{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:K3W76T7ADH2H4Y3PY6XCZ3JYC6","short_pith_number":"pith:K3W76T7A","schema_version":"1.0","canonical_sha256":"56edff4fe019f47e636fc7ae2ced3817b0ef18781d18b677589cd2fd8ea56f7e","source":{"kind":"arxiv","id":"1903.08560","version":5},"attestation_state":"computed","paper":{"title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Andrea Montanari, Ryan J. Tibshirani, Saharon Rosset, Trevor Hastie","submitted_at":"2019-03-19T16:53:11Z","abstract_excerpt":"Interpolators -- estimators that achieve zero training error -- have attracted growing attention in machine learning, mainly because state-of-the art neural networks appear to be models of this type. In this paper, we study minimum $\\ell_2$ norm (\"ridgeless\") interpolation in high-dimensional least squares regression. We consider two different models for the feature distribution: a linear model, where the feature vectors $x_i \\in {\\mathbb R}^p$ are obtained by applying a linear transform to a vector of i.i.d. entries, $x_i = \\Sigma^{1/2} z_i$ (with $z_i \\in {\\mathbb R}^p$); and a nonlinear mod"},"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":"1903.08560","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-03-19T16:53:11Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"61eb86a08ad39c8c4f5d1627b609331297b197cc695cb498f81187aee180557e","abstract_canon_sha256":"5660e4161a82f0ebd6e9a3201018f980fd679bffefecdc865af2a09a64a4fb06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:47.498934Z","signature_b64":"DWmhXjEv6VTAkLDd3RHpe0IsvsX+RABCZhg/0KggcDbY9I6/HmHXsw+9Ucutz4Kj2DJnLKN0AdVhWRDlwdCmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56edff4fe019f47e636fc7ae2ced3817b0ef18781d18b677589cd2fd8ea56f7e","last_reissued_at":"2026-07-05T04:55:47.498500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:47.498500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Andrea Montanari, Ryan J. Tibshirani, Saharon Rosset, Trevor Hastie","submitted_at":"2019-03-19T16:53:11Z","abstract_excerpt":"Interpolators -- estimators that achieve zero training error -- have attracted growing attention in machine learning, mainly because state-of-the art neural networks appear to be models of this type. In this paper, we study minimum $\\ell_2$ norm (\"ridgeless\") interpolation in high-dimensional least squares regression. We consider two different models for the feature distribution: a linear model, where the feature vectors $x_i \\in {\\mathbb R}^p$ are obtained by applying a linear transform to a vector of i.i.d. entries, $x_i = \\Sigma^{1/2} z_i$ (with $z_i \\in {\\mathbb R}^p$); and a nonlinear mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08560","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1903.08560/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":"1903.08560","created_at":"2026-07-05T04:55:47.498563+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08560v5","created_at":"2026-07-05T04:55:47.498563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08560","created_at":"2026-07-05T04:55:47.498563+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3W76T7ADH2H","created_at":"2026-07-05T04:55:47.498563+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3W76T7ADH2H4Y3P","created_at":"2026-07-05T04:55:47.498563+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3W76T7A","created_at":"2026-07-05T04:55:47.498563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08377","citing_title":"Eigenvalue Calibration for Semantic Embeddings of Large Language Models","ref_index":243,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27142","citing_title":"Estimation of High Dimensional Bounded Discrete Graphical Models via Regularized Generalized Score Matching","ref_index":263,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10089","citing_title":"A Theory on Flow Matching with Neural Networks","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"1906.08899","citing_title":"Limitations of Lazy Training of Two-layers Neural Networks","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23591","citing_title":"Asymmetric Scaling Laws from Sparse Features","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2205.13469","citing_title":"Proximal Estimation and Inference","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18448","citing_title":"Fixed-order PCA: Theory for Overestimated Factor Models","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2401.01335","citing_title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6","json":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6.json","graph_json":"https://pith.science/api/pith-number/K3W76T7ADH2H4Y3PY6XCZ3JYC6/graph.json","events_json":"https://pith.science/api/pith-number/K3W76T7ADH2H4Y3PY6XCZ3JYC6/events.json","paper":"https://pith.science/paper/K3W76T7A"},"agent_actions":{"view_html":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6","download_json":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6.json","view_paper":"https://pith.science/paper/K3W76T7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08560&json=true","fetch_graph":"https://pith.science/api/pith-number/K3W76T7ADH2H4Y3PY6XCZ3JYC6/graph.json","fetch_events":"https://pith.science/api/pith-number/K3W76T7ADH2H4Y3PY6XCZ3JYC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6/action/storage_attestation","attest_author":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6/action/author_attestation","sign_citation":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6/action/citation_signature","submit_replication":"https://pith.science/pith/K3W76T7ADH2H4Y3PY6XCZ3JYC6/action/replication_record"}},"created_at":"2026-07-05T04:55:47.498563+00:00","updated_at":"2026-07-05T04:55:47.498563+00:00"}