{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4JBGSEVCLOUZLQPI56E7HRHAZ7","short_pith_number":"pith:4JBGSEVC","schema_version":"1.0","canonical_sha256":"e2426912a25ba995c1e8ef89f3c4e0cfc006ac86d0f8a61d12a55a1e5bda2f37","source":{"kind":"arxiv","id":"2205.01156","version":1},"attestation_state":"computed","paper":{"title":"SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wenbo He, Yangdi Lu","submitted_at":"2022-05-02T18:42:47Z","abstract_excerpt":"Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct noisy labels and refine the model. We look deeper into the memorization behavior in training with noisy labels and observe that the network outputs are reliable in the early stage. To retain this reliable knowledge, SELC uses ensemble predictions formed by an exponential moving average of network outputs to update the original noisy labels. We show that training"},"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":"2205.01156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-02T18:42:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"703902df3dac67a4fe1a6fe3bcfadc52d4346cb419913a605ddc2fb688255f10","abstract_canon_sha256":"fd99a5230f88fc641de7efa357f459f64b584329f07522786557eb46d8664fca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:01.408758Z","signature_b64":"BxaFDvPsZeWR77sAfTfxsuOSK2YdkGgFoJJhH29yZKzLRHyRINyburAVGnxVwJXd82VOfsJCgKhKqjPz/GGACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2426912a25ba995c1e8ef89f3c4e0cfc006ac86d0f8a61d12a55a1e5bda2f37","last_reissued_at":"2026-07-05T04:20:01.408304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:01.408304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wenbo He, Yangdi Lu","submitted_at":"2022-05-02T18:42:47Z","abstract_excerpt":"Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct noisy labels and refine the model. We look deeper into the memorization behavior in training with noisy labels and observe that the network outputs are reliable in the early stage. To retain this reliable knowledge, SELC uses ensemble predictions formed by an exponential moving average of network outputs to update the original noisy labels. We show that training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01156","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/2205.01156/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":"2205.01156","created_at":"2026-07-05T04:20:01.408379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.01156v1","created_at":"2026-07-05T04:20:01.408379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01156","created_at":"2026-07-05T04:20:01.408379+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JBGSEVCLOUZ","created_at":"2026-07-05T04:20:01.408379+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JBGSEVCLOUZLQPI","created_at":"2026-07-05T04:20:01.408379+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JBGSEVC","created_at":"2026-07-05T04:20:01.408379+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/4JBGSEVCLOUZLQPI56E7HRHAZ7","json":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7.json","graph_json":"https://pith.science/api/pith-number/4JBGSEVCLOUZLQPI56E7HRHAZ7/graph.json","events_json":"https://pith.science/api/pith-number/4JBGSEVCLOUZLQPI56E7HRHAZ7/events.json","paper":"https://pith.science/paper/4JBGSEVC"},"agent_actions":{"view_html":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7","download_json":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7.json","view_paper":"https://pith.science/paper/4JBGSEVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.01156&json=true","fetch_graph":"https://pith.science/api/pith-number/4JBGSEVCLOUZLQPI56E7HRHAZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/4JBGSEVCLOUZLQPI56E7HRHAZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7/action/storage_attestation","attest_author":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7/action/author_attestation","sign_citation":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7/action/citation_signature","submit_replication":"https://pith.science/pith/4JBGSEVCLOUZLQPI56E7HRHAZ7/action/replication_record"}},"created_at":"2026-07-05T04:20:01.408379+00:00","updated_at":"2026-07-05T04:20:01.408379+00:00"}