{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:T4NERQ5BVZCDKRQBJNHHI7PWWJ","short_pith_number":"pith:T4NERQ5B","canonical_record":{"source":{"id":"2103.04972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T18:51:00Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"01ee570f03a4747d8b78c5c57e24c590bc4d31ab075cc2e81e3d9f9c27af45a6","abstract_canon_sha256":"6699926beddd5c07a65d2159eef03bb38eef64ef15fc6e5dd5d30ab6749dc87a"},"schema_version":"1.0"},"canonical_sha256":"9f1a48c3a1ae443546014b4e747df6b273a0cf3d79fdb9b4c5164edef120801f","source":{"kind":"arxiv","id":"2103.04972","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04972","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04972v1","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04972","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"pith_short_12","alias_value":"T4NERQ5BVZCD","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"T4NERQ5BVZCDKRQB","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"T4NERQ5B","created_at":"2026-07-05T02:26:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:T4NERQ5BVZCDKRQBJNHHI7PWWJ","target":"record","payload":{"canonical_record":{"source":{"id":"2103.04972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T18:51:00Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"01ee570f03a4747d8b78c5c57e24c590bc4d31ab075cc2e81e3d9f9c27af45a6","abstract_canon_sha256":"6699926beddd5c07a65d2159eef03bb38eef64ef15fc6e5dd5d30ab6749dc87a"},"schema_version":"1.0"},"canonical_sha256":"9f1a48c3a1ae443546014b4e747df6b273a0cf3d79fdb9b4c5164edef120801f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:56.453083Z","signature_b64":"RxyoifYCCHkpN0QAkvsjlIus8u8o3rN2E49kj+RlDAdHB3+SdzHtyn5/EaND/S41YjRpRMVyCq7h7NXPTQIyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f1a48c3a1ae443546014b4e747df6b273a0cf3d79fdb9b4c5164edef120801f","last_reissued_at":"2026-07-05T02:26:56.452710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:56.452710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.04972","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":"2026-07-05T02:26:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1p1Y7UzcfCLydMpGijTbgzEycngIeFOkKFwke/iTfDRcSWvzyUfUx+hkXsu5RNq+OQ6t7vhUAyk7ek0nFrI7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:11:17.608582Z"},"content_sha256":"0f24e0353f5a41f634c3ad29100f0234b7311abae8256b5692813c119821a3a5","schema_version":"1.0","event_id":"sha256:0f24e0353f5a41f634c3ad29100f0234b7311abae8256b5692813c119821a3a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:T4NERQ5BVZCDKRQBJNHHI7PWWJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhimanyu Dubey, Alex Pentland","submitted_at":"2021-03-08T18:51:00Z","abstract_excerpt":"Reinforcement learning in cooperative multi-agent settings has recently advanced significantly in its scope, with applications in cooperative estimation for advertising, dynamic treatment regimes, distributed control, and federated learning. In this paper, we discuss the problem of cooperative multi-agent RL with function approximation, where a group of agents communicates with each other to jointly solve an episodic MDP. We demonstrate that via careful message-passing and cooperative value iteration, it is possible to achieve near-optimal no-regret learning even with a fixed constant communic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04972","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/2103.04972/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":"2026-07-05T02:26:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4xQ1UVAIO7YFY+hnSRoWTKGsS61MbxM0oYXscy6A54BKEx8qEMI3q4DYFTmNL9uAvbfx2MosFzmJFSmh48rBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:11:17.609096Z"},"content_sha256":"21ec99801e0a516f4ed1cc4194feb67128e89ab1e4be345cc53f051e6503568b","schema_version":"1.0","event_id":"sha256:21ec99801e0a516f4ed1cc4194feb67128e89ab1e4be345cc53f051e6503568b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4NERQ5BVZCDKRQBJNHHI7PWWJ/bundle.json","state_url":"https://pith.science/pith/T4NERQ5BVZCDKRQBJNHHI7PWWJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4NERQ5BVZCDKRQBJNHHI7PWWJ/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":"2026-08-09T06:11:17Z","links":{"resolver":"https://pith.science/pith/T4NERQ5BVZCDKRQBJNHHI7PWWJ","bundle":"https://pith.science/pith/T4NERQ5BVZCDKRQBJNHHI7PWWJ/bundle.json","state":"https://pith.science/pith/T4NERQ5BVZCDKRQBJNHHI7PWWJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4NERQ5BVZCDKRQBJNHHI7PWWJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:T4NERQ5BVZCDKRQBJNHHI7PWWJ","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":"6699926beddd5c07a65d2159eef03bb38eef64ef15fc6e5dd5d30ab6749dc87a","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T18:51:00Z","title_canon_sha256":"01ee570f03a4747d8b78c5c57e24c590bc4d31ab075cc2e81e3d9f9c27af45a6"},"schema_version":"1.0","source":{"id":"2103.04972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04972","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04972v1","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04972","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"pith_short_12","alias_value":"T4NERQ5BVZCD","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"T4NERQ5BVZCDKRQB","created_at":"2026-07-05T02:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"T4NERQ5B","created_at":"2026-07-05T02:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:21ec99801e0a516f4ed1cc4194feb67128e89ab1e4be345cc53f051e6503568b","target":"graph","created_at":"2026-07-05T02:26:56Z","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/2103.04972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning in cooperative multi-agent settings has recently advanced significantly in its scope, with applications in cooperative estimation for advertising, dynamic treatment regimes, distributed control, and federated learning. In this paper, we discuss the problem of cooperative multi-agent RL with function approximation, where a group of agents communicates with each other to jointly solve an episodic MDP. We demonstrate that via careful message-passing and cooperative value iteration, it is possible to achieve near-optimal no-regret learning even with a fixed constant communic","authors_text":"Abhimanyu Dubey, Alex Pentland","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T18:51:00Z","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04972","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":"sha256:0f24e0353f5a41f634c3ad29100f0234b7311abae8256b5692813c119821a3a5","target":"record","created_at":"2026-07-05T02:26:56Z","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":"6699926beddd5c07a65d2159eef03bb38eef64ef15fc6e5dd5d30ab6749dc87a","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T18:51:00Z","title_canon_sha256":"01ee570f03a4747d8b78c5c57e24c590bc4d31ab075cc2e81e3d9f9c27af45a6"},"schema_version":"1.0","source":{"id":"2103.04972","kind":"arxiv","version":1}},"canonical_sha256":"9f1a48c3a1ae443546014b4e747df6b273a0cf3d79fdb9b4c5164edef120801f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f1a48c3a1ae443546014b4e747df6b273a0cf3d79fdb9b4c5164edef120801f","first_computed_at":"2026-07-05T02:26:56.452710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:56.452710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RxyoifYCCHkpN0QAkvsjlIus8u8o3rN2E49kj+RlDAdHB3+SdzHtyn5/EaND/S41YjRpRMVyCq7h7NXPTQIyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:56.453083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.04972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f24e0353f5a41f634c3ad29100f0234b7311abae8256b5692813c119821a3a5","sha256:21ec99801e0a516f4ed1cc4194feb67128e89ab1e4be345cc53f051e6503568b"],"state_sha256":"bd6f989769f2f9721dbfb01b7dfe5995125b48414dadac95b3227be1b350cedb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qg3SMypFBQOzEIojEm9O1UnsoDU1NKriPlZWLvuUBJ3iFc9VG3odOwDXkkCUSku0AHAi6tQnODbTMUo6w0LVCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:11:17.612896Z","bundle_sha256":"c40564cb39b278b0de3f2d96edb1a8fdf9c0c6a9ae9bae482c9a9b73047f98ad"}}