{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NYK3ODZGT3P2LKRCKMS2CSC6DT","short_pith_number":"pith:NYK3ODZG","schema_version":"1.0","canonical_sha256":"6e15b70f269edfa5aa225325a1485e1cf5f693af6841148a498f4e36175c79a4","source":{"kind":"arxiv","id":"2403.18407","version":1},"attestation_state":"computed","paper":{"title":"A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Jiaqi Wu, Junbiao Pang, Qingming Huang","submitted_at":"2024-03-27T09:49:37Z","abstract_excerpt":"Semi-supervised learning (SSL) is a practical challenge in computer vision. Pseudo-label (PL) methods, e.g., FixMatch and FreeMatch, obtain the State Of The Art (SOTA) performances in SSL. These approaches employ a threshold-to-pseudo-label (T2L) process to generate PLs by truncating the confidence scores of unlabeled data predicted by the self-training method. However, self-trained models typically yield biased and high-variance predictions, especially in the scenarios when a little labeled data are supplied. To address this issue, we propose a lightweight channel-based ensemble method to eff"},"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":"2403.18407","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T09:49:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7876e13008dfe09887d9aafccf5e63111343cbb56355628b7878558372599155","abstract_canon_sha256":"db4960f418922d6edf4ebfd7cd8ace3c90e13dcd8bcbe1b6c8f94a4b73ac8145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:22.262000Z","signature_b64":"jUH7HJlGKgcOXg4JI7l8cZnlYInGpjD71RVbSNqQ5oYb4dCNKwyfdg8SoULMb0KdkT2ripudty3aaTAMBq+nDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e15b70f269edfa5aa225325a1485e1cf5f693af6841148a498f4e36175c79a4","last_reissued_at":"2026-07-05T08:01:22.261565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:22.261565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Jiaqi Wu, Junbiao Pang, Qingming Huang","submitted_at":"2024-03-27T09:49:37Z","abstract_excerpt":"Semi-supervised learning (SSL) is a practical challenge in computer vision. Pseudo-label (PL) methods, e.g., FixMatch and FreeMatch, obtain the State Of The Art (SOTA) performances in SSL. These approaches employ a threshold-to-pseudo-label (T2L) process to generate PLs by truncating the confidence scores of unlabeled data predicted by the self-training method. However, self-trained models typically yield biased and high-variance predictions, especially in the scenarios when a little labeled data are supplied. To address this issue, we propose a lightweight channel-based ensemble method to eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18407","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/2403.18407/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":"2403.18407","created_at":"2026-07-05T08:01:22.261617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18407v1","created_at":"2026-07-05T08:01:22.261617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18407","created_at":"2026-07-05T08:01:22.261617+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYK3ODZGT3P2","created_at":"2026-07-05T08:01:22.261617+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYK3ODZGT3P2LKRC","created_at":"2026-07-05T08:01:22.261617+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYK3ODZG","created_at":"2026-07-05T08:01:22.261617+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/NYK3ODZGT3P2LKRCKMS2CSC6DT","json":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT.json","graph_json":"https://pith.science/api/pith-number/NYK3ODZGT3P2LKRCKMS2CSC6DT/graph.json","events_json":"https://pith.science/api/pith-number/NYK3ODZGT3P2LKRCKMS2CSC6DT/events.json","paper":"https://pith.science/paper/NYK3ODZG"},"agent_actions":{"view_html":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT","download_json":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT.json","view_paper":"https://pith.science/paper/NYK3ODZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18407&json=true","fetch_graph":"https://pith.science/api/pith-number/NYK3ODZGT3P2LKRCKMS2CSC6DT/graph.json","fetch_events":"https://pith.science/api/pith-number/NYK3ODZGT3P2LKRCKMS2CSC6DT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT/action/storage_attestation","attest_author":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT/action/author_attestation","sign_citation":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT/action/citation_signature","submit_replication":"https://pith.science/pith/NYK3ODZGT3P2LKRCKMS2CSC6DT/action/replication_record"}},"created_at":"2026-07-05T08:01:22.261617+00:00","updated_at":"2026-07-05T08:01:22.261617+00:00"}