{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3YZ7BIWR24AAXSEYMLZBG6D6GQ","short_pith_number":"pith:3YZ7BIWR","canonical_record":{"source":{"id":"2206.00159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T00:18:15Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"a457b0167b9a77c41cfcd75753cce52a55fd341495458ffe99cddb5bba9b8911","abstract_canon_sha256":"259f38958589775267359125e66941a407050dc390d585580c972ed912effed0"},"schema_version":"1.0"},"canonical_sha256":"de33f0a2d1d7000bc89862f213787e340f8daef674fbdc709222a1bbbac70f20","source":{"kind":"arxiv","id":"2206.00159","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00159","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00159v2","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00159","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"3YZ7BIWR24AA","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"3YZ7BIWR24AAXSEY","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"3YZ7BIWR","created_at":"2026-07-05T05:06:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3YZ7BIWR24AAXSEYMLZBG6D6GQ","target":"record","payload":{"canonical_record":{"source":{"id":"2206.00159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T00:18:15Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"a457b0167b9a77c41cfcd75753cce52a55fd341495458ffe99cddb5bba9b8911","abstract_canon_sha256":"259f38958589775267359125e66941a407050dc390d585580c972ed912effed0"},"schema_version":"1.0"},"canonical_sha256":"de33f0a2d1d7000bc89862f213787e340f8daef674fbdc709222a1bbbac70f20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:31.985294Z","signature_b64":"xdWwD4YC2rECoc9P29T8FFWsQS7bwcqQxn12QIOInrLcmj/Q7gcOugLMuWlXzZ2u3axq+zvKQXJ6TY2UxEXVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de33f0a2d1d7000bc89862f213787e340f8daef674fbdc709222a1bbbac70f20","last_reissued_at":"2026-07-05T05:06:31.984837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:31.984837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.00159","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":"2026-07-05T05:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ajUgu79Ry6FEWCs2taMelMMX5Kyi6hJT9NKp9NL2zr0mZRv+LtgLTOyYePRZxfNLG6oSKaJitIXr3XcVSblvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:52:21.030583Z"},"content_sha256":"371016d0de32875234c7c02ee19110f99183d34c5f124b15f28e5322fbafdc46","schema_version":"1.0","event_id":"sha256:371016d0de32875234c7c02ee19110f99183d34c5f124b15f28e5322fbafdc46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3YZ7BIWR24AAXSEYMLZBG6D6GQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Qiwen Cui, Simon S. Du","submitted_at":"2022-06-01T00:18:15Z","abstract_excerpt":"This paper considers offline multi-agent reinforcement learning. We propose the strategy-wise concentration principle which directly builds a confidence interval for the joint strategy, in contrast to the point-wise concentration principle that builds a confidence interval for each point in the joint action space. For two-player zero-sum Markov games, by exploiting the convexity of the strategy-wise bonus, we propose a computationally efficient algorithm whose sample complexity enjoys a better dependency on the number of actions than the prior methods based on the point-wise bonus. Furthermore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00159","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/2206.00159/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":"2026-07-05T05:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1c6iKB/MQnQPWs2HrTNUM6vSDy/uvSZyMMmvTrJmVKRJJIKnoPBEFwIygpP4a0SrBt43OH6kEjWt0/MTWgZcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:52:21.031076Z"},"content_sha256":"b8623faca3a7437d4d184f16c35d748dfbd252ca066c5db0a02e2030129f84f2","schema_version":"1.0","event_id":"sha256:b8623faca3a7437d4d184f16c35d748dfbd252ca066c5db0a02e2030129f84f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YZ7BIWR24AAXSEYMLZBG6D6GQ/bundle.json","state_url":"https://pith.science/pith/3YZ7BIWR24AAXSEYMLZBG6D6GQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YZ7BIWR24AAXSEYMLZBG6D6GQ/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":"2026-08-18T22:52:21Z","links":{"resolver":"https://pith.science/pith/3YZ7BIWR24AAXSEYMLZBG6D6GQ","bundle":"https://pith.science/pith/3YZ7BIWR24AAXSEYMLZBG6D6GQ/bundle.json","state":"https://pith.science/pith/3YZ7BIWR24AAXSEYMLZBG6D6GQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YZ7BIWR24AAXSEYMLZBG6D6GQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3YZ7BIWR24AAXSEYMLZBG6D6GQ","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":"259f38958589775267359125e66941a407050dc390d585580c972ed912effed0","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T00:18:15Z","title_canon_sha256":"a457b0167b9a77c41cfcd75753cce52a55fd341495458ffe99cddb5bba9b8911"},"schema_version":"1.0","source":{"id":"2206.00159","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00159","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00159v2","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00159","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"3YZ7BIWR24AA","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"3YZ7BIWR24AAXSEY","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"3YZ7BIWR","created_at":"2026-07-05T05:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:b8623faca3a7437d4d184f16c35d748dfbd252ca066c5db0a02e2030129f84f2","target":"graph","created_at":"2026-07-05T05:06:31Z","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/2206.00159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper considers offline multi-agent reinforcement learning. We propose the strategy-wise concentration principle which directly builds a confidence interval for the joint strategy, in contrast to the point-wise concentration principle that builds a confidence interval for each point in the joint action space. For two-player zero-sum Markov games, by exploiting the convexity of the strategy-wise bonus, we propose a computationally efficient algorithm whose sample complexity enjoys a better dependency on the number of actions than the prior methods based on the point-wise bonus. Furthermore","authors_text":"Qiwen Cui, Simon S. Du","cross_cats":["cs.AI","cs.GT","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T00:18:15Z","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00159","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":"sha256:371016d0de32875234c7c02ee19110f99183d34c5f124b15f28e5322fbafdc46","target":"record","created_at":"2026-07-05T05:06:31Z","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":"259f38958589775267359125e66941a407050dc390d585580c972ed912effed0","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T00:18:15Z","title_canon_sha256":"a457b0167b9a77c41cfcd75753cce52a55fd341495458ffe99cddb5bba9b8911"},"schema_version":"1.0","source":{"id":"2206.00159","kind":"arxiv","version":2}},"canonical_sha256":"de33f0a2d1d7000bc89862f213787e340f8daef674fbdc709222a1bbbac70f20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de33f0a2d1d7000bc89862f213787e340f8daef674fbdc709222a1bbbac70f20","first_computed_at":"2026-07-05T05:06:31.984837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:31.984837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xdWwD4YC2rECoc9P29T8FFWsQS7bwcqQxn12QIOInrLcmj/Q7gcOugLMuWlXzZ2u3axq+zvKQXJ6TY2UxEXVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:31.985294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00159","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:371016d0de32875234c7c02ee19110f99183d34c5f124b15f28e5322fbafdc46","sha256:b8623faca3a7437d4d184f16c35d748dfbd252ca066c5db0a02e2030129f84f2"],"state_sha256":"9e2f5e0bd3730ba01254b6cda81972756625bf5e71850b4e8d0c0a46e4b5143a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIDA3LK14tYSlRpwePLJXOw6tK3+SBkJBi9oPSEMrVHIgSD+P0oZ7Txqu8SPQoAdTFwPV5OzZ8UG3Kzzcp/sDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:52:21.034174Z","bundle_sha256":"f985308eda992cc0a58916995c4e991a1e8118442a4caf212205f13ec77207dc"}}