{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3ZI67ZN37PGRQXARTVBKY643IZ","short_pith_number":"pith:3ZI67ZN3","canonical_record":{"source":{"id":"2110.14555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T16:25:55Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"e368946e13b253a6743995839176f7271b20b914c80f369dde790f8d4c0df6ed","abstract_canon_sha256":"94b50860c54d8e15e75de442125b768d71376dcac58123d486b71f5034d66a32"},"schema_version":"1.0"},"canonical_sha256":"de51efe5bbfbcd185c119d42ac7b9b466550ee416328eda39c6e5a6e0eadd28a","source":{"kind":"arxiv","id":"2110.14555","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14555","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14555v1","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14555","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"pith_short_12","alias_value":"3ZI67ZN37PGR","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"pith_short_16","alias_value":"3ZI67ZN37PGRQXAR","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"pith_short_8","alias_value":"3ZI67ZN3","created_at":"2026-07-05T03:26:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3ZI67ZN37PGRQXARTVBKY643IZ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.14555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T16:25:55Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"e368946e13b253a6743995839176f7271b20b914c80f369dde790f8d4c0df6ed","abstract_canon_sha256":"94b50860c54d8e15e75de442125b768d71376dcac58123d486b71f5034d66a32"},"schema_version":"1.0"},"canonical_sha256":"de51efe5bbfbcd185c119d42ac7b9b466550ee416328eda39c6e5a6e0eadd28a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:29.135917Z","signature_b64":"f6p0G2yLjJKYdVRNa8T5hQL3ZTgKPWBaOrPyH7kdZaeqEpU2eQxcEpA3jw1SUHAo5mpgf6uj8nToCPlo15CVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de51efe5bbfbcd185c119d42ac7b9b466550ee416328eda39c6e5a6e0eadd28a","last_reissued_at":"2026-07-05T03:26:29.135399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:29.135399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.14555","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":"2026-07-05T03:26:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dIW7nd9q8jy6vmvlh75hpSQQepI4HUAewfG2yjmuiyLCDWv67zOcoy416s8nT8b7RQgHCeo77ZxEEyspS4uSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:21:52.731392Z"},"content_sha256":"21d5500a669b8e0feb8d2a97f7f6154eed693fb7d8bbcd341b139abe177a190d","schema_version":"1.0","event_id":"sha256:21d5500a669b8e0feb8d2a97f7f6154eed693fb7d8bbcd341b139abe177a190d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3ZI67ZN37PGRQXARTVBKY643IZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Qinghua Liu, Tiancheng Yu, Yuanhao Wang","submitted_at":"2021-10-27T16:25:55Z","abstract_excerpt":"A major challenge of multiagent reinforcement learning (MARL) is the curse of multiagents, where the size of the joint action space scales exponentially with the number of agents. This remains to be a bottleneck for designing efficient MARL algorithms even in a basic scenario with finitely many states and actions. This paper resolves this challenge for the model of episodic Markov games. We design a new class of fully decentralized algorithms -- V-learning, which provably learns Nash equilibria (in the two-player zero-sum setting), correlated equilibria and coarse correlated equilibria (in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14555","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/2110.14555/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":"2026-07-05T03:26:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wu1x1Yx/+HC9y4lK5WB8y7OkT/p9dDQkxqg2cPIhDwcXGWdwtB/in26b5bSKnokQDPc86kRjLZcCK0myAsTLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:21:52.731924Z"},"content_sha256":"b311bb8b7ca6ad30e813f354e5dbb1473fb993c3aa58342c45cfec686d0e2962","schema_version":"1.0","event_id":"sha256:b311bb8b7ca6ad30e813f354e5dbb1473fb993c3aa58342c45cfec686d0e2962"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZI67ZN37PGRQXARTVBKY643IZ/bundle.json","state_url":"https://pith.science