{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4CJUMB46OY4FNGQYXF7CWFF74S","short_pith_number":"pith:4CJUMB46","schema_version":"1.0","canonical_sha256":"e09346079e7638569a18b97e2b14bfe4a262a162007dd1cee29807d8123dfe42","source":{"kind":"arxiv","id":"2011.07451","version":1},"attestation_state":"computed","paper":{"title":"Coresets for Robust Training of Neural Networks against Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baharan Mirzasoleiman, Jure Leskovec, Kaidi Cao","submitted_at":"2020-11-15T04:58:11Z","abstract_excerpt":"Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the neural networks trained with noisy labels. Here we propose a novel approach with strong theoretical guarantees for robust training of deep networks trained with noisy labels. The key idea behind our method is to select weighted subsets (coresets) of clean data points that provide an approximately low-rank Jacobian matrix. We then prove that gradient descent "},"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":"2011.07451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-15T04:58:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a3c5c08420de1b5b2c4a3b369ed4f5d67b19ef86ee22f8e29909fe25e41c42e0","abstract_canon_sha256":"131f02a0a6ca431e5b80aace42370ef8e4a2ce0aaf95a59046b1fbaa458bf03e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:49.904266Z","signature_b64":"zCiluePBwkDJixp4e8NnABc0vs/bxVVV7QVIdaNhvPy7iDCLnpFPZnKkC+pWeKKQsNM8h5FYmvjCzKE6GknrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e09346079e7638569a18b97e2b14bfe4a262a162007dd1cee29807d8123dfe42","last_reissued_at":"2026-07-05T01:51:49.903850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:49.903850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coresets for Robust Training of Neural Networks against Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baharan Mirzasoleiman, Jure Leskovec, Kaidi Cao","submitted_at":"2020-11-15T04:58:11Z","abstract_excerpt":"Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the neural networks trained with noisy labels. Here we propose a novel approach with strong theoretical guarantees for robust training of deep networks trained with noisy labels. The key idea behind our method is to select weighted subsets (coresets) of clean data points that provide an approximately low-rank Jacobian matrix. We then prove that gradient descent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07451","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/2011.07451/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":"2011.07451","created_at":"2026-07-05T01:51:49.903906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.07451v1","created_at":"2026-07-05T01:51:49.903906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07451","created_at":"2026-07-05T01:51:49.903906+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CJUMB46OY4F","created_at":"2026-07-05T01:51:49.903906+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CJUMB46OY4FNGQY","created_at":"2026-07-05T01:51:49.903906+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CJUMB46","created_at":"2026-07-05T01:51:49.903906+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/4CJUMB46OY4FNGQYXF7CWFF74S","json":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S.json","graph_json":"https://pith.science/api/pith-number/4CJUMB46OY4FNGQYXF7CWFF74S/graph.json","events_json":"https://pith.science/api/pith-number/4CJUMB46OY4FNGQYXF7CWFF74S/events.json","paper":"https://pith.science/paper/4CJUMB46"},"agent_actions":{"view_html":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S","download_json":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S.json","view_paper":"https://pith.science/paper/4CJUMB46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.07451&json=true","fetch_graph":"https://pith.science/api/pith-number/4CJUMB46OY4FNGQYXF7CWFF74S/graph.json","fetch_events":"https://pith.science/api/pith-number/4CJUMB46OY4FNGQYXF7CWFF74S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S/action/storage_attestation","attest_author":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S/action/author_attestation","sign_citation":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S/action/citation_signature","submit_replication":"https://pith.science/pith/4CJUMB46OY4FNGQYXF7CWFF74S/action/replication_record"}},"created_at":"2026-07-05T01:51:49.903906+00:00","updated_at":"2026-07-05T01:51:49.903906+00:00"}