{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FF6ZTM72ORKRES22BEFOFUB66B","short_pith_number":"pith:FF6ZTM72","schema_version":"1.0","canonical_sha256":"297d99b3fa7455124b5a090ae2d03ef0698a2e9b3431f8028fd7b9b29a7a466b","source":{"kind":"arxiv","id":"2310.07973","version":3},"attestation_state":"computed","paper":{"title":"Statistical Performance Guarantee for Subgroup Identification with Generic Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.AP","stat.ML"],"primary_cat":"stat.ME","authors_text":"Kosuke Imai, Michael Lingzhi Li","submitted_at":"2023-10-12T01:41:47Z","abstract_excerpt":"Across a wide array of disciplines, many researchers use machine learning (ML) algorithms to identify a subgroup of individuals who are likely to benefit from a treatment the most (``exceptional responders'') or those who are harmed by it. A common approach to this subgroup identification problem consists of two steps. First, researchers estimate the conditional average treatment effect (CATE) using an ML algorithm. Next, they use the estimated CATE to select those individuals who are predicted to be most affected by the treatment, either positively or negatively. Unfortunately, CATE estimates"},"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":"2310.07973","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-10-12T01:41:47Z","cross_cats_sorted":["math.OC","stat.AP","stat.ML"],"title_canon_sha256":"a44f3684566febbec25539fcbd8feb404db6505ea83efb8d96a7c961d8cfab8b","abstract_canon_sha256":"29d8ee1f3ecf57fc1a7b4bc2768f2b2117ebce2ddbbdf11ac50ce7a5c9494b1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:52.558508Z","signature_b64":"mv9P9CP31PFoFjWXpSEw8D913eBVoXjQydQJzI+lQo7zsj0cK6kJ8zpD+LiXsuqFzB9LYtNLCWYLsIB9/uLcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"297d99b3fa7455124b5a090ae2d03ef0698a2e9b3431f8028fd7b9b29a7a466b","last_reissued_at":"2026-07-05T12:01:52.557934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:52.557934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Performance Guarantee for Subgroup Identification with Generic Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.AP","stat.ML"],"primary_cat":"stat.ME","authors_text":"Kosuke Imai, Michael Lingzhi Li","submitted_at":"2023-10-12T01:41:47Z","abstract_excerpt":"Across a wide array of disciplines, many researchers use machine learning (ML) algorithms to identify a subgroup of individuals who are likely to benefit from a treatment the most (``exceptional responders'') or those who are harmed by it. A common approach to this subgroup identification problem consists of two steps. First, researchers estimate the conditional average treatment effect (CATE) using an ML algorithm. Next, they use the estimated CATE to select those individuals who are predicted to be most affected by the treatment, either positively or negatively. Unfortunately, CATE estimates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07973","kind":"arxiv","version":3},"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/2310.07973/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":"2310.07973","created_at":"2026-07-05T12:01:52.558000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07973v3","created_at":"2026-07-05T12:01:52.558000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07973","created_at":"2026-07-05T12:01:52.558000+00:00"},{"alias_kind":"pith_short_12","alias_value":"FF6ZTM72ORKR","created_at":"2026-07-05T12:01:52.558000+00:00"},{"alias_kind":"pith_short_16","alias_value":"FF6ZTM72ORKRES22","created_at":"2026-07-05T12:01:52.558000+00:00"},{"alias_kind":"pith_short_8","alias_value":"FF6ZTM72","created_at":"2026-07-05T12:01:52.558000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09741","citing_title":"Adaptive discovery of effect modification in matched observational studies","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B","json":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B.json","graph_json":"https://pith.science/api/pith-number/FF6ZTM72ORKRES22BEFOFUB66B/graph.json","events_json":"https://pith.science/api/pith-number/FF6ZTM72ORKRES22BEFOFUB66B/events.json","paper":"https://pith.science/paper/FF6ZTM72"},"agent_actions":{"view_html":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B","download_json":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B.json","view_paper":"https://pith.science/paper/FF6ZTM72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07973&json=true","fetch_graph":"https://pith.science/api/pith-number/FF6ZTM72ORKRES22BEFOFUB66B/graph.json","fetch_events":"https://pith.science/api/pith-number/FF6ZTM72ORKRES22BEFOFUB66B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B/action/storage_attestation","attest_author":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B/action/author_attestation","sign_citation":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B/action/citation_signature","submit_replication":"https://pith.science/pith/FF6ZTM72ORKRES22BEFOFUB66B/action/replication_record"}},"created_at":"2026-07-05T12:01:52.558000+00:00","updated_at":"2026-07-05T12:01:52.558000+00:00"}