{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DMGHK65GBVNCGI5TAFXOZ5GXLF","short_pith_number":"pith:DMGHK65G","schema_version":"1.0","canonical_sha256":"1b0c757ba60d5a2323b3016eecf4d75949755bd309b6627373226f4b199d5098","source":{"kind":"arxiv","id":"2210.04525","version":2},"attestation_state":"computed","paper":{"title":"SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenchen Dai, Dan Qiao, Juntao Li, Min Zhang, Qiang Chen, Wenliang Chen, Yuyang Ding","submitted_at":"2022-10-10T09:46:40Z","abstract_excerpt":"The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise inevitably exists in training data, damaging the effectiveness, robustness, and generalization of the models constructed on such data. Recently, remarkable achievements have been made to mitigate this dilemma in visual data, while only a few explore textual data. To fill this gap, we present SelfMix, a simple yet effective method, to handle label noise in t"},"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":"2210.04525","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T09:46:40Z","cross_cats_sorted":[],"title_canon_sha256":"54a756c686ae61a504aa25f12a35a4e2633d2edeb43186f4299e5224809cc63c","abstract_canon_sha256":"0e3e575ebfe33dd34cd203231820413fced3aa4c0fcaf76f3cbd521bf3c4f448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:15.365065Z","signature_b64":"9Ho9SbLUOyAjF1s1sx93wYRhwGYFWexEoP5hyPzrTu5Sh2Pm1aY+Mvf+67KiTxiSfosOKE6ef/zJualXvvPkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b0c757ba60d5a2323b3016eecf4d75949755bd309b6627373226f4b199d5098","last_reissued_at":"2026-07-05T05:06:15.364556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:15.364556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenchen Dai, Dan Qiao, Juntao Li, Min Zhang, Qiang Chen, Wenliang Chen, Yuyang Ding","submitted_at":"2022-10-10T09:46:40Z","abstract_excerpt":"The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise inevitably exists in training data, damaging the effectiveness, robustness, and generalization of the models constructed on such data. Recently, remarkable achievements have been made to mitigate this dilemma in visual data, while only a few explore textual data. To fill this gap, we present SelfMix, a simple yet effective method, to handle label noise in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04525","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/2210.04525/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":"2210.04525","created_at":"2026-07-05T05:06:15.364622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04525v2","created_at":"2026-07-05T05:06:15.364622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04525","created_at":"2026-07-05T05:06:15.364622+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMGHK65GBVNC","created_at":"2026-07-05T05:06:15.364622+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMGHK65GBVNCGI5T","created_at":"2026-07-05T05:06:15.364622+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMGHK65G","created_at":"2026-07-05T05:06:15.364622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14922","citing_title":"RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF","json":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF.json","graph_json":"https://pith.science/api/pith-number/DMGHK65GBVNCGI5TAFXOZ5GXLF/graph.json","events_json":"https://pith.science/api/pith-number/DMGHK65GBVNCGI5TAFXOZ5GXLF/events.json","paper":"https://pith.science/paper/DMGHK65G"},"agent_actions":{"view_html":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF","download_json":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF.json","view_paper":"https://pith.science/paper/DMGHK65G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04525&json=true","fetch_graph":"https://pith.science/api/pith-number/DMGHK65GBVNCGI5TAFXOZ5GXLF/graph.json","fetch_events":"https://pith.science/api/pith-number/DMGHK65GBVNCGI5TAFXOZ5GXLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF/action/storage_attestation","attest_author":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF/action/author_attestation","sign_citation":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF/action/citation_signature","submit_replication":"https://pith.science/pith/DMGHK65GBVNCGI5TAFXOZ5GXLF/action/replication_record"}},"created_at":"2026-07-05T05:06:15.364622+00:00","updated_at":"2026-07-05T05:06:15.364622+00:00"}