{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GYDTI7OCSYLVDML44FGWUAG636","short_pith_number":"pith:GYDTI7OC","schema_version":"1.0","canonical_sha256":"3607347dc2961751b17ce14d6a00dedf8b8c1eccee1f63a42dbdf3045e5d3260","source":{"kind":"arxiv","id":"2601.11670","version":3},"attestation_state":"computed","paper":{"title":"CoVar: Confidence-Variance-Guided Pseudo-Label Selection for Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinshi Liu, Lei He, Pan Liu","submitted_at":"2026-01-16T02:51:59Z","abstract_excerpt":"Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance. We propose CoVar, a confidence--variance framework that assesses pseudo-label reliability by jointly modeling Maximum Confidence (MC) and Residual-Class Variance (RCV). Starting from entropy minimization, we derive a second-order cross-entropy approximation showing that low-loss pseudo-labels are favored when MC is high and RCV is low, with a confidence-dependent penalty that becomes stronger for near-cert"},"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":"2601.11670","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-16T02:51:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa826b5cf3df6c83b10469b16cd3d9b6fce42b39c13b4f3e3afa2bd94694cf60","abstract_canon_sha256":"4ca613a625921560b4e2e2fcd7922468ffd0f293bad0e731e23d3a7ca681a7d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:31.832163Z","signature_b64":"CspdsfliVvx0l0sTtrSuLbdxFg/K9CVUfpAsaouC7vwx9VIp5beV+WW7Rc41NarSyzzqsz72E0ckTpwu0OThDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3607347dc2961751b17ce14d6a00dedf8b8c1eccee1f63a42dbdf3045e5d3260","last_reissued_at":"2026-06-11T01:10:31.830998Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:31.830998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoVar: Confidence-Variance-Guided Pseudo-Label Selection for Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinshi Liu, Lei He, Pan Liu","submitted_at":"2026-01-16T02:51:59Z","abstract_excerpt":"Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance. We propose CoVar, a confidence--variance framework that assesses pseudo-label reliability by jointly modeling Maximum Confidence (MC) and Residual-Class Variance (RCV). Starting from entropy minimization, we derive a second-order cross-entropy approximation showing that low-loss pseudo-labels are favored when MC is high and RCV is low, with a confidence-dependent penalty that becomes stronger for near-cert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.11670","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/2601.11670/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":"2601.11670","created_at":"2026-06-11T01:10:31.831159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.11670v3","created_at":"2026-06-11T01:10:31.831159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11670","created_at":"2026-06-11T01:10:31.831159+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYDTI7OCSYLV","created_at":"2026-06-11T01:10:31.831159+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYDTI7OCSYLVDML4","created_at":"2026-06-11T01:10:31.831159+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYDTI7OC","created_at":"2026-06-11T01:10:31.831159+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/GYDTI7OCSYLVDML44FGWUAG636","json":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636.json","graph_json":"https://pith.science/api/pith-number/GYDTI7OCSYLVDML44FGWUAG636/graph.json","events_json":"https://pith.science/api/pith-number/GYDTI7OCSYLVDML44FGWUAG636/events.json","paper":"https://pith.science/paper/GYDTI7OC"},"agent_actions":{"view_html":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636","download_json":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636.json","view_paper":"https://pith.science/paper/GYDTI7OC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.11670&json=true","fetch_graph":"https://pith.science/api/pith-number/GYDTI7OCSYLVDML44FGWUAG636/graph.json","fetch_events":"https://pith.science/api/pith-number/GYDTI7OCSYLVDML44FGWUAG636/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636/action/storage_attestation","attest_author":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636/action/author_attestation","sign_citation":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636/action/citation_signature","submit_replication":"https://pith.science/pith/GYDTI7OCSYLVDML44FGWUAG636/action/replication_record"}},"created_at":"2026-06-11T01:10:31.831159+00:00","updated_at":"2026-06-11T01:10:31.831159+00:00"}