{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A6F5CYUMZ7XHP4NI23FIXL6KI3","short_pith_number":"pith:A6F5CYUM","schema_version":"1.0","canonical_sha256":"078bd1628ccfee77f1a8d6ca8bafca46c0b56f48ff5797423eefb5decfa579ac","source":{"kind":"arxiv","id":"2108.11569","version":1},"attestation_state":"computed","paper":{"title":"Robust Long-Tailed Learning under Label Noise","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiang-Xin Shi, Tong Wei, Wei-Wei Tu, Yu-Feng Li","submitted_at":"2021-08-26T03:45:00Z","abstract_excerpt":"Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without considering the prevailing noise in the training dataset. To move long-tailed learning towards more realistic scenarios, this work investigates the label noise problem under long-tailed label distribution. We first observe the negative impact of noisy labels on the performance of existing methods, revealing the intrinsic challenges of this problem. As the most commonly used approach to cope with noisy labels in previous lite"},"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":"2108.11569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-26T03:45:00Z","cross_cats_sorted":[],"title_canon_sha256":"2288bd4c5d8a18798528138993da8a340e7b68c8b8c14f150b57bf5a09194d1c","abstract_canon_sha256":"1255792d9d3b0bb6e99e78ba1fe8dcbe224e936eb7d5a6b112e7b54de48f3a4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:58.531142Z","signature_b64":"+YcrtAnvCXW3tOtMwsolhrISzF2mq5YINVfK4R4CEpZtuLQk4V8dvNGDPwt+QnUDnlLgkDqLqdvcw9Hz6KFdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"078bd1628ccfee77f1a8d6ca8bafca46c0b56f48ff5797423eefb5decfa579ac","last_reissued_at":"2026-07-05T03:08:58.530663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:58.530663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Long-Tailed Learning under Label Noise","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiang-Xin Shi, Tong Wei, Wei-Wei Tu, Yu-Feng Li","submitted_at":"2021-08-26T03:45:00Z","abstract_excerpt":"Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without considering the prevailing noise in the training dataset. To move long-tailed learning towards more realistic scenarios, this work investigates the label noise problem under long-tailed label distribution. We first observe the negative impact of noisy labels on the performance of existing methods, revealing the intrinsic challenges of this problem. As the most commonly used approach to cope with noisy labels in previous lite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11569","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/2108.11569/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":"2108.11569","created_at":"2026-07-05T03:08:58.530723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.11569v1","created_at":"2026-07-05T03:08:58.530723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11569","created_at":"2026-07-05T03:08:58.530723+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6F5CYUMZ7XH","created_at":"2026-07-05T03:08:58.530723+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6F5CYUMZ7XHP4NI","created_at":"2026-07-05T03:08:58.530723+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6F5CYUM","created_at":"2026-07-05T03:08:58.530723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.13187","citing_title":"Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3","json":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3.json","graph_json":"https://pith.science/api/pith-number/A6F5CYUMZ7XHP4NI23FIXL6KI3/graph.json","events_json":"https://pith.science/api/pith-number/A6F5CYUMZ7XHP4NI23FIXL6KI3/events.json","paper":"https://pith.science/paper/A6F5CYUM"},"agent_actions":{"view_html":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3","download_json":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3.json","view_paper":"https://pith.science/paper/A6F5CYUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.11569&json=true","fetch_graph":"https://pith.science/api/pith-number/A6F5CYUMZ7XHP4NI23FIXL6KI3/graph.json","fetch_events":"https://pith.science/api/pith-number/A6F5CYUMZ7XHP4NI23FIXL6KI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3/action/storage_attestation","attest_author":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3/action/author_attestation","sign_citation":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3/action/citation_signature","submit_replication":"https://pith.science/pith/A6F5CYUMZ7XHP4NI23FIXL6KI3/action/replication_record"}},"created_at":"2026-07-05T03:08:58.530723+00:00","updated_at":"2026-07-05T03:08:58.530723+00:00"}