{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GFB3P47MEALCPKRFHBEDWFPZJN","short_pith_number":"pith:GFB3P47M","schema_version":"1.0","canonical_sha256":"3143b7f3ec201627aa2538483b15f94b4b4035f40eb5ea1176588a1d2f11854d","source":{"kind":"arxiv","id":"1901.09036","version":4},"attestation_state":"computed","paper":{"title":"Orthogonal Statistical Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","econ.EM","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Dylan J. Foster, Vasilis Syrgkanis","submitted_at":"2019-01-25T02:21:24Z","abstract_excerpt":"We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data. We analyze a two-stage sample splitting meta-algorithm that takes as input arbitrary estimation algorithms for the target parameter and nuisance parameter. We show that if the population risk satisfies a condition called Neyman orthogonality, the impact of the nuisance estimation error on the excess risk bound achieved by the meta-algorithm is of second o"},"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":"1901.09036","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-01-25T02:21:24Z","cross_cats_sorted":["cs.LG","econ.EM","stat.ML","stat.TH"],"title_canon_sha256":"3f6bc0f32204659e9257b29afb132baa997f326680a2c26bfbc90c9027c8ce67","abstract_canon_sha256":"2f7e30d0bb3a92339a6fd44c847c5d99cbf1dee3c2bee09f2d8abfb771829d76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:35.057216Z","signature_b64":"DxqDWBiH3NJH8sqgmutP2La73h+6mbfq6dXw+7AIm1RaOAYu5Yttwg5BTwm5Li+Vh72KNxnovpqRL+SFO29lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3143b7f3ec201627aa2538483b15f94b4b4035f40eb5ea1176588a1d2f11854d","last_reissued_at":"2026-07-05T06:17:35.056725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:35.056725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orthogonal Statistical Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","econ.EM","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Dylan J. Foster, Vasilis Syrgkanis","submitted_at":"2019-01-25T02:21:24Z","abstract_excerpt":"We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data. We analyze a two-stage sample splitting meta-algorithm that takes as input arbitrary estimation algorithms for the target parameter and nuisance parameter. We show that if the population risk satisfies a condition called Neyman orthogonality, the impact of the nuisance estimation error on the excess risk bound achieved by the meta-algorithm is of second o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09036","kind":"arxiv","version":4},"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/1901.09036/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":"1901.09036","created_at":"2026-07-05T06:17:35.056782+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.09036v4","created_at":"2026-07-05T06:17:35.056782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09036","created_at":"2026-07-05T06:17:35.056782+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFB3P47MEALC","created_at":"2026-07-05T06:17:35.056782+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFB3P47MEALCPKRF","created_at":"2026-07-05T06:17:35.056782+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFB3P47M","created_at":"2026-07-05T06:17:35.056782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31122","citing_title":"Generating Plausible Stress Scenarios via Large Deviations","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26288","citing_title":"Beyond Differences: Doubly Robust Meta-Learners for Ratio-Based Treatment Effects","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2207.11825","citing_title":"Fast convergence rates for dose-response estimation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07176","citing_title":"Mind the Gap: Optimal and Equitable Encouragement Policies","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15373","citing_title":"Nonparametric inference for sublevel-set probabilities of conditional average treatment effect functions","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN","json":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN.json","graph_json":"https://pith.science/api/pith-number/GFB3P47MEALCPKRFHBEDWFPZJN/graph.json","events_json":"https://pith.science/api/pith-number/GFB3P47MEALCPKRFHBEDWFPZJN/events.json","paper":"https://pith.science/paper/GFB3P47M"},"agent_actions":{"view_html":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN","download_json":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN.json","view_paper":"https://pith.science/paper/GFB3P47M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.09036&json=true","fetch_graph":"https://pith.science/api/pith-number/GFB3P47MEALCPKRFHBEDWFPZJN/graph.json","fetch_events":"https://pith.science/api/pith-number/GFB3P47MEALCPKRFHBEDWFPZJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN/action/storage_attestation","attest_author":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN/action/author_attestation","sign_citation":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN/action/citation_signature","submit_replication":"https://pith.science/pith/GFB3P47MEALCPKRFHBEDWFPZJN/action/replication_record"}},"created_at":"2026-07-05T06:17:35.056782+00:00","updated_at":"2026-07-05T06:17:35.056782+00:00"}