{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BBZVXTGSWUGWCAESAAAHPIY7XW","short_pith_number":"pith:BBZVXTGS","schema_version":"1.0","canonical_sha256":"08735bccd2b50d610092000077a31fbda78aad007e31229fc8321834446a22f1","source":{"kind":"arxiv","id":"1906.11300","version":3},"attestation_state":"computed","paper":{"title":"Benign Overfitting in Linear Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexander Tsigler, G\\'abor Lugosi, Peter L. Bartlett, Philip M. Long","submitted_at":"2019-06-26T19:09:56Z","abstract_excerpt":"The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Motivated by this phenomenon, we consider when a perfect fit to training data in linear regression is compatible with accurate prediction. We give a characterization of linear regression problems for which the minimum norm interpolating prediction rule has near-optimal prediction accuracy. The characterization is in terms of two notions of the effective rank of the data covariance. It shows that overp"},"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":"1906.11300","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-26T19:09:56Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"0ab2e531d06ebb62ff59832e02b9751fee00f01200cf63614cf23ff52dd0f491","abstract_canon_sha256":"8b2aba8997524fd5e22d4b30706f1e82bf3f1d86937bbdcafe0aee896dcbad7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:49.033663Z","signature_b64":"hyL7GxXVZ4Cq9xnBtXH1PIutHpA8yYpBxiwnGYmxKJ/SkwFKOlVX+nyq6p/LcHiPi8+WPfRpifnUTbmlP7o3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08735bccd2b50d610092000077a31fbda78aad007e31229fc8321834446a22f1","last_reissued_at":"2026-07-05T04:29:49.033154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:49.033154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benign Overfitting in Linear Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexander Tsigler, G\\'abor Lugosi, Peter L. Bartlett, Philip M. Long","submitted_at":"2019-06-26T19:09:56Z","abstract_excerpt":"The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Motivated by this phenomenon, we consider when a perfect fit to training data in linear regression is compatible with accurate prediction. We give a characterization of linear regression problems for which the minimum norm interpolating prediction rule has near-optimal prediction accuracy. The characterization is in terms of two notions of the effective rank of the data covariance. It shows that overp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11300","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/1906.11300/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":"1906.11300","created_at":"2026-07-05T04:29:49.033211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11300v3","created_at":"2026-07-05T04:29:49.033211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11300","created_at":"2026-07-05T04:29:49.033211+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBZVXTGSWUGW","created_at":"2026-07-05T04:29:49.033211+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBZVXTGSWUGWCAES","created_at":"2026-07-05T04:29:49.033211+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBZVXTGS","created_at":"2026-07-05T04:29:49.033211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23591","citing_title":"Asymmetric Scaling Laws from Sparse Features","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW","json":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW.json","graph_json":"https://pith.science/api/pith-number/BBZVXTGSWUGWCAESAAAHPIY7XW/graph.json","events_json":"https://pith.science/api/pith-number/BBZVXTGSWUGWCAESAAAHPIY7XW/events.json","paper":"https://pith.science/paper/BBZVXTGS"},"agent_actions":{"view_html":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW","download_json":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW.json","view_paper":"https://pith.science/paper/BBZVXTGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11300&json=true","fetch_graph":"https://pith.science/api/pith-number/BBZVXTGSWUGWCAESAAAHPIY7XW/graph.json","fetch_events":"https://pith.science/api/pith-number/BBZVXTGSWUGWCAESAAAHPIY7XW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW/action/storage_attestation","attest_author":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW/action/author_attestation","sign_citation":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW/action/citation_signature","submit_replication":"https://pith.science/pith/BBZVXTGSWUGWCAESAAAHPIY7XW/action/replication_record"}},"created_at":"2026-07-05T04:29:49.033211+00:00","updated_at":"2026-07-05T04:29:49.033211+00:00"}