/pith/3ZI67ZN37PGRQXARTVBKY643IZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZI67ZN37PGRQXARTVBKY643IZ/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":"2026-08-06T08:21:52Z","links":{"resolver":"https://pith.science/pith/3ZI67ZN37PGRQXARTVBKY643IZ","bundle":"https://pith.science/pith/3ZI67ZN37PGRQXARTVBKY643IZ/bundle.json","state":"https://pith.science/pith/3ZI67ZN37PGRQXARTVBKY643IZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZI67ZN37PGRQXARTVBKY643IZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3ZI67ZN37PGRQXARTVBKY643IZ","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":"94b50860c54d8e15e75de442125b768d71376dcac58123d486b71f5034d66a32","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T16:25:55Z","title_canon_sha256":"e368946e13b253a6743995839176f7271b20b914c80f369dde790f8d4c0df6ed"},"schema_version":"1.0","source":{"id":"2110.14555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14555","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14555v1","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14555","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"pith_short_12","alias_value":"3ZI67ZN37PGR","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"pith_short_16","alias_value":"3ZI67ZN37PGRQXAR","created_at":"2026-07-05T03:26:29Z"},{"alias_kind":"pith_short_8","alias_value":"3ZI67ZN3","created_at":"2026-07-05T03:26:29Z"}],"graph_snapshots":[{"event_id":"sha256:b311bb8b7ca6ad30e813f354e5dbb1473fb993c3aa58342c45cfec686d0e2962","target":"graph","created_at":"2026-07-05T03:26:29Z","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/2110.14555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A major challenge of multiagent reinforcement learning (MARL) is the curse of multiagents, where the size of the joint action space scales exponentially with the number of agents. This remains to be a bottleneck for designing efficient MARL algorithms even in a basic scenario with finitely many states and actions. This paper resolves this challenge for the model of episodic Markov games. We design a new class of fully decentralized algorithms -- V-learning, which provably learns Nash equilibria (in the two-player zero-sum setting), correlated equilibria and coarse correlated equilibria (in the","authors_text":"Chi Jin, Qinghua Liu, Tiancheng Yu, Yuanhao Wang","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T16:25:55Z","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14555","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":"sha256:21d5500a669b8e0feb8d2a97f7f6154eed693fb7d8bbcd341b139abe177a190d","target":"record","created_at":"2026-07-05T03:26:29Z","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":"94b50860c54d8e15e75de442125b768d71376dcac58123d486b71f5034d66a32","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T16:25:55Z","title_canon_sha256":"e368946e13b253a6743995839176f7271b20b914c80f369dde790f8d4c0df6ed"},"schema_version":"1.0","source":{"id":"2110.14555","kind":"arxiv","version":1}},"canonical_sha256":"de51efe5bbfbcd185c119d42ac7b9b466550ee416328eda39c6e5a6e0eadd28a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de51efe5bbfbcd185c119d42ac7b9b466550ee416328eda39c6e5a6e0eadd28a","first_computed_at":"2026-07-05T03:26:29.135399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:29.135399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f6p0G2yLjJKYdVRNa8T5hQL3ZTgKPWBaOrPyH7kdZaeqEpU2eQxcEpA3jw1SUHAo5mpgf6uj8nToCPlo15CVCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:29.135917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21d5500a669b8e0feb8d2a97f7f6154eed693fb7d8bbcd341b139abe177a190d","sha256:b311bb8b7ca6ad30e813f354e5dbb1473fb993c3aa58342c45cfec686d0e2962"],"state_sha256":"23cb4a97ef0847d809db6851e05f890eca514b5603a10c79e4e3613cd7807202"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uWowRw4SQZzMBguslc1CGFzCQKwHAApwUgFRA28Kyo296+AzY83zi6zwuDg5YHwq1NMI4QBSQOplNJJvAxEFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:21:52.735838Z","bundle_sha256":"14b5e2c6517ffca13059f4e21c8c6f4b37deeb8d9d326558822da062e4aae69b"}}