{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JVBF2HM5HDSXGTC2Q6VAF3SFSS","short_pith_number":"pith:JVBF2HM5","schema_version":"1.0","canonical_sha256":"4d425d1d9d38e5734c5a87aa02ee4594a21f7cde0a67ad092bceee2c77c0d3cc","source":{"kind":"arxiv","id":"2002.02561","version":7},"attestation_state":"computed","paper":{"title":"Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan","submitted_at":"2020-02-07T00:03:40Z","abstract_excerpt":"We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples using theoretical methods from Gaussian processes and statistical physics. Our expressions apply to wide neural networks due to an equivalence between training them and kernel regression with the Neural Tangent Kernel (NTK). By computing the decomposition of the total generalization error due to different spectral components of the kernel, we identify a new spectral principle: as the size of the training set grows, kernel machines and neural networks fit succ"},"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":"2002.02561","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T00:03:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a3b718d7577bbe06d3c680c630960a3a4445443d0ab873cf7306c93048212ab4","abstract_canon_sha256":"3dbf352d2425804736df6a0beed1e58ab4d396d94d10ae46bf73f32e3b594fcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:14.771310Z","signature_b64":"E7mxcq/qchKLMSD/pq0sJB4m309pNJjDrz4i0pD6Qta2xOi0DZoZ9VACI0z8PjiYe+0h77zLkrcf9EvTyrtYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d425d1d9d38e5734c5a87aa02ee4594a21f7cde0a67ad092bceee2c77c0d3cc","last_reissued_at":"2026-07-05T02:18:14.770800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:14.770800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan","submitted_at":"2020-02-07T00:03:40Z","abstract_excerpt":"We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples using theoretical methods from Gaussian processes and statistical physics. Our expressions apply to wide neural networks due to an equivalence between training them and kernel regression with the Neural Tangent Kernel (NTK). By computing the decomposition of the total generalization error due to different spectral components of the kernel, we identify a new spectral principle: as the size of the training set grows, kernel machines and neural networks fit succ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02561","kind":"arxiv","version":7},"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/2002.02561/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":"2002.02561","created_at":"2026-07-05T02:18:14.770875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02561v7","created_at":"2026-07-05T02:18:14.770875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02561","created_at":"2026-07-05T02:18:14.770875+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVBF2HM5HDSX","created_at":"2026-07-05T02:18:14.770875+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVBF2HM5HDSXGTC2","created_at":"2026-07-05T02:18:14.770875+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVBF2HM5","created_at":"2026-07-05T02:18:14.770875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06949","citing_title":"SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11317","citing_title":"Lectures on Semiclassical Methods for Composite Operators","ref_index":121,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS","json":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS.json","graph_json":"https://pith.science/api/pith-number/JVBF2HM5HDSXGTC2Q6VAF3SFSS/graph.json","events_json":"https://pith.science/api/pith-number/JVBF2HM5HDSXGTC2Q6VAF3SFSS/events.json","paper":"https://pith.science/paper/JVBF2HM5"},"agent_actions":{"view_html":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS","download_json":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS.json","view_paper":"https://pith.science/paper/JVBF2HM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02561&json=true","fetch_graph":"https://pith.science/api/pith-number/JVBF2HM5HDSXGTC2Q6VAF3SFSS/graph.json","fetch_events":"https://pith.science/api/pith-number/JVBF2HM5HDSXGTC2Q6VAF3SFSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS/action/storage_attestation","attest_author":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS/action/author_attestation","sign_citation":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS/action/citation_signature","submit_replication":"https://pith.science/pith/JVBF2HM5HDSXGTC2Q6VAF3SFSS/action/replication_record"}},"created_at":"2026-07-05T02:18:14.770875+00:00","updated_at":"2026-07-05T02:18:14.770875+00:00"}