{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3VMDSXN22MOBCXPAKOBCMVS5IU","short_pith_number":"pith:3VMDSXN2","schema_version":"1.0","canonical_sha256":"dd58395dbad31c115de0538226565d45307f7a72383d7dafe200af279131bb58","source":{"kind":"arxiv","id":"2210.08571","version":3},"attestation_state":"computed","paper":{"title":"Dimension free ridge regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Andrea Montanari, Chen Cheng","submitted_at":"2022-10-16T16:01:05Z","abstract_excerpt":"Random matrix theory has become a widely useful tool in high-dimensional statistics and theoretical machine learning. However, random matrix theory is largely focused on the proportional asymptotics in which the number of columns grows proportionally to the number of rows of the data matrix. This is not always the most natural setting in statistics where columns correspond to covariates and rows to samples. With the objective to move beyond the proportional asymptotics, we revisit ridge regression ($\\ell_2$-penalized least squares) on i.i.d. data $(x_i, y_i)$, $i\\le n$, where $x_i$ is a featur"},"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":"2210.08571","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2022-10-16T16:01:05Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"398e16b9bde8822eff20436deed99734444a9dba291c09fb4254fa6aa930a104","abstract_canon_sha256":"1676193f00a615d84a20932c17a40b701a22eaf9aed06018f89d7d95734498f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:59.586685Z","signature_b64":"wAMznD44Pc9k9oLYe1q0pNzHuwKpyaJJQCCqOnIH2EDWZNQV9iRKjOvfBVvxa/s7HGlTUz6huTRjXZMO35rSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd58395dbad31c115de0538226565d45307f7a72383d7dafe200af279131bb58","last_reissued_at":"2026-07-05T11:23:59.586067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:59.586067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimension free ridge regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Andrea Montanari, Chen Cheng","submitted_at":"2022-10-16T16:01:05Z","abstract_excerpt":"Random matrix theory has become a widely useful tool in high-dimensional statistics and theoretical machine learning. However, random matrix theory is largely focused on the proportional asymptotics in which the number of columns grows proportionally to the number of rows of the data matrix. This is not always the most natural setting in statistics where columns correspond to covariates and rows to samples. With the objective to move beyond the proportional asymptotics, we revisit ridge regression ($\\ell_2$-penalized least squares) on i.i.d. data $(x_i, y_i)$, $i\\le n$, where $x_i$ is a featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08571","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/2210.08571/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":"2210.08571","created_at":"2026-07-05T11:23:59.586166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08571v3","created_at":"2026-07-05T11:23:59.586166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08571","created_at":"2026-07-05T11:23:59.586166+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VMDSXN22MOB","created_at":"2026-07-05T11:23:59.586166+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VMDSXN22MOBCXPA","created_at":"2026-07-05T11:23:59.586166+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VMDSXN2","created_at":"2026-07-05T11:23:59.586166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.00592","citing_title":"Scaling and renormalization in high-dimensional regression","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14473","citing_title":"Sharp convergence rates for Spectral methods via the feature space decomposition method","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23212","citing_title":"Learning Curves and Benign Overfitting of Spectral Algorithms in Large Dimensions","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU","json":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU.json","graph_json":"https://pith.science/api/pith-number/3VMDSXN22MOBCXPAKOBCMVS5IU/graph.json","events_json":"https://pith.science/api/pith-number/3VMDSXN22MOBCXPAKOBCMVS5IU/events.json","paper":"https://pith.science/paper/3VMDSXN2"},"agent_actions":{"view_html":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU","download_json":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU.json","view_paper":"https://pith.science/paper/3VMDSXN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08571&json=true","fetch_graph":"https://pith.science/api/pith-number/3VMDSXN22MOBCXPAKOBCMVS5IU/graph.json","fetch_events":"https://pith.science/api/pith-number/3VMDSXN22MOBCXPAKOBCMVS5IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU/action/storage_attestation","attest_author":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU/action/author_attestation","sign_citation":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU/action/citation_signature","submit_replication":"https://pith.science/pith/3VMDSXN22MOBCXPAKOBCMVS5IU/action/replication_record"}},"created_at":"2026-07-05T11:23:59.586166+00:00","updated_at":"2026-07-05T11:23:59.586166+00:00"}