{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O2KJLZ6QWJGN4M44YTWSPW4CSE","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":"2a6b72f2a0b86e3f19debc64b6cfa0e1a4d8b29e62f8ed5712f235f285c36605","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-11-19T10:18:27Z","title_canon_sha256":"6f52ab736bc64eac90a32acecd932960c11eeb6fc7b310f901faf1aa45007817"},"schema_version":"1.0","source":{"id":"2411.12786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12786","created_at":"2026-07-05T09:38:00Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12786v1","created_at":"2026-07-05T09:38:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12786","created_at":"2026-07-05T09:38:00Z"},{"alias_kind":"pith_short_12","alias_value":"O2KJLZ6QWJGN","created_at":"2026-07-05T09:38:00Z"},{"alias_kind":"pith_short_16","alias_value":"O2KJLZ6QWJGN4M44","created_at":"2026-07-05T09:38:00Z"},{"alias_kind":"pith_short_8","alias_value":"O2KJLZ6Q","created_at":"2026-07-05T09:38:00Z"}],"graph_snapshots":[{"event_id":"sha256:d60707bfbda77d15893d92b750930c1f91eac6f8c284f32120ba31399a459759","target":"graph","created_at":"2026-07-05T09:38:00Z","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/2411.12786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider estimation of a linear functional of the treatment effect using adaptively collected data. This task finds a variety of applications including the off-policy evaluation (\\textsf{OPE}) in contextual bandits, and estimation of the average treatment effect (\\textsf{ATE}) in causal inference. While a certain class of augmented inverse propensity weighting (\\textsf{AIPW}) estimators enjoys desirable asymptotic properties including the semi-parametric efficiency, much less is known about their non-asymptotic theory with adaptively collected data. To fill in the gap, we first establish ge","authors_text":"Cong Ma, Jeonghwan Lee","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-11-19T10:18:27Z","title":"Off-policy estimation with adaptively collected data: the power of online learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12786","kind":"arxiv","version":1},"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":"sha256:7e1e8e57b4de33e6ff29c90a30f9839ed265c11626d97cf3944480dd475eb559","target":"record","created_at":"2026-07-05T09:38:00Z","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":"2a6b72f2a0b86e3f19debc64b6cfa0e1a4d8b29e62f8ed5712f235f285c36605","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-11-19T10:18:27Z","title_canon_sha256":"6f52ab736bc64eac90a32acecd932960c11eeb6fc7b310f901faf1aa45007817"},"schema_version":"1.0","source":{"id":"2411.12786","kind":"arxiv","version":1}},"canonical_sha256":"769495e7d0b24cde339cc4ed27db829115140af3ca24bde015990935fe13da14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"769495e7d0b24cde339cc4ed27db829115140af3ca24bde015990935fe13da14","first_computed_at":"2026-07-05T09:38:00.415111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:00.415111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6/1VK7XNF+H191duFIwBCY7qeZVo0Pi0TKJ6Dtpft7VUQl8w1lUahIpWWu4xMYIgvBOS2wzjR7YVWriBIHvUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:00.415494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e1e8e57b4de33e6ff29c90a30f9839ed265c11626d97cf3944480dd475eb559","sha256:d60707bfbda77d15893d92b750930c1f91eac6f8c284f32120ba31399a459759"],"state_sha256":"a5613ae2fff8cf2f3f10769f9d3c01f304cf764858c340a61e5ebdeb0875e846"}