{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RFV4GZTOPKD67RZ6BS4RDVTNUW","short_pith_number":"pith:RFV4GZTO","schema_version":"1.0","canonical_sha256":"896bc3666e7a87efc73e0cb911d66da5a8270039b644f9e6ae197c883b24b0c9","source":{"kind":"arxiv","id":"2503.19605","version":5},"attestation_state":"computed","paper":{"title":"Lean Formalization of Generalization Error Bound by Rademacher Complexity and Dudley's Entropy Integral","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Kazumi Kasaura, Kei Tsukamoto, Naoto Onda, Sho Sonoda, Yuma Mizuno","submitted_at":"2025-03-25T12:40:43Z","abstract_excerpt":"Understanding and certifying the generalization performance of machine learning algorithms -- i.e. obtaining theoretical estimates of the test error from the training error -- is a central theme of statistical learning theory. Among the many complexity measures used to derive such guarantees, Rademacher complexity yields sharp, data-dependent bounds that apply well beyond classical VC-dimension theory. In this study, we formalize the generalization error bound by Rademacher complexity in Lean 4, building on measure-theoretic probability theory available in the Mathlib library. Our development "},"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":"2503.19605","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T12:40:43Z","cross_cats_sorted":["cs.CL","math.ST","stat.TH"],"title_canon_sha256":"d35555a01dadbf5203186b42860aa7b54dc438be7eece78e350244965fa049f3","abstract_canon_sha256":"983d9316901d2b7722cf0f6170f051edacb1533aa8dc66d0a22369bad1ebbf03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:49.615719Z","signature_b64":"KI0QZEWrhYXSyE/rCrqXo5tQgpYBUgOtd3XdW0eMhgPENlgcT2QJaHWMPMRoHN9xb85oSZStYQY8rBjvY8Y4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"896bc3666e7a87efc73e0cb911d66da5a8270039b644f9e6ae197c883b24b0c9","last_reissued_at":"2026-05-26T02:03:49.614350Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:49.614350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lean Formalization of Generalization Error Bound by Rademacher Complexity and Dudley's Entropy Integral","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Kazumi Kasaura, Kei Tsukamoto, Naoto Onda, Sho Sonoda, Yuma Mizuno","submitted_at":"2025-03-25T12:40:43Z","abstract_excerpt":"Understanding and certifying the generalization performance of machine learning algorithms -- i.e. obtaining theoretical estimates of the test error from the training error -- is a central theme of statistical learning theory. Among the many complexity measures used to derive such guarantees, Rademacher complexity yields sharp, data-dependent bounds that apply well beyond classical VC-dimension theory. In this study, we formalize the generalization error bound by Rademacher complexity in Lean 4, building on measure-theoretic probability theory available in the Mathlib library. Our development "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19605","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/2503.19605/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":"2503.19605","created_at":"2026-05-26T02:03:49.614497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19605v5","created_at":"2026-05-26T02:03:49.614497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19605","created_at":"2026-05-26T02:03:49.614497+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFV4GZTOPKD6","created_at":"2026-05-26T02:03:49.614497+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFV4GZTOPKD67RZ6","created_at":"2026-05-26T02:03:49.614497+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFV4GZTO","created_at":"2026-05-26T02:03:49.614497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW","json":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW.json","graph_json":"https://pith.science/api/pith-number/RFV4GZTOPKD67RZ6BS4RDVTNUW/graph.json","events_json":"https://pith.science/api/pith-number/RFV4GZTOPKD67RZ6BS4RDVTNUW/events.json","paper":"https://pith.science/paper/RFV4GZTO"},"agent_actions":{"view_html":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW","download_json":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW.json","view_paper":"https://pith.science/paper/RFV4GZTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19605&json=true","fetch_graph":"https://pith.science/api/pith-number/RFV4GZTOPKD67RZ6BS4RDVTNUW/graph.json","fetch_events":"https://pith.science/api/pith-number/RFV4GZTOPKD67RZ6BS4RDVTNUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW/action/storage_attestation","attest_author":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW/action/author_attestation","sign_citation":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW/action/citation_signature","submit_replication":"https://pith.science/pith/RFV4GZTOPKD67RZ6BS4RDVTNUW/action/replication_record"}},"created_at":"2026-05-26T02:03:49.614497+00:00","updated_at":"2026-05-26T02:03:49.614497+00:00"}