{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BS2HLUEVEHOZJPOM5CNNFY2NJ3","short_pith_number":"pith:BS2HLUEV","schema_version":"1.0","canonical_sha256":"0cb475d09521dd94bdcce89ad2e34d4ee08aa9805b4f14da3b2d5a31a5a24ca3","source":{"kind":"arxiv","id":"2301.06010","version":1},"attestation_state":"computed","paper":{"title":"On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Lu Han","submitted_at":"2023-01-15T03:21:59Z","abstract_excerpt":"When there are unlabeled Out-Of-Distribution (OOD) data from other classes, Semi-Supervised Learning (SSL) methods suffer from severe performance degradation and even get worse than merely training on labeled data. In this paper, we empirically analyze Pseudo-Labeling (PL) in class-mismatched SSL. PL is a simple and representative SSL method that transforms SSL problems into supervised learning by creating pseudo-labels for unlabeled data according to the model's prediction. We aim to answer two main questions: (1) How do OOD data influence PL? (2) What is the proper usage of OOD data with PL?"},"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":"2301.06010","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-15T03:21:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cde65bacc3431b579dc72b2e7b9476b89f1cca07755d4cb656dae7e5f2d7adc4","abstract_canon_sha256":"80c39b81f88bf534c8fee27bae1d0ea4fe35ccae77a0ae5837def14c6ce4ad56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:26.587678Z","signature_b64":"iLH/upP4vcEOFVeqVgjZi0q5C+hnsugZPMmP8F/EvcIpJstlI39EBA0i2xgR/EQVqpn3Xg7wmvjUlYAAGMqyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cb475d09521dd94bdcce89ad2e34d4ee08aa9805b4f14da3b2d5a31a5a24ca3","last_reissued_at":"2026-07-05T05:33:26.587120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:26.587120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Lu Han","submitted_at":"2023-01-15T03:21:59Z","abstract_excerpt":"When there are unlabeled Out-Of-Distribution (OOD) data from other classes, Semi-Supervised Learning (SSL) methods suffer from severe performance degradation and even get worse than merely training on labeled data. In this paper, we empirically analyze Pseudo-Labeling (PL) in class-mismatched SSL. PL is a simple and representative SSL method that transforms SSL problems into supervised learning by creating pseudo-labels for unlabeled data according to the model's prediction. We aim to answer two main questions: (1) How do OOD data influence PL? (2) What is the proper usage of OOD data with PL?"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06010","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/2301.06010/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":"2301.06010","created_at":"2026-07-05T05:33:26.587179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06010v1","created_at":"2026-07-05T05:33:26.587179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06010","created_at":"2026-07-05T05:33:26.587179+00:00"},{"alias_kind":"pith_short_12","alias_value":"BS2HLUEVEHOZ","created_at":"2026-07-05T05:33:26.587179+00:00"},{"alias_kind":"pith_short_16","alias_value":"BS2HLUEVEHOZJPOM","created_at":"2026-07-05T05:33:26.587179+00:00"},{"alias_kind":"pith_short_8","alias_value":"BS2HLUEV","created_at":"2026-07-05T05:33:26.587179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01924","citing_title":"Exploring a Hybrid Deep Learning Approach for Anomaly Detection in Mental Healthcare Provider Billing: Addressing Label Scarcity through Semi-Supervised Anomaly Detection","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3","json":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3.json","graph_json":"https://pith.science/api/pith-number/BS2HLUEVEHOZJPOM5CNNFY2NJ3/graph.json","events_json":"https://pith.science/api/pith-number/BS2HLUEVEHOZJPOM5CNNFY2NJ3/events.json","paper":"https://pith.science/paper/BS2HLUEV"},"agent_actions":{"view_html":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3","download_json":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3.json","view_paper":"https://pith.science/paper/BS2HLUEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06010&json=true","fetch_graph":"https://pith.science/api/pith-number/BS2HLUEVEHOZJPOM5CNNFY2NJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/BS2HLUEVEHOZJPOM5CNNFY2NJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3/action/storage_attestation","attest_author":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3/action/author_attestation","sign_citation":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3/action/citation_signature","submit_replication":"https://pith.science/pith/BS2HLUEVEHOZJPOM5CNNFY2NJ3/action/replication_record"}},"created_at":"2026-07-05T05:33:26.587179+00:00","updated_at":"2026-07-05T05:33:26.587179+00:00"}