{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:75FGIQ725WTTGOMKFPRVLMMGL4","short_pith_number":"pith:75FGIQ72","schema_version":"1.0","canonical_sha256":"ff4a6443faeda733398a2be355b1865f12f71ce01e248b882dc72d4bfcca15f1","source":{"kind":"arxiv","id":"2503.07966","version":1},"attestation_state":"computed","paper":{"title":"Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Tsigler, Luiz F. O. Chamon, Peter L. Bartlett, Spencer Frei","submitted_at":"2025-03-11T01:45:42Z","abstract_excerpt":"In this work, we investigate the behavior of ridge regression in an overparameterized binary classification task. We assume examples are drawn from (anisotropic) class-conditional cluster distributions with opposing means and we allow for the training labels to have a constant level of label-flipping noise. We characterize the classification error achieved by ridge regression under the assumption that the covariance matrix of the cluster distribution has a high effective rank in the tail. We show that ridge regression has qualitatively different behavior depending on the scale of the cluster m"},"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":"2503.07966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-03-11T01:45:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"26159406f23424c30c1754f0d3ef88ea89904d2be62990d5248658d825c2d128","abstract_canon_sha256":"74d93499e2cf2c0f5c1553ab912da8554ae2ee64dcd395be426740ec1fb3c302"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:47.613290Z","signature_b64":"BRCtnamCzkcNKhgtwzFi68urzlsTMPp5oqqeztaxKdJ1yeubxiCzwyyL1bUuwjr3CDTGPgzxWjoSSeoClmLpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff4a6443faeda733398a2be355b1865f12f71ce01e248b882dc72d4bfcca15f1","last_reissued_at":"2026-07-05T10:28:47.612229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:47.612229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Tsigler, Luiz F. O. Chamon, Peter L. Bartlett, Spencer Frei","submitted_at":"2025-03-11T01:45:42Z","abstract_excerpt":"In this work, we investigate the behavior of ridge regression in an overparameterized binary classification task. We assume examples are drawn from (anisotropic) class-conditional cluster distributions with opposing means and we allow for the training labels to have a constant level of label-flipping noise. We characterize the classification error achieved by ridge regression under the assumption that the covariance matrix of the cluster distribution has a high effective rank in the tail. We show that ridge regression has qualitatively different behavior depending on the scale of the cluster m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07966","kind":"arxiv","version":1},"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/2503.07966/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":"2503.07966","created_at":"2026-07-05T10:28:47.612327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07966v1","created_at":"2026-07-05T10:28:47.612327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07966","created_at":"2026-07-05T10:28:47.612327+00:00"},{"alias_kind":"pith_short_12","alias_value":"75FGIQ725WTT","created_at":"2026-07-05T10:28:47.612327+00:00"},{"alias_kind":"pith_short_16","alias_value":"75FGIQ725WTTGOMK","created_at":"2026-07-05T10:28:47.612327+00:00"},{"alias_kind":"pith_short_8","alias_value":"75FGIQ72","created_at":"2026-07-05T10:28:47.612327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14200","citing_title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4","json":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4.json","graph_json":"https://pith.science/api/pith-number/75FGIQ725WTTGOMKFPRVLMMGL4/graph.json","events_json":"https://pith.science/api/pith-number/75FGIQ725WTTGOMKFPRVLMMGL4/events.json","paper":"https://pith.science/paper/75FGIQ72"},"agent_actions":{"view_html":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4","download_json":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4.json","view_paper":"https://pith.science/paper/75FGIQ72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07966&json=true","fetch_graph":"https://pith.science/api/pith-number/75FGIQ725WTTGOMKFPRVLMMGL4/graph.json","fetch_events":"https://pith.science/api/pith-number/75FGIQ725WTTGOMKFPRVLMMGL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4/action/storage_attestation","attest_author":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4/action/author_attestation","sign_citation":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4/action/citation_signature","submit_replication":"https://pith.science/pith/75FGIQ725WTTGOMKFPRVLMMGL4/action/replication_record"}},"created_at":"2026-07-05T10:28:47.612327+00:00","updated_at":"2026-07-05T10:28:47.612327+00:00"}