{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2009:WP6DU432Y6ZBAR3JR5JTPTT7NI","short_pith_number":"pith:WP6DU432","schema_version":"1.0","canonical_sha256":"b3fc3a737ac7b21047698f5337ce7f6a3e927b41e72449e387d9300e23b0d88e","source":{"kind":"arxiv","id":"1001.0188","version":5},"attestation_state":"computed","paper":{"title":"Least squares after model selection in high-dimensional sparse models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Alexandre Belloni, Victor Chernozhukov","submitted_at":"2009-12-31T22:10:59Z","abstract_excerpt":"In this article we study post-model selection estimators that apply ordinary least squares (OLS) to the model selected by first-step penalized estimators, typically Lasso. It is well known that Lasso can estimate the nonparametric regression function at nearly the oracle rate, and is thus hard to improve upon. We show that the OLS post-Lasso estimator performs at least as well as Lasso in terms of the rate of convergence, and has the advantage of a smaller bias. Remarkably, this performance occurs even if the Lasso-based model selection \"fails\" in the sense of missing some components of the \"t"},"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":"1001.0188","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2009-12-31T22:10:59Z","cross_cats_sorted":["math.PR","stat.ME","stat.TH"],"title_canon_sha256":"d7d33e2f9cc08fd0f182c61406b0b8d27f1164527340203387e69d4cb44e4fd0","abstract_canon_sha256":"d5d090138a1b53a17f6414558e51cb47abf557a59fcc961b52319369c9d228b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:30:26.226914Z","signature_b64":"XjjlTFENJG92FdoC+FloBRcpu/fBzdZ5N5dbjp2rSQmXTmrIU0ZKJf9MBUcQ49xOPf2a2C3GsMsJy8ObcdhHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3fc3a737ac7b21047698f5337ce7f6a3e927b41e72449e387d9300e23b0d88e","last_reissued_at":"2026-05-18T03:30:26.226255Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:30:26.226255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Least squares after model selection in high-dimensional sparse models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Alexandre Belloni, Victor Chernozhukov","submitted_at":"2009-12-31T22:10:59Z","abstract_excerpt":"In this article we study post-model selection estimators that apply ordinary least squares (OLS) to the model selected by first-step penalized estimators, typically Lasso. It is well known that Lasso can estimate the nonparametric regression function at nearly the oracle rate, and is thus hard to improve upon. We show that the OLS post-Lasso estimator performs at least as well as Lasso in terms of the rate of convergence, and has the advantage of a smaller bias. Remarkably, this performance occurs even if the Lasso-based model selection \"fails\" in the sense of missing some components of the \"t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1001.0188","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1001.0188","created_at":"2026-05-18T03:30:26.226355+00:00"},{"alias_kind":"arxiv_version","alias_value":"1001.0188v5","created_at":"2026-05-18T03:30:26.226355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1001.0188","created_at":"2026-05-18T03:30:26.226355+00:00"},{"alias_kind":"pith_short_12","alias_value":"WP6DU432Y6ZB","created_at":"2026-05-18T12:26:02.257875+00:00"},{"alias_kind":"pith_short_16","alias_value":"WP6DU432Y6ZBAR3J","created_at":"2026-05-18T12:26:02.257875+00:00"},{"alias_kind":"pith_short_8","alias_value":"WP6DU432","created_at":"2026-05-18T12:26:02.257875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17910","citing_title":"Double/Debiased Machine Learning for Continuous Treatment Effects in Panel Data with Endogeneity","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI","json":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI.json","graph_json":"https://pith.science/api/pith-number/WP6DU432Y6ZBAR3JR5JTPTT7NI/graph.json","events_json":"https://pith.science/api/pith-number/WP6DU432Y6ZBAR3JR5JTPTT7NI/events.json","paper":"https://pith.science/paper/WP6DU432"},"agent_actions":{"view_html":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI","download_json":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI.json","view_paper":"https://pith.science/paper/WP6DU432","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1001.0188&json=true","fetch_graph":"https://pith.science/api/pith-number/WP6DU432Y6ZBAR3JR5JTPTT7NI/graph.json","fetch_events":"https://pith.science/api/pith-number/WP6DU432Y6ZBAR3JR5JTPTT7NI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI/action/storage_attestation","attest_author":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI/action/author_attestation","sign_citation":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI/action/citation_signature","submit_replication":"https://pith.science/pith/WP6DU432Y6ZBAR3JR5JTPTT7NI/action/replication_record"}},"created_at":"2026-05-18T03:30:26.226355+00:00","updated_at":"2026-05-18T03:30:26.226355+00:00"}