{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3A5GXXP5RK6NEYFE37OAZMR5Y","short_pith_number":"pith:Q3A5GXXP","schema_version":"1.0","canonical_sha256":"86c1d35eefec55e6930526fee06591ee0504efa5c3c8bd7907f9888460f9c605","source":{"kind":"arxiv","id":"2411.18806","version":1},"attestation_state":"computed","paper":{"title":"One-Step Early Stopping Strategy using Neural Tangent Kernel Theory and Rademacher Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Daniel Martin Xavier, Jawher Jerray, Laurent Fribourg, Ludovic Chamoin","submitted_at":"2024-11-27T23:22:28Z","abstract_excerpt":"The early stopping strategy consists in stopping the training process of a neural network (NN) on a set $S$ of input data before training error is minimal. The advantage is that the NN then retains good generalization properties, i.e. it gives good predictions on data outside $S$, and a good estimate of the statistical error (``population loss'') is obtained. We give here an analytical estimation of the optimal stopping time involving basically the initial training error vector and the eigenvalues of the ``neural tangent kernel''. This yields an upper bound on the population loss which is well"},"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":"2411.18806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-27T23:22:28Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"ffa7362346e1e7dd0022cc2cb5b513fdc9b4e4f34b5703f51ad762a7d65016ad","abstract_canon_sha256":"7d2b1c597e11d09c723e2322cf5b4f417a8e8b8fc1813152e6028271987623e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:51.884865Z","signature_b64":"DYxH75M3ZPc7urhQUqdCTjzyM7YNwoP845vHwFchhi/5zSeFDa8VhidzMNxJpDEpJEaOdZ4MeknfijCyk6ylCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c1d35eefec55e6930526fee06591ee0504efa5c3c8bd7907f9888460f9c605","last_reissued_at":"2026-07-05T09:41:51.884313Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:51.884313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Step Early Stopping Strategy using Neural Tangent Kernel Theory and Rademacher Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Daniel Martin Xavier, Jawher Jerray, Laurent Fribourg, Ludovic Chamoin","submitted_at":"2024-11-27T23:22:28Z","abstract_excerpt":"The early stopping strategy consists in stopping the training process of a neural network (NN) on a set $S$ of input data before training error is minimal. The advantage is that the NN then retains good generalization properties, i.e. it gives good predictions on data outside $S$, and a good estimate of the statistical error (``population loss'') is obtained. We give here an analytical estimation of the optimal stopping time involving basically the initial training error vector and the eigenvalues of the ``neural tangent kernel''. This yields an upper bound on the population loss which is well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18806","kind":"arxiv","version":1},"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/2411.18806/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":"2411.18806","created_at":"2026-07-05T09:41:51.884389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18806v1","created_at":"2026-07-05T09:41:51.884389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18806","created_at":"2026-07-05T09:41:51.884389+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3A5GXXP5RK6","created_at":"2026-07-05T09:41:51.884389+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3A5GXXP5RK6NEYF","created_at":"2026-07-05T09:41:51.884389+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3A5GXXP","created_at":"2026-07-05T09:41:51.884389+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/Q3A5GXXP5RK6NEYFE37OAZMR5Y","json":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y.json","graph_json":"https://pith.science/api/pith-number/Q3A5GXXP5RK6NEYFE37OAZMR5Y/graph.json","events_json":"https://pith.science/api/pith-number/Q3A5GXXP5RK6NEYFE37OAZMR5Y/events.json","paper":"https://pith.science/paper/Q3A5GXXP"},"agent_actions":{"view_html":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y","download_json":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y.json","view_paper":"https://pith.science/paper/Q3A5GXXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18806&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3A5GXXP5RK6NEYFE37OAZMR5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3A5GXXP5RK6NEYFE37OAZMR5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y/action/storage_attestation","attest_author":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y/action/author_attestation","sign_citation":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y/action/citation_signature","submit_replication":"https://pith.science/pith/Q3A5GXXP5RK6NEYFE37OAZMR5Y/action/replication_record"}},"created_at":"2026-07-05T09:41:51.884389+00:00","updated_at":"2026-07-05T09:41:51.884389+00:00"}