{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:URITOVHWR3CZPJCJYYZZUY43V5","short_pith_number":"pith:URITOVHW","canonical_record":{"source":{"id":"2505.24113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-05-30T01:23:14Z","cross_cats_sorted":[],"title_canon_sha256":"68e677aaf87a7f2af966c3b4699235de23cc48dff7412ac80f950f8467dc926e","abstract_canon_sha256":"f604d9e18bb144859c10b9d110daf2c41c2fb3a705ddee7075c69d340e841213"},"schema_version":"1.0"},"canonical_sha256":"a4513754f68ec597a449c6339a639baf7abd8f9c37621f02874eab53e43d3ce9","source":{"kind":"arxiv","id":"2505.24113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24113","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24113v1","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24113","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"pith_short_12","alias_value":"URITOVHWR3CZ","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"pith_short_16","alias_value":"URITOVHWR3CZPJCJ","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"pith_short_8","alias_value":"URITOVHW","created_at":"2026-07-05T11:12:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:URITOVHWR3CZPJCJYYZZUY43V5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-05-30T01:23:14Z","cross_cats_sorted":[],"title_canon_sha256":"68e677aaf87a7f2af966c3b4699235de23cc48dff7412ac80f950f8467dc926e","abstract_canon_sha256":"f604d9e18bb144859c10b9d110daf2c41c2fb3a705ddee7075c69d340e841213"},"schema_version":"1.0"},"canonical_sha256":"a4513754f68ec597a449c6339a639baf7abd8f9c37621f02874eab53e43d3ce9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:42.138346Z","signature_b64":"05bWkIcSn0Dbghzirifc1qT2X9codJsTNPLYzCehQIUzJmGKT7f+Ae5FBgL7BmDDHmAHlev2ZM6GWTmuB621AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4513754f68ec597a449c6339a639baf7abd8f9c37621f02874eab53e43d3ce9","last_reissued_at":"2026-07-05T11:12:42.137782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:42.137782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24113","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E5zman2UQ3UHORqrMjXqK6TUHcaDwpfeMG7reTmfrLUwrQuxlfLwHmCV3YWImrWnrs7bgtBZiX8w1OShP9B8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:58:59.821778Z"},"content_sha256":"02e41d94dc2f2b73d71946bd887faa18c62e8880e17ffa487bb7ab767d8f0591","schema_version":"1.0","event_id":"sha256:02e41d94dc2f2b73d71946bd887faa18c62e8880e17ffa487bb7ab767d8f0591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:URITOVHWR3CZPJCJYYZZUY43V5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Pengcheng Dai, Wei Ren, Wenwu Yu, Yuanqiu Mo","submitted_at":"2025-05-30T01:23:14Z","abstract_excerpt":"This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer from poor expression due to linear function approximation, we propose a distributed neural policy gradient algorithm that features two innovatively designed neural networks, specifically for the approximate Q-functions and policy functions of agents. This distributed neural policy gradient algorithm consists of two key components: the distributed critic step an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24113","kind":"arxiv","version":1},"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/2505.24113/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":"2026-07-05T11:12:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mb9PpnJtI+mV03wM+l3oFNN3k+Ispafh6U/bNXe2Gt3LDowI+7RaRRmgDjSU/fksLpOJXqvsLE3VYqiM6dCXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:58:59.822254Z"},"content_sha256":"4f9fa3ace4d60ea6ed9b298fbc77705dca481c1429a8f106656909bb5b0b3271","schema_version":"1.0","event_id":"sha256:4f9fa3ace4d60ea6ed9b298fbc77705dca481c1429a8f106656909bb5b0b3271"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URITOVHWR3CZPJCJYYZZUY43V5/bundle.json","state_url":"https://pith.science/pith/URITOVHWR3CZPJCJYYZZUY43V5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URITOVHWR3CZPJCJYYZZUY43V5/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":"2026-08-08T05:58:59Z","links":{"resolver":"https://pith.science/pith/URITOVHWR3CZPJCJYYZZUY43V5","bundle":"https://pith.science/pith/URITOVHWR3CZPJCJYYZZUY43V5/bundle.json","state":"https://pith.science/pith/URITOVHWR3CZPJCJYYZZUY43V5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URITOVHWR3CZPJCJYYZZUY43V5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:URITOVHWR3CZPJCJYYZZUY43V5","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":"f604d9e18bb144859c10b9d110daf2c41c2fb3a705ddee7075c69d340e841213","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-05-30T01:23:14Z","title_canon_sha256":"68e677aaf87a7f2af966c3b4699235de23cc48dff7412ac80f950f8467dc926e"},"schema_version":"1.0","source":{"id":"2505.24113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24113","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24113v1","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24113","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"pith_short_12","alias_value":"URITOVHWR3CZ","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"pith_short_16","alias_value":"URITOVHWR3CZPJCJ","created_at":"2026-07-05T11:12:42Z"},{"alias_kind":"pith_short_8","alias_value":"URITOVHW","created_at":"2026-07-05T11:12:42Z"}],"graph_snapshots":[{"event_id":"sha256:4f9fa3ace4d60ea6ed9b298fbc77705dca481c1429a8f106656909bb5b0b3271","target":"graph","created_at":"2026-07-05T11:12:42Z","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/2505.24113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer from poor expression due to linear function approximation, we propose a distributed neural policy gradient algorithm that features two innovatively designed neural networks, specifically for the approximate Q-functions and policy functions of agents. This distributed neural policy gradient algorithm consists of two key components: the distributed critic step an","authors_text":"Pengcheng Dai, Wei Ren, Wenwu Yu, Yuanqiu Mo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-05-30T01:23:14Z","title":"Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24113","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":"sha256:02e41d94dc2f2b73d71946bd887faa18c62e8880e17ffa487bb7ab767d8f0591","target":"record","created_at":"2026-07-05T11:12:42Z","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":"f604d9e18bb144859c10b9d110daf2c41c2fb3a705ddee7075c69d340e841213","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-05-30T01:23:14Z","title_canon_sha256":"68e677aaf87a7f2af966c3b4699235de23cc48dff7412ac80f950f8467dc926e"},"schema_version":"1.0","source":{"id":"2505.24113","kind":"arxiv","version":1}},"canonical_sha256":"a4513754f68ec597a449c6339a639baf7abd8f9c37621f02874eab53e43d3ce9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4513754f68ec597a449c6339a639baf7abd8f9c37621f02874eab53e43d3ce9","first_computed_at":"2026-07-05T11:12:42.137782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:42.137782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"05bWkIcSn0Dbghzirifc1qT2X9codJsTNPLYzCehQIUzJmGKT7f+Ae5FBgL7BmDDHmAHlev2ZM6GWTmuB621AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:42.138346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02e41d94dc2f2b73d71946bd887faa18c62e8880e17ffa487bb7ab767d8f0591","sha256:4f9fa3ace4d60ea6ed9b298fbc77705dca481c1429a8f106656909bb5b0b3271"],"state_sha256":"87d7b8aad7091397b64d5e5653d1d479043ffb4f72f293ea9a34a277cdae4116"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R3rqNIWJuwboVuXbgmqvmSa5MCq/gDVmfAMIGt/+DitQhlbSVEXDK04f2X22M/JZM7B6EXuEBMF8/Hc4rcDZCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:58:59.825430Z","bundle_sha256":"bb81c4f8a261c8101f8073295bca4ad78595cd03eb75d31a08a0c4f8f1060d9e"}}