{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LLTCNPBQPTMZAO6U4VNJIMRJEE","short_pith_number":"pith:LLTCNPBQ","schema_version":"1.0","canonical_sha256":"5ae626bc307cd9903bd4e55a943229210daa55f54ac289e310f77468e9144fbf","source":{"kind":"arxiv","id":"2406.08466","version":3},"attestation_state":"computed","paper":{"title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Jingfeng Wu, Licong Lin, Peter L. Bartlett, Sham M. Kakade","submitted_at":"2024-06-12T17:53:29Z","abstract_excerpt":"Empirically, large-scale deep learning models often satisfy a neural scaling law: the test error of the trained model improves polynomially as the model size and data size grow. However, conventional wisdom suggests the test error consists of approximation, bias, and variance errors, where the variance error increases with model size. This disagrees with the general form of neural scaling laws, which predict that increasing model size monotonically improves performance.\n  We study the theory of scaling laws in an infinite dimensional linear regression setup. Specifically, we consider a model w"},"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":"2406.08466","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T17:53:29Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"3faf975edd35ca73cd5556289bfca77529619e3841b56f275657d76b9bc483d6","abstract_canon_sha256":"e0084418f0acd53d47b3408f16c8d4b9c6efff1118cfb77d5e02ccc7ad4b6c12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:38.986079Z","signature_b64":"YxRPRK3QhMS+WM9FKuZhFTa0rw5diRsrYwB3QPF11rOyAUNoIMlnL254M3LaXPwPf+k8x5zEwj18Ef4ei7qoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ae626bc307cd9903bd4e55a943229210daa55f54ac289e310f77468e9144fbf","last_reissued_at":"2026-07-05T11:18:38.985582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:38.985582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Jingfeng Wu, Licong Lin, Peter L. Bartlett, Sham M. Kakade","submitted_at":"2024-06-12T17:53:29Z","abstract_excerpt":"Empirically, large-scale deep learning models often satisfy a neural scaling law: the test error of the trained model improves polynomially as the model size and data size grow. However, conventional wisdom suggests the test error consists of approximation, bias, and variance errors, where the variance error increases with model size. This disagrees with the general form of neural scaling laws, which predict that increasing model size monotonically improves performance.\n  We study the theory of scaling laws in an infinite dimensional linear regression setup. Specifically, we consider a model w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08466","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/2406.08466/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":"2406.08466","created_at":"2026-07-05T11:18:38.985644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08466v3","created_at":"2026-07-05T11:18:38.985644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08466","created_at":"2026-07-05T11:18:38.985644+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLTCNPBQPTMZ","created_at":"2026-07-05T11:18:38.985644+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLTCNPBQPTMZAO6U","created_at":"2026-07-05T11:18:38.985644+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLTCNPBQ","created_at":"2026-07-05T11:18:38.985644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.05074","citing_title":"Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26554","citing_title":"Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE","json":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE.json","graph_json":"https://pith.science/api/pith-number/LLTCNPBQPTMZAO6U4VNJIMRJEE/graph.json","events_json":"https://pith.science/api/pith-number/LLTCNPBQPTMZAO6U4VNJIMRJEE/events.json","paper":"https://pith.science/paper/LLTCNPBQ"},"agent_actions":{"view_html":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE","download_json":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE.json","view_paper":"https://pith.science/paper/LLTCNPBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08466&json=true","fetch_graph":"https://pith.science/api/pith-number/LLTCNPBQPTMZAO6U4VNJIMRJEE/graph.json","fetch_events":"https://pith.science/api/pith-number/LLTCNPBQPTMZAO6U4VNJIMRJEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE/action/storage_attestation","attest_author":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE/action/author_attestation","sign_citation":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE/action/citation_signature","submit_replication":"https://pith.science/pith/LLTCNPBQPTMZAO6U4VNJIMRJEE/action/replication_record"}},"created_at":"2026-07-05T11:18:38.985644+00:00","updated_at":"2026-07-05T11:18:38.985644+00:00"}