{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DCJXHN4FINUYGD3J6DGXEXPF5A","short_pith_number":"pith:DCJXHN4F","canonical_record":{"source":{"id":"2110.04184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"4078a4ae94ccaad02a304372d6ba022c79884852a2d089a9491b0fba0018ac10","abstract_canon_sha256":"b3abd51364e49410a39b71412952744119a13fe229a5d5eeefb9adadc1730a74"},"schema_version":"1.0"},"canonical_sha256":"189373b7854369830f69f0cd725de5e83e34c526554a1a538db3fe4094ebf4e3","source":{"kind":"arxiv","id":"2110.04184","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04184","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04184v2","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04184","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"DCJXHN4FINUY","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"DCJXHN4FINUYGD3J","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"DCJXHN4F","created_at":"2026-07-05T04:10:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DCJXHN4FINUYGD3J6DGXEXPF5A","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"4078a4ae94ccaad02a304372d6ba022c79884852a2d089a9491b0fba0018ac10","abstract_canon_sha256":"b3abd51364e49410a39b71412952744119a13fe229a5d5eeefb9adadc1730a74"},"schema_version":"1.0"},"canonical_sha256":"189373b7854369830f69f0cd725de5e83e34c526554a1a538db3fe4094ebf4e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:23.843547Z","signature_b64":"oW4vnwIXAhDy+m6byGlMIQYiDEeOum0Cg8BJ4OoYf9hfvrieYMBr8A8HbWk+ve45HMtTgdE2dGBmGeNeJ1XsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"189373b7854369830f69f0cd725de5e83e34c526554a1a538db3fe4094ebf4e3","last_reissued_at":"2026-07-05T04:10:23.842988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:23.842988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04184","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t8TrVYvQqVc5eOtjYvm5FH/KFI5IKVU5R7ofxsRILieFGrjKroVn2ZxMREf6StpN9x2yTC/V7ikcI4SivfJxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:51:40.463173Z"},"content_sha256":"c6b87db8a66de7a8585d4894e7fe551996c8f45e3682c928bf0eec36adaf7786","schema_version":"1.0","event_id":"sha256:c6b87db8a66de7a8585d4894e7fe551996c8f45e3682c928bf0eec36adaf7786"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DCJXHN4FINUYGD3J6DGXEXPF5A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Song Mei, Yu Bai, Ziang Song","submitted_at":"2021-10-08T15:06:22Z","abstract_excerpt":"Multi-agent reinforcement learning has made substantial empirical progresses in solving games with a large number of players. However, theoretically, the best known sample complexity for finding a Nash equilibrium in general-sum games scales exponentially in the number of players due to the size of the joint action space, and there is a matching exponential lower bound. This paper investigates what learning goals admit better sample complexities in the setting of $m$-player general-sum Markov games with $H$ steps, $S$ states, and $A_i$ actions per player. First, we design algorithms for learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04184","kind":"arxiv","version":2},"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/2110.04184/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":"2026-07-05T04:10:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yssuu9tqKQgRdB/7yzvmi0+9c6mivNLPptS0YkB4RLiB8nno9cT0DdM9uTjKdb+eCk7mZemGkdeiOg9B0YMpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:51:40.463757Z"},"content_sha256":"3a27f22f06e85be2afa555cff1fcf7dbeb1ab3d63fb781996c17299a0c9c2558","schema_version":"1.0","event_id":"sha256:3a27f22f06e85be2afa555cff1fcf7dbeb1ab3d63fb781996c17299a0c9c2558"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DCJXHN4FINUYGD3J6DGXEXPF5A/bundle.json","state_url":"https://pith.science/pith/DCJXHN4FINUYGD3J6DGXEXPF5A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DCJXHN4FINUYGD3J6DGXEXPF5A/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":"2026-08-12T10:51:40Z","links":{"resolver":"https://pith.science/pith/DCJXHN4FINUYGD3J6DGXEXPF5A","bundle":"https://pith.science/pith/DCJXHN4FINUYGD3J6DGXEXPF5A/bundle.json","state":"https://pith.science/pith/DCJXHN4FINUYGD3J6DGXEXPF5A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DCJXHN4FINUYGD3J6DGXEXPF5A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DCJXHN4FINUYGD3J6DGXEXPF5A","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":"b3abd51364e49410a39b71412952744119a13fe229a5d5eeefb9adadc1730a74","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","title_canon_sha256":"4078a4ae94ccaad02a304372d6ba022c79884852a2d089a9491b0fba0018ac10"},"schema_version":"1.0","source":{"id":"2110.04184","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04184","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04184v2","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04184","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"DCJXHN4FINUY","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"DCJXHN4FINUYGD3J","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"DCJXHN4F","created_at":"2026-07-05T04:10:23Z"}],"graph_snapshots":[{"event_id":"sha256:3a27f22f06e85be2afa555cff1fcf7dbeb1ab3d63fb781996c17299a0c9c2558","target":"graph","created_at":"2026-07-05T04:10:23Z","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/2110.04184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning has made substantial empirical progresses in solving games with a large number of players. However, theoretically, the best known sample complexity for finding a Nash equilibrium in general-sum games scales exponentially in the number of players due to the size of the joint action space, and there is a matching exponential lower bound. This paper investigates what learning goals admit better sample complexities in the setting of $m$-player general-sum Markov games with $H$ steps, $S$ states, and $A_i$ actions per player. First, we design algorithms for learni","authors_text":"Song Mei, Yu Bai, Ziang Song","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04184","kind":"arxiv","version":2},"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:c6b87db8a66de7a8585d4894e7fe551996c8f45e3682c928bf0eec36adaf7786","target":"record","created_at":"2026-07-05T04:10:23Z","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":"b3abd51364e49410a39b71412952744119a13fe229a5d5eeefb9adadc1730a74","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","title_canon_sha256":"4078a4ae94ccaad02a304372d6ba022c79884852a2d089a9491b0fba0018ac10"},"schema_version":"1.0","source":{"id":"2110.04184","kind":"arxiv","version":2}},"canonical_sha256":"189373b7854369830f69f0cd725de5e83e34c526554a1a538db3fe4094ebf4e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"189373b7854369830f69f0cd725de5e83e34c526554a1a538db3fe4094ebf4e3","first_computed_at":"2026-07-05T04:10:23.842988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:23.842988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oW4vnwIXAhDy+m6byGlMIQYiDEeOum0Cg8BJ4OoYf9hfvrieYMBr8A8HbWk+ve45HMtTgdE2dGBmGeNeJ1XsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:23.843547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04184","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6b87db8a66de7a8585d4894e7fe551996c8f45e3682c928bf0eec36adaf7786","sha256:3a27f22f06e85be2afa555cff1fcf7dbeb1ab3d63fb781996c17299a0c9c2558"],"state_sha256":"23c32356526e7b900dbf9dd742d939065db06ad424096ba2ba525df3a978cd6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NINm3Xrbiw1Np6ztBkvEOIdyjv8HD8vkYomMqlCwbvzXFbdgzFeD0bE+0OrI3ps56Wss1YDKCvHb10TsdoQrDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T10:51:40.469860Z","bundle_sha256":"a739eeb0cd36fe7a5bd9316537c3877fc711a957794ac9665019c54b3c61de96"}}