54.090390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rycOdHNq45kGPZ2/bKFT6V9LKe6eWLBIlx3jXCIkpdqsuuJrlO6hLg04dF/ByinR4KmH6AMRe4TIP5bklmfxBg==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:54.091093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f827f2688f98389d04c5470a2b257bdf31d7ad07c81076508c90e2de9c34aff","sha256:14fa14aad09ba28c867ae8301d86d2dbf0fa9c7f0459415f4847e23be84f1454"],"state_sha256":"dc9792d95c5d73005933a30cb3f6c0da1193cf415aaf3e12cf40d48288a64f40"}