{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BYY5H3QV75D2Y32IH3UN33WLGM","short_pith_number":"pith:BYY5H3QV","canonical_record":{"source":{"id":"2007.03760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:44:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6a10551798d13e78194118dff984040f7fd1c54eb0978e0ac29e4f6383c70816","abstract_canon_sha256":"1afcfa8f42e83f442c3e4ae13474eae6f738165f19b5ce61e97e4d4991bd7cf3"},"schema_version":"1.0"},"canonical_sha256":"0e31d3ee15ff47ac6f483ee8ddeecb331feeec59faed62e9e592a127c4d0f670","source":{"kind":"arxiv","id":"2007.03760","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03760","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03760v2","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03760","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_12","alias_value":"BYY5H3QV75D2","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_16","alias_value":"BYY5H3QV75D2Y32I","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_8","alias_value":"BYY5H3QV","created_at":"2026-07-05T01:55:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BYY5H3QV75D2Y32IH3UN33WLGM","target":"record","payload":{"canonical_record":{"source":{"id":"2007.03760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:44:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6a10551798d13e78194118dff984040f7fd1c54eb0978e0ac29e4f6383c70816","abstract_canon_sha256":"1afcfa8f42e83f442c3e4ae13474eae6f738165f19b5ce61e97e4d4991bd7cf3"},"schema_version":"1.0"},"canonical_sha256":"0e31d3ee15ff47ac6f483ee8ddeecb331feeec59faed62e9e592a127c4d0f670","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:29.263307Z","signature_b64":"IQ0pSckj3tXITFR4C/TXtms343wcxvOQpUM/h4VcBhmHbHsaomYN0k/qGWKgZZqNCF8mjZSW7gKNJKzC9lAIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e31d3ee15ff47ac6f483ee8ddeecb331feeec59faed62e9e592a127c4d0f670","last_reissued_at":"2026-07-05T01:55:29.262863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:29.262863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.03760","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":"2026-07-05T01:55:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qkZxNYjpgS04m9FxAwLl1UnmGGThqbfZbFkAXswVkO6lVL965tiir3B8Q3j1VclWEv1vXEWhHY7y2sMrQLJdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:55:06.322110Z"},"content_sha256":"6465086ba5bcf7827fe965d64222d7fc6d0ed963eab89623e20d3dc390de96a4","schema_version":"1.0","event_id":"sha256:6465086ba5bcf7827fe965d64222d7fc6d0ed963eab89623e20d3dc390de96a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BYY5H3QV75D2Y32IH3UN33WLGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ming Yin, Yu Bai, Yu-Xiang Wang","submitted_at":"2020-07-07T19:44:14Z","abstract_excerpt":"The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications. Existing work on OPE mostly focus on evaluating a fixed target policy $\\pi$, which does not provide useful bounds for offline policy learning as $\\pi$ will then be data-dependent. We address this problem by simultaneously evaluating all policies in a policy class $\\Pi$ -- uniform convergence in OPE -- and obtain nearly optimal error bounds for a number of global / local policy classes. Our results imply that the model-based planning achieves an optimal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03760","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/2007.03760/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":"2026-07-05T01:55:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d8Nv3U5R8A4gmKKR1JN4teBSw3NgupI+Ot+7otwhF56J5nawkTCO5te4sLYH3VOamhki8v71Zr22u2Ouf4BdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:55:06.326120Z"},"content_sha256":"464255c282ef18f3ad4b2d1500c717529b52e1dae3913e084eda21837b8c2141","schema_version":"1.0","event_id":"sha256:464255c282ef18f3ad4b2d1500c717529b52e1dae3913e084eda21837b8c2141"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYY5H3QV75D2Y32IH3UN33WLGM/bundle.json","state_url":"https://pith.science/pith/BYY5H3QV75D2Y32IH3UN33WLGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYY5H3QV75D2Y32IH3UN33WLGM/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":"2026-08-16T13:55:06Z","links":{"resolver":"https://pith.science/pith/BYY5H3QV75D2Y32IH3UN33WLGM","bundle":"https://pith.science/pith/BYY5H3QV75D2Y32IH3UN33WLGM/bundle.json","state":"https://pith.science/pith/BYY5H3QV75D2Y32IH3UN33WLGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYY5H3QV75D2Y32IH3UN33WLGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BYY5H3QV75D2Y32IH3UN33WLGM","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":"1afcfa8f42e83f442c3e4ae13474eae6f738165f19b5ce61e97e4d4991bd7cf3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:44:14Z","title_canon_sha256":"6a10551798d13e78194118dff984040f7fd1c54eb0978e0ac29e4f6383c70816"},"schema_version":"1.0","source":{"id":"2007.03760","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03760","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03760v2","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03760","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_12","alias_value":"BYY5H3QV75D2","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_16","alias_value":"BYY5H3QV75D2Y32I","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_8","alias_value":"BYY5H3QV","created_at":"2026-07-05T01:55:29Z"}],"graph_snapshots":[{"event_id":"sha256:464255c282ef18f3ad4b2d1500c717529b52e1dae3913e084eda21837b8c2141","target":"graph","created_at":"2026-07-05T01:55:29Z","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/2007.03760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications. Existing work on OPE mostly focus on evaluating a fixed target policy $\\pi$, which does not provide useful bounds for offline policy learning as $\\pi$ will then be data-dependent. We address this problem by simultaneously evaluating all policies in a policy class $\\Pi$ -- uniform convergence in OPE -- and obtain nearly optimal error bounds for a number of global / local policy classes. Our results imply that the model-based planning achieves an optimal","authors_text":"Ming Yin, Yu Bai, Yu-Xiang Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:44:14Z","title":"Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03760","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":"sha256:6465086ba5bcf7827fe965d64222d7fc6d0ed963eab89623e20d3dc390de96a4","target":"record","created_at":"2026-07-05T01:55:29Z","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":"1afcfa8f42e83f442c3e4ae13474eae6f738165f19b5ce61e97e4d4991bd7cf3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:44:14Z","title_canon_sha256":"6a10551798d13e78194118dff984040f7fd1c54eb0978e0ac29e4f6383c70816"},"schema_version":"1.0","source":{"id":"2007.03760","kind":"arxiv","version":2}},"canonical_sha256":"0e31d3ee15ff47ac6f483ee8ddeecb331feeec59faed62e9e592a127c4d0f670","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e31d3ee15ff47ac6f483ee8ddeecb331feeec59faed62e9e592a127c4d0f670","first_computed_at":"2026-07-05T01:55:29.262863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:29.262863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQ0pSckj3tXITFR4C/TXtms343wcxvOQpUM/h4VcBhmHbHsaomYN0k/qGWKgZZqNCF8mjZSW7gKNJKzC9lAIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:29.263307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03760","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6465086ba5bcf7827fe965d64222d7fc6d0ed963eab89623e20d3dc390de96a4","sha256:464255c282ef18f3ad4b2d1500c717529b52e1dae3913e084eda21837b8c2141"],"state_sha256":"fd638ebc35e2c2967391ca10ddfbc28e519d94cc8a87194b20ef88cf764d2bbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ufKVCYnVm8N2W8zSn+X5/kNDs1n0KIJYitPnx0+uy75PQFCe0uEeboqTCJ2Dj2JniLTjXssVwRvO3HF89joUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T13:55:06.387943Z","bundle_sha256":"a61862170745ae79dc8e2251cda233453f9cd1cd4e76aa78e97a0b7f87b48f28"}}