{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JDBHDXBHJKLWQ6UCFC6LYDZLZE","short_pith_number":"pith:JDBHDXBH","canonical_record":{"source":{"id":"2202.13890","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T15:39:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f1f86cca545fd2ecb5671610d74a9fddb7d2e40799e01257381bd5b9fef1a572","abstract_canon_sha256":"c281939f6363be2e0da47d11e74e810b68469a6ce914d1126549d445c2a03c7c"},"schema_version":"1.0"},"canonical_sha256":"48c271dc274a97687a8228bcbc0f2bc93226e921171102a9d3c1a47cc238ca68","source":{"kind":"arxiv","id":"2202.13890","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.13890","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"2202.13890v2","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13890","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"JDBHDXBHJKLW","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"JDBHDXBHJKLWQ6UC","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"JDBHDXBH","created_at":"2026-07-05T04:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JDBHDXBHJKLWQ6UCFC6LYDZLZE","target":"record","payload":{"canonical_record":{"source":{"id":"2202.13890","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T15:39:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f1f86cca545fd2ecb5671610d74a9fddb7d2e40799e01257381bd5b9fef1a572","abstract_canon_sha256":"c281939f6363be2e0da47d11e74e810b68469a6ce914d1126549d445c2a03c7c"},"schema_version":"1.0"},"canonical_sha256":"48c271dc274a97687a8228bcbc0f2bc93226e921171102a9d3c1a47cc238ca68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:55.340008Z","signature_b64":"uPHWrQlh/3/G4UpDA2EubZj5p/iBfaAof2uV5snOMlSkEI3sH4IFKPBxlq5WsBcSZ7SoHVDGamJ5PQZZUpnRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48c271dc274a97687a8228bcbc0f2bc93226e921171102a9d3c1a47cc238ca68","last_reissued_at":"2026-07-05T04:30:55.339494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:55.339494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.13890","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":"2026-07-05T04:30:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9xwihDV2Y69R06Xu9zWQEwEe0XKf4XcwZHL/FYeOrRch46j7o79AU7G8KNHmvy8cbT7qorUTOPbdxtcz7VHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:10:26.885452Z"},"content_sha256":"1ab19c858e10b96bd0b9eb7986190b940f0581dea38764ac6558d547c5c08ab7","schema_version":"1.0","event_id":"sha256:1ab19c858e10b96bd0b9eb7986190b940f0581dea38764ac6558d547c5c08ab7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JDBHDXBHJKLWQ6UCFC6LYDZLZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gen Li, Laixi Shi, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2022-02-28T15:39:36Z","abstract_excerpt":"Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle of pessimism has been recently introduced to mitigate high bias of the estimated values. While pessimistic variants of model-based algorithms (e.g., value iteration with lower confidence bounds) have been theoretically investigated, their model-free counterparts -- which do not require explicit model estimation -- have not been adequately studied, especially"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13890","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/2202.13890/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":"2026-07-05T04:30:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vv2TBBrc6I3qd7pEaq9qYomz+5Zx08/HdbKrH0t0f9UnfY4d6mbHT5EMOvSoX7fXPpfjcsglDJDZa7gxPBbkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:10:26.885953Z"},"content_sha256":"491db28bf9a1317042787c551466a1afd34ddede9ac4c65e6769960f8172407d","schema_version":"1.0","event_id":"sha256:491db28bf9a1317042787c551466a1afd34ddede9ac4c65e6769960f8172407d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDBHDXBHJKLWQ6UCFC6LYDZLZE/bundle.json","state_url":"https://pith.science/pith/JDBHDXBHJKLWQ6UCFC6LYDZLZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDBHDXBHJKLWQ6UCFC6LYDZLZE/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":"2026-08-21T10:10:26Z","links":{"resolver":"https://pith.science/pith/JDBHDXBHJKLWQ6UCFC6LYDZLZE","bundle":"https://pith.science/pith/JDBHDXBHJKLWQ6UCFC6LYDZLZE/bundle.json","state":"https://pith.science/pith/JDBHDXBHJKLWQ6UCFC6LYDZLZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDBHDXBHJKLWQ6UCFC6LYDZLZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JDBHDXBHJKLWQ6UCFC6LYDZLZE","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":"c281939f6363be2e0da47d11e74e810b68469a6ce914d1126549d445c2a03c7c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T15:39:36Z","title_canon_sha256":"f1f86cca545fd2ecb5671610d74a9fddb7d2e40799e01257381bd5b9fef1a572"},"schema_version":"1.0","source":{"id":"2202.13890","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.13890","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"2202.13890v2","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13890","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"JDBHDXBHJKLW","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"JDBHDXBHJKLWQ6UC","created_at":"2026-07-05T04:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"JDBHDXBH","created_at":"2026-07-05T04:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:491db28bf9a1317042787c551466a1afd34ddede9ac4c65e6769960f8172407d","target":"graph","created_at":"2026-07-05T04:30:55Z","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/2202.13890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle of pessimism has been recently introduced to mitigate high bias of the estimated values. While pessimistic variants of model-based algorithms (e.g., value iteration with lower confidence bounds) have been theoretically investigated, their model-free counterparts -- which do not require explicit model estimation -- have not been adequately studied, especially","authors_text":"Gen Li, Laixi Shi, Yuejie Chi, Yuting Wei, Yuxin Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T15:39:36Z","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13890","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":"sha256:1ab19c858e10b96bd0b9eb7986190b940f0581dea38764ac6558d547c5c08ab7","target":"record","created_at":"2026-07-05T04:30:55Z","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":"c281939f6363be2e0da47d11e74e810b68469a6ce914d1126549d445c2a03c7c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T15:39:36Z","title_canon_sha256":"f1f86cca545fd2ecb5671610d74a9fddb7d2e40799e01257381bd5b9fef1a572"},"schema_version":"1.0","source":{"id":"2202.13890","kind":"arxiv","version":2}},"canonical_sha256":"48c271dc274a97687a8228bcbc0f2bc93226e921171102a9d3c1a47cc238ca68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48c271dc274a97687a8228bcbc0f2bc93226e921171102a9d3c1a47cc238ca68","first_computed_at":"2026-07-05T04:30:55.339494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:55.339494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uPHWrQlh/3/G4UpDA2EubZj5p/iBfaAof2uV5snOMlSkEI3sH4IFKPBxlq5WsBcSZ7SoHVDGamJ5PQZZUpnRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:55.340008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.13890","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ab19c858e10b96bd0b9eb7986190b940f0581dea38764ac6558d547c5c08ab7","sha256:491db28bf9a1317042787c551466a1afd34ddede9ac4c65e6769960f8172407d"],"state_sha256":"ecea3b528fe831e732c61aad6a746a6bc4d90559a87c52a799a55aaa977b4769"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1lIeOLwQklyqdvuANcrgbRwbvCV71P7pPncMxosbFHWcvWyzJpFaRm1n6z9bfnfSadiuoBQi/WnHWQNHvOvCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:10:26.889906Z","bundle_sha256":"6c825a55f8639b55dd4280f2a590f8f682e0d50c91894ae0e47542a6185357be"}}