{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XT57SREITSB5DXHTBOBCYWL6KQ","short_pith_number":"pith:XT57SREI","schema_version":"1.0","canonical_sha256":"bcfbf944889c83d1dcf30b822c597e54198ff891e6a74ffb240bec61e77e4cd1","source":{"kind":"arxiv","id":"2309.13278","version":2},"attestation_state":"computed","paper":{"title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Annie Qu, Ruoqing Zhu, Wenzhuo Zhou, Yuhan Li","submitted_at":"2023-09-23T06:35:44Z","abstract_excerpt":"We study high-confidence off-policy evaluation in the context of infinite-horizon Markov decision processes, where the objective is to establish a confidence interval (CI) for the target policy value using only offline data pre-collected from unknown behavior policies. This task faces two primary challenges: providing a comprehensive and rigorous error quantification in CI estimation, and addressing the distributional shift that results from discrepancies between the distribution induced by the target policy and the offline data-generating process. Motivated by an innovative unified error anal"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.13278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-23T06:35:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f5d2a6d886de467e1f0fa8758b6635b4fc67be76a8ce2bd9cc33bb52b99b8ad","abstract_canon_sha256":"b70ac48af63aa448668edb70d414c3a6998c124fed6d840d517807da31eb58a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:59.556176Z","signature_b64":"FYo5Ri/7jFFApSoUFliEytagINcMMlzkP4lo1kQAMNBkg9+ou0KrdmtfKBU2ACy1rkHn/9XBLenCSD44fs3uCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcfbf944889c83d1dcf30b822c597e54198ff891e6a74ffb240bec61e77e4cd1","last_reissued_at":"2026-07-05T06:55:59.555779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:59.555779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Annie Qu, Ruoqing Zhu, Wenzhuo Zhou, Yuhan Li","submitted_at":"2023-09-23T06:35:44Z","abstract_excerpt":"We study high-confidence off-policy evaluation in the context of infinite-horizon Markov decision processes, where the objective is to establish a confidence interval (CI) for the target policy value using only offline data pre-collected from unknown behavior policies. This task faces two primary challenges: providing a comprehensive and rigorous error quantification in CI estimation, and addressing the distributional shift that results from discrepancies between the distribution induced by the target policy and the offline data-generating process. Motivated by an innovative unified error anal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13278","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/2309.13278/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.13278","created_at":"2026-07-05T06:55:59.555834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13278v2","created_at":"2026-07-05T06:55:59.555834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13278","created_at":"2026-07-05T06:55:59.555834+00:00"},{"alias_kind":"pith_short_12","alias_value":"XT57SREITSB5","created_at":"2026-07-05T06:55:59.555834+00:00"},{"alias_kind":"pith_short_16","alias_value":"XT57SREITSB5DXHT","created_at":"2026-07-05T06:55:59.555834+00:00"},{"alias_kind":"pith_short_8","alias_value":"XT57SREI","created_at":"2026-07-05T06:55:59.555834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22492","citing_title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","ref_index":93,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ","json":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ.json","graph_json":"https://pith.science/api/pith-number/XT57SREITSB5DXHTBOBCYWL6KQ/graph.json","events_json":"https://pith.science/api/pith-number/XT57SREITSB5DXHTBOBCYWL6KQ/events.json","paper":"https://pith.science/paper/XT57SREI"},"agent_actions":{"view_html":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ","download_json":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ.json","view_paper":"https://pith.science/paper/XT57SREI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13278&json=true","fetch_graph":"https://pith.science/api/pith-number/XT57SREITSB5DXHTBOBCYWL6KQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XT57SREITSB5DXHTBOBCYWL6KQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ/action/storage_attestation","attest_author":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ/action/author_attestation","sign_citation":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ/action/citation_signature","submit_replication":"https://pith.science/pith/XT57SREITSB5DXHTBOBCYWL6KQ/action/replication_record"}},"created_at":"2026-07-05T06:55:59.555834+00:00","updated_at":"2026-07-05T06:55:59.555834+00:00"}