{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ETFSHERQ6EHJ4BE62LI2SMVFET","short_pith_number":"pith:ETFSHERQ","schema_version":"1.0","canonical_sha256":"24cb239230f10e9e049ed2d1a932a524cece6cc0403140d10ea53d5b5ed1f128","source":{"kind":"arxiv","id":"2412.10741","version":2},"attestation_state":"computed","paper":{"title":"RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chixuan Wei, Haorong Han, Jidong Yuan, Zhongyang Yu","submitted_at":"2024-12-14T08:22:49Z","abstract_excerpt":"Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup for consistency regularization may degrade SSL performance by compromising the purity of artificial labels. Moreover, most pseudo-labeling based methods utilize thresholding strategy to exclude low-confidence data, aiming to mitigate confirmation bias; however, this approach limits the utility of unlabeled samples. To address these challenges, we propose Re"},"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":"2412.10741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T08:22:49Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"1b89518059a680e6523b283c55205ab10a74a4dc5798c3acc04650ea4d3f46bc","abstract_canon_sha256":"0459dfa6a0266f379fac102ece8929882a63207ce547b1b2fdb302a94752836d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:10.991712Z","signature_b64":"xxiIPAvRlBF6113vEPFeIhnVqrV8ZDECKV0lLWJA5A9nW8RzOu6nfGVLzqcQLCaJnkQIVYOTfQjAufBcPlW4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24cb239230f10e9e049ed2d1a932a524cece6cc0403140d10ea53d5b5ed1f128","last_reissued_at":"2026-07-05T10:50:10.991217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:10.991217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chixuan Wei, Haorong Han, Jidong Yuan, Zhongyang Yu","submitted_at":"2024-12-14T08:22:49Z","abstract_excerpt":"Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup for consistency regularization may degrade SSL performance by compromising the purity of artificial labels. Moreover, most pseudo-labeling based methods utilize thresholding strategy to exclude low-confidence data, aiming to mitigate confirmation bias; however, this approach limits the utility of unlabeled samples. To address these challenges, we propose Re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10741","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/2412.10741/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":"2412.10741","created_at":"2026-07-05T10:50:10.991283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10741v2","created_at":"2026-07-05T10:50:10.991283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10741","created_at":"2026-07-05T10:50:10.991283+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETFSHERQ6EHJ","created_at":"2026-07-05T10:50:10.991283+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETFSHERQ6EHJ4BE6","created_at":"2026-07-05T10:50:10.991283+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETFSHERQ","created_at":"2026-07-05T10:50:10.991283+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/ETFSHERQ6EHJ4BE62LI2SMVFET","json":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET.json","graph_json":"https://pith.science/api/pith-number/ETFSHERQ6EHJ4BE62LI2SMVFET/graph.json","events_json":"https://pith.science/api/pith-number/ETFSHERQ6EHJ4BE62LI2SMVFET/events.json","paper":"https://pith.science/paper/ETFSHERQ"},"agent_actions":{"view_html":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET","download_json":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET.json","view_paper":"https://pith.science/paper/ETFSHERQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10741&json=true","fetch_graph":"https://pith.science/api/pith-number/ETFSHERQ6EHJ4BE62LI2SMVFET/graph.json","fetch_events":"https://pith.science/api/pith-number/ETFSHERQ6EHJ4BE62LI2SMVFET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET/action/storage_attestation","attest_author":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET/action/author_attestation","sign_citation":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET/action/citation_signature","submit_replication":"https://pith.science/pith/ETFSHERQ6EHJ4BE62LI2SMVFET/action/replication_record"}},"created_at":"2026-07-05T10:50:10.991283+00:00","updated_at":"2026-07-05T10:50:10.991283+00:00"}