{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7WLTOY2JGANG7FKWQBO33BAGS3","short_pith_number":"pith:7WLTOY2J","schema_version":"1.0","canonical_sha256":"fd97376349301a6f9556805dbd840696c22526df9fbd85e1444ee58204e22ddd","source":{"kind":"arxiv","id":"1905.11368","version":4},"attestation_state":"computed","paper":{"title":"Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dingli Yu, Wei Hu, Zhiyuan Li","submitted_at":"2019-05-27T17:52:28Z","abstract_excerpt":"Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization when mislabeled training examples are present. On the other hand, simple regularization methods like early-stopping can often achieve highly nontrivial performance on clean test data in these scenarios, a phenomenon not theoretically understood. This paper proposes and analyzes two simple and intuitive regularization methods: (i) regularization by the distance between the network parameters to initialization, and (ii) a"},"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":"1905.11368","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T17:52:28Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"76f1e1ba79754d2bf3959c87f08c44452ffec1f353c79a324a2b2fb594d682a4","abstract_canon_sha256":"8316a0d67a2819eb1409aefcbde7a6ac390b4e025c5a0d562ea1dc078c89373f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:54.016999Z","signature_b64":"KaRm0oMWpXyKhAaXTVGgGkQUl9yWA+RDiXRa6/eC1IlWZ9LoXqwSqICt7Xe+c7uV+uNosyMyfc45vHORTrPXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd97376349301a6f9556805dbd840696c22526df9fbd85e1444ee58204e22ddd","last_reissued_at":"2026-07-05T01:39:54.016656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:54.016656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dingli Yu, Wei Hu, Zhiyuan Li","submitted_at":"2019-05-27T17:52:28Z","abstract_excerpt":"Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization when mislabeled training examples are present. On the other hand, simple regularization methods like early-stopping can often achieve highly nontrivial performance on clean test data in these scenarios, a phenomenon not theoretically understood. This paper proposes and analyzes two simple and intuitive regularization methods: (i) regularization by the distance between the network parameters to initialization, and (ii) a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11368","kind":"arxiv","version":4},"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/1905.11368/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":"1905.11368","created_at":"2026-07-05T01:39:54.016711+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11368v4","created_at":"2026-07-05T01:39:54.016711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11368","created_at":"2026-07-05T01:39:54.016711+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WLTOY2JGANG","created_at":"2026-07-05T01:39:54.016711+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WLTOY2JGANG7FKW","created_at":"2026-07-05T01:39:54.016711+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WLTOY2J","created_at":"2026-07-05T01:39:54.016711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03560","citing_title":"Simplifying Graph Kernels for Efficient","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3","json":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3.json","graph_json":"https://pith.science/api/pith-number/7WLTOY2JGANG7FKWQBO33BAGS3/graph.json","events_json":"https://pith.science/api/pith-number/7WLTOY2JGANG7FKWQBO33BAGS3/events.json","paper":"https://pith.science/paper/7WLTOY2J"},"agent_actions":{"view_html":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3","download_json":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3.json","view_paper":"https://pith.science/paper/7WLTOY2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11368&json=true","fetch_graph":"https://pith.science/api/pith-number/7WLTOY2JGANG7FKWQBO33BAGS3/graph.json","fetch_events":"https://pith.science/api/pith-number/7WLTOY2JGANG7FKWQBO33BAGS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3/action/storage_attestation","attest_author":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3/action/author_attestation","sign_citation":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3/action/citation_signature","submit_replication":"https://pith.science/pith/7WLTOY2JGANG7FKWQBO33BAGS3/action/replication_record"}},"created_at":"2026-07-05T01:39:54.016711+00:00","updated_at":"2026-07-05T01:39:54.016711+00:00"}