{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UORNZOTWGTEWXUUKMEIHH4BWX4","short_pith_number":"pith:UORNZOTW","schema_version":"1.0","canonical_sha256":"a3a2dcba7634c96bd28a611073f036bf34039f5065ad141495ba5c6b2df89378","source":{"kind":"arxiv","id":"2508.00922","version":1},"attestation_state":"computed","paper":{"title":"CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyungrok Do, Jinsoo Bae, Seoung Bum Kim","submitted_at":"2025-07-30T07:00:56Z","abstract_excerpt":"Semi-supervised learning (SSL) uses unlabeled data to improve the performance of machine learning models when labeled data is scarce. However, its real-world applications often face the label distribution mismatch problem, in which the unlabeled dataset includes instances whose ground-truth labels are absent from the labeled training dataset. Recent studies, referred to as safe SSL, have addressed this issue by using both classification and out-of-distribution (OOD) detection. However, the existing methods may suffer from overconfidence in deep neural networks, leading to increased SSL errors "},"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":"2508.00922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T07:00:56Z","cross_cats_sorted":[],"title_canon_sha256":"7a209b7860f55a718f066c2b09868d0797595f55eda144f5cde55ccda0630f6b","abstract_canon_sha256":"6d68fceec4c8ca4f10055150be6d1574f9e5f619b09154f604bebe19f5ea3698"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:29.843712Z","signature_b64":"E+TZyCmtWhygBT2URbf+O/w9Ep3E8fAfLwyh/eEO9SfFdOjYHgaT+bhxI1v1j6sxz4RfrYDRgIqZjex1zrzrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a2dcba7634c96bd28a611073f036bf34039f5065ad141495ba5c6b2df89378","last_reissued_at":"2026-07-05T11:47:29.843279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:29.843279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyungrok Do, Jinsoo Bae, Seoung Bum Kim","submitted_at":"2025-07-30T07:00:56Z","abstract_excerpt":"Semi-supervised learning (SSL) uses unlabeled data to improve the performance of machine learning models when labeled data is scarce. However, its real-world applications often face the label distribution mismatch problem, in which the unlabeled dataset includes instances whose ground-truth labels are absent from the labeled training dataset. Recent studies, referred to as safe SSL, have addressed this issue by using both classification and out-of-distribution (OOD) detection. However, the existing methods may suffer from overconfidence in deep neural networks, leading to increased SSL errors "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00922","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/2508.00922/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":"2508.00922","created_at":"2026-07-05T11:47:29.843344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00922v1","created_at":"2026-07-05T11:47:29.843344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00922","created_at":"2026-07-05T11:47:29.843344+00:00"},{"alias_kind":"pith_short_12","alias_value":"UORNZOTWGTEW","created_at":"2026-07-05T11:47:29.843344+00:00"},{"alias_kind":"pith_short_16","alias_value":"UORNZOTWGTEWXUUK","created_at":"2026-07-05T11:47:29.843344+00:00"},{"alias_kind":"pith_short_8","alias_value":"UORNZOTW","created_at":"2026-07-05T11:47:29.843344+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/UORNZOTWGTEWXUUKMEIHH4BWX4","json":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4.json","graph_json":"https://pith.science/api/pith-number/UORNZOTWGTEWXUUKMEIHH4BWX4/graph.json","events_json":"https://pith.science/api/pith-number/UORNZOTWGTEWXUUKMEIHH4BWX4/events.json","paper":"https://pith.science/paper/UORNZOTW"},"agent_actions":{"view_html":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4","download_json":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4.json","view_paper":"https://pith.science/paper/UORNZOTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00922&json=true","fetch_graph":"https://pith.science/api/pith-number/UORNZOTWGTEWXUUKMEIHH4BWX4/graph.json","fetch_events":"https://pith.science/api/pith-number/UORNZOTWGTEWXUUKMEIHH4BWX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4/action/storage_attestation","attest_author":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4/action/author_attestation","sign_citation":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4/action/citation_signature","submit_replication":"https://pith.science/pith/UORNZOTWGTEWXUUKMEIHH4BWX4/action/replication_record"}},"created_at":"2026-07-05T11:47:29.843344+00:00","updated_at":"2026-07-05T11:47:29.843344+00:00"}