{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AM5ADYGNVHJ7TDA5GD33JYQWQY","short_pith_number":"pith:AM5ADYGN","schema_version":"1.0","canonical_sha256":"033a01e0cda9d3f98c1d30f7b4e216861fb245a182f89583b920ee6a91817926","source":{"kind":"arxiv","id":"2109.06099","version":3},"attestation_state":"computed","paper":{"title":"Uniform Generalization Bounds for Overparameterized Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Bernacchia, Da-shan Shiu, Jezabel Garcia, Michael Bromberg, Sattar Vakili","submitted_at":"2021-09-13T16:20:13Z","abstract_excerpt":"An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the classical statistical learning methods often result in vacuous generalization errors in the case of overparameterized neural networks. Adopting the recently developed Neural Tangent (NT) kernel theory, we prove uniform generalization bounds for overparameterized neural networks in kernel regimes, when the true data generating model belongs to the reproducing kernel Hilbert space (RKHS) corresponding to the NT kernel. Imp"},"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":"2109.06099","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-13T16:20:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"119f274cbd600deea5d41689befa9bf405d02ba7b9b582d029d74162cb95b8ab","abstract_canon_sha256":"005455ba38a991364681b5d98a02625ea9e6a85db276202b073ab34f1c0e6de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:33.616683Z","signature_b64":"AQ9EI6onnlfuvcDTa1VM607YnT+o9ZxDazhEwqIoirYvfO/39PMYcFh6IkL5zV4xiNrS88l6EbYOApi6RUKMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"033a01e0cda9d3f98c1d30f7b4e216861fb245a182f89583b920ee6a91817926","last_reissued_at":"2026-07-05T03:21:33.616246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:33.616246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uniform Generalization Bounds for Overparameterized Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Bernacchia, Da-shan Shiu, Jezabel Garcia, Michael Bromberg, Sattar Vakili","submitted_at":"2021-09-13T16:20:13Z","abstract_excerpt":"An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the classical statistical learning methods often result in vacuous generalization errors in the case of overparameterized neural networks. Adopting the recently developed Neural Tangent (NT) kernel theory, we prove uniform generalization bounds for overparameterized neural networks in kernel regimes, when the true data generating model belongs to the reproducing kernel Hilbert space (RKHS) corresponding to the NT kernel. Imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06099","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/2109.06099/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":"2109.06099","created_at":"2026-07-05T03:21:33.616301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06099v3","created_at":"2026-07-05T03:21:33.616301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06099","created_at":"2026-07-05T03:21:33.616301+00:00"},{"alias_kind":"pith_short_12","alias_value":"AM5ADYGNVHJ7","created_at":"2026-07-05T03:21:33.616301+00:00"},{"alias_kind":"pith_short_16","alias_value":"AM5ADYGNVHJ7TDA5","created_at":"2026-07-05T03:21:33.616301+00:00"},{"alias_kind":"pith_short_8","alias_value":"AM5ADYGN","created_at":"2026-07-05T03:21:33.616301+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/AM5ADYGNVHJ7TDA5GD33JYQWQY","json":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY.json","graph_json":"https://pith.science/api/pith-number/AM5ADYGNVHJ7TDA5GD33JYQWQY/graph.json","events_json":"https://pith.science/api/pith-number/AM5ADYGNVHJ7TDA5GD33JYQWQY/events.json","paper":"https://pith.science/paper/AM5ADYGN"},"agent_actions":{"view_html":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY","download_json":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY.json","view_paper":"https://pith.science/paper/AM5ADYGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06099&json=true","fetch_graph":"https://pith.science/api/pith-number/AM5ADYGNVHJ7TDA5GD33JYQWQY/graph.json","fetch_events":"https://pith.science/api/pith-number/AM5ADYGNVHJ7TDA5GD33JYQWQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY/action/storage_attestation","attest_author":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY/action/author_attestation","sign_citation":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY/action/citation_signature","submit_replication":"https://pith.science/pith/AM5ADYGNVHJ7TDA5GD33JYQWQY/action/replication_record"}},"created_at":"2026-07-05T03:21:33.616301+00:00","updated_at":"2026-07-05T03:21:33.616301+00:00"}