{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3E5UYKBLZHBZRURQR6V6F3LR7I","short_pith_number":"pith:3E5UYKBL","schema_version":"1.0","canonical_sha256":"d93b4c282bc9c398d2308fabe2ed71fa135c9b5def4d862449d9fb391fb2bff0","source":{"kind":"arxiv","id":"2105.13244","version":2},"attestation_state":"computed","paper":{"title":"Using Early-Learning Regularization to Classify Real-World Noisy Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessio Galatolo, Alfred Nilsson, Roderick Karlemstrand, Yineng Wang","submitted_at":"2021-05-27T15:41:45Z","abstract_excerpt":"The memorization problem is well-known in the field of computer vision. Liu et al. propose a technique called Early-Learning Regularization, which improves accuracy on the CIFAR datasets when label noise is present. This project replicates their experiments and investigates the performance on a real-world dataset with intrinsic noise. Results show that their experimental results are consistent. We also explore Sharpness-Aware Minimization in addition to SGD and observed a further 14.6 percentage points improvement. Future work includes using all 6 million images and manually clean a fraction o"},"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":"2105.13244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-27T15:41:45Z","cross_cats_sorted":[],"title_canon_sha256":"fbbbbc1092f0c2d93aa4d00421370c3fbfd616b849f0e3d2b53007f01ca2fc26","abstract_canon_sha256":"89b35ee4ef3ddcf98b46a415dc872c941fe8bd7493d75c4c963274e8861418b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:59.464548Z","signature_b64":"Pj2SvopRvhJi1GWUfHd5JmR9I1Hun3anAiMEkPhl7TmZt2XU8knMMmsltmdbSvnQTFtG/S8K4UxVJU3HRDTRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d93b4c282bc9c398d2308fabe2ed71fa135c9b5def4d862449d9fb391fb2bff0","last_reissued_at":"2026-07-05T02:44:59.464026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:59.464026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Early-Learning Regularization to Classify Real-World Noisy Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessio Galatolo, Alfred Nilsson, Roderick Karlemstrand, Yineng Wang","submitted_at":"2021-05-27T15:41:45Z","abstract_excerpt":"The memorization problem is well-known in the field of computer vision. Liu et al. propose a technique called Early-Learning Regularization, which improves accuracy on the CIFAR datasets when label noise is present. This project replicates their experiments and investigates the performance on a real-world dataset with intrinsic noise. Results show that their experimental results are consistent. We also explore Sharpness-Aware Minimization in addition to SGD and observed a further 14.6 percentage points improvement. Future work includes using all 6 million images and manually clean a fraction o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13244","kind":"arxiv","version":2},"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/2105.13244/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":"2105.13244","created_at":"2026-07-05T02:44:59.464089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13244v2","created_at":"2026-07-05T02:44:59.464089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13244","created_at":"2026-07-05T02:44:59.464089+00:00"},{"alias_kind":"pith_short_12","alias_value":"3E5UYKBLZHBZ","created_at":"2026-07-05T02:44:59.464089+00:00"},{"alias_kind":"pith_short_16","alias_value":"3E5UYKBLZHBZRURQ","created_at":"2026-07-05T02:44:59.464089+00:00"},{"alias_kind":"pith_short_8","alias_value":"3E5UYKBL","created_at":"2026-07-05T02:44:59.464089+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/3E5UYKBLZHBZRURQR6V6F3LR7I","json":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I.json","graph_json":"https://pith.science/api/pith-number/3E5UYKBLZHBZRURQR6V6F3LR7I/graph.json","events_json":"https://pith.science/api/pith-number/3E5UYKBLZHBZRURQR6V6F3LR7I/events.json","paper":"https://pith.science/paper/3E5UYKBL"},"agent_actions":{"view_html":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I","download_json":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I.json","view_paper":"https://pith.science/paper/3E5UYKBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13244&json=true","fetch_graph":"https://pith.science/api/pith-number/3E5UYKBLZHBZRURQR6V6F3LR7I/graph.json","fetch_events":"https://pith.science/api/pith-number/3E5UYKBLZHBZRURQR6V6F3LR7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I/action/storage_attestation","attest_author":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I/action/author_attestation","sign_citation":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I/action/citation_signature","submit_replication":"https://pith.science/pith/3E5UYKBLZHBZRURQR6V6F3LR7I/action/replication_record"}},"created_at":"2026-07-05T02:44:59.464089+00:00","updated_at":"2026-07-05T02:44:59.464089+00:00"}