{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YUWQEDYRVDIZWDO4FLZO6V6LO3","short_pith_number":"pith:YUWQEDYR","schema_version":"1.0","canonical_sha256":"c52d020f11a8d19b0ddc2af2ef57cb76cca0a60da42b4532fd04baf70a8101fd","source":{"kind":"arxiv","id":"2209.12611","version":1},"attestation_state":"computed","paper":{"title":"MaxMatch: Semi-Supervised Learning with Worst-Case Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qianqian Xu, Qingming Huang, Xiaochun Cao, Xiaodan Li, Yangbangyan Jiang, Yuan He, Yuefeng Chen, Zhiyong Yang","submitted_at":"2022-09-26T12:04:49Z","abstract_excerpt":"In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-art models are based on the idea of pursuing consistent model predictions over unlabeled data toward the input noise, which is called consistency regularization. Nonetheless, there is a lack of theoretical insights into the reason behind its success. To bridge the gap between theoretical and practical results, we propose a worst-case consistency regularization technique for SSL in this paper. Specifically, we first pr"},"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":"2209.12611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T12:04:49Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"766fa0b81f06bac51daff2e737b1c0928287305ffeea57ee924fc7f9ea880f47","abstract_canon_sha256":"e11798b10b8b96e7e5f2cc03324ba98b3730f99ccd2387b3ec7dde50376aaea5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:54.232229Z","signature_b64":"iN98ebYsWvfeGaqj8LlfgSOcConjxeEZOEuKwFRWV4oC3RRqeSfC+Xjlv64X6caGtpsSTBkV9UM24BquC6azCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c52d020f11a8d19b0ddc2af2ef57cb76cca0a60da42b4532fd04baf70a8101fd","last_reissued_at":"2026-07-05T05:00:54.231837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:54.231837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaxMatch: Semi-Supervised Learning with Worst-Case Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qianqian Xu, Qingming Huang, Xiaochun Cao, Xiaodan Li, Yangbangyan Jiang, Yuan He, Yuefeng Chen, Zhiyong Yang","submitted_at":"2022-09-26T12:04:49Z","abstract_excerpt":"In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-art models are based on the idea of pursuing consistent model predictions over unlabeled data toward the input noise, which is called consistency regularization. Nonetheless, there is a lack of theoretical insights into the reason behind its success. To bridge the gap between theoretical and practical results, we propose a worst-case consistency regularization technique for SSL in this paper. Specifically, we first pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12611","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/2209.12611/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":"2209.12611","created_at":"2026-07-05T05:00:54.231892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12611v1","created_at":"2026-07-05T05:00:54.231892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12611","created_at":"2026-07-05T05:00:54.231892+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUWQEDYRVDIZ","created_at":"2026-07-05T05:00:54.231892+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUWQEDYRVDIZWDO4","created_at":"2026-07-05T05:00:54.231892+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUWQEDYR","created_at":"2026-07-05T05:00:54.231892+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/YUWQEDYRVDIZWDO4FLZO6V6LO3","json":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3.json","graph_json":"https://pith.science/api/pith-number/YUWQEDYRVDIZWDO4FLZO6V6LO3/graph.json","events_json":"https://pith.science/api/pith-number/YUWQEDYRVDIZWDO4FLZO6V6LO3/events.json","paper":"https://pith.science/paper/YUWQEDYR"},"agent_actions":{"view_html":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3","download_json":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3.json","view_paper":"https://pith.science/paper/YUWQEDYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12611&json=true","fetch_graph":"https://pith.science/api/pith-number/YUWQEDYRVDIZWDO4FLZO6V6LO3/graph.json","fetch_events":"https://pith.science/api/pith-number/YUWQEDYRVDIZWDO4FLZO6V6LO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3/action/storage_attestation","attest_author":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3/action/author_attestation","sign_citation":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3/action/citation_signature","submit_replication":"https://pith.science/pith/YUWQEDYRVDIZWDO4FLZO6V6LO3/action/replication_record"}},"created_at":"2026-07-05T05:00:54.231892+00:00","updated_at":"2026-07-05T05:00:54.231892+00:00"}