{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CWWSIJD5J2HNO3QKAHPRPU7LB5","short_pith_number":"pith:CWWSIJD5","schema_version":"1.0","canonical_sha256":"15ad24247d4e8ed76e0a01df17d3eb0f5481c89fad0acb890ad1f917821fa17f","source":{"kind":"arxiv","id":"2101.06329","version":3},"attestation_state":"computed","paper":{"title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Kevin Duarte, Mamshad Nayeem Rizve, Mubarak Shah, Yogesh S Rawat","submitted_at":"2021-01-15T23:29:57Z","abstract_excerpt":"The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to generate for all data modalities. Pseudo-labeling (PL) is a general SSL approach that does not have this constraint but performs relatively poorly in its original formulation. We argue that PL underperforms due to the erroneous high confidence predictions from poorly calibrated models; these predictions generate many incorrect pseudo-labels, leading to noisy"},"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":"2101.06329","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-15T23:29:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"68225c60cb01b81fa2f0c26e0ff771f2d2ec3cd11fa8c089f163912b18f0ceb8","abstract_canon_sha256":"8600678b213edb8c598fd662acdc2bd8cb9f3f64ecd8735307be10d75a55e6df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:07.367475Z","signature_b64":"+5ciWFJhMhoowZnfl4LjhixGtAN+OfFHOGOpB3FsD3+riLaDwuJxfyWHkT4nVkGwyE/TvPRjqp2gAEShW4VLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15ad24247d4e8ed76e0a01df17d3eb0f5481c89fad0acb890ad1f917821fa17f","last_reissued_at":"2026-07-05T02:33:07.366952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:07.366952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Kevin Duarte, Mamshad Nayeem Rizve, Mubarak Shah, Yogesh S Rawat","submitted_at":"2021-01-15T23:29:57Z","abstract_excerpt":"The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to generate for all data modalities. Pseudo-labeling (PL) is a general SSL approach that does not have this constraint but performs relatively poorly in its original formulation. We argue that PL underperforms due to the erroneous high confidence predictions from poorly calibrated models; these predictions generate many incorrect pseudo-labels, leading to noisy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06329","kind":"arxiv","version":3},"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/2101.06329/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":"2101.06329","created_at":"2026-07-05T02:33:07.367017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.06329v3","created_at":"2026-07-05T02:33:07.367017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06329","created_at":"2026-07-05T02:33:07.367017+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWWSIJD5J2HN","created_at":"2026-07-05T02:33:07.367017+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWWSIJD5J2HNO3QK","created_at":"2026-07-05T02:33:07.367017+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWWSIJD5","created_at":"2026-07-05T02:33:07.367017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11583","citing_title":"Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24985","citing_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10754","citing_title":"Human Gaze-based Dual Teacher Guidance Learning for Semi-Supervised Medical Image Segmentation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5","json":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5.json","graph_json":"https://pith.science/api/pith-number/CWWSIJD5J2HNO3QKAHPRPU7LB5/graph.json","events_json":"https://pith.science/api/pith-number/CWWSIJD5J2HNO3QKAHPRPU7LB5/events.json","paper":"https://pith.science/paper/CWWSIJD5"},"agent_actions":{"view_html":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5","download_json":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5.json","view_paper":"https://pith.science/paper/CWWSIJD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.06329&json=true","fetch_graph":"https://pith.science/api/pith-number/CWWSIJD5J2HNO3QKAHPRPU7LB5/graph.json","fetch_events":"https://pith.science/api/pith-number/CWWSIJD5J2HNO3QKAHPRPU7LB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5/action/storage_attestation","attest_author":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5/action/author_attestation","sign_citation":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5/action/citation_signature","submit_replication":"https://pith.science/pith/CWWSIJD5J2HNO3QKAHPRPU7LB5/action/replication_record"}},"created_at":"2026-07-05T02:33:07.367017+00:00","updated_at":"2026-07-05T02:33:07.367017+00:00"}