{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6JPBCBLOMBEVARECDBC3PRTJSA","short_pith_number":"pith:6JPBCBLO","schema_version":"1.0","canonical_sha256":"f25e11056e60495044821845b7c6699017609d9f8d41fb4848999e27f83836ee","source":{"kind":"arxiv","id":"2001.07685","version":2},"attestation_state":"computed","paper":{"title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Kurakin, Chun-Liang Li, Colin Raffel, David Berthelot, Ekin D. Cubuk, Han Zhang, Kihyuk Sohn, Nicholas Carlini, Zizhao Zhang","submitted_at":"2020-01-21T18:32:27Z","abstract_excerpt":"Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm, FixMatch, first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. "},"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":"2001.07685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T18:32:27Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"95d775d555de3700bee85240d7470369cdb1543a12b5746d396fedf2cd5fa343","abstract_canon_sha256":"4acea3e681534680a1ef68c28a304e64fd3af97f4060d444f98f30e53d52230d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:27.354388Z","signature_b64":"PSYC2Jp5j79SnUqQo5vwhhINV2sTpotzLqlyAz3w1BRhLoZG+D9CMI6tjgmY1unzEoICKJl80qNVUY5B6xhrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f25e11056e60495044821845b7c6699017609d9f8d41fb4848999e27f83836ee","last_reissued_at":"2026-07-05T01:54:27.353843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:27.353843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Kurakin, Chun-Liang Li, Colin Raffel, David Berthelot, Ekin D. Cubuk, Han Zhang, Kihyuk Sohn, Nicholas Carlini, Zizhao Zhang","submitted_at":"2020-01-21T18:32:27Z","abstract_excerpt":"Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm, FixMatch, first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07685","kind":"arxiv","version":2},"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/2001.07685/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":"2001.07685","created_at":"2026-07-05T01:54:27.353919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07685v2","created_at":"2026-07-05T01:54:27.353919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07685","created_at":"2026-07-05T01:54:27.353919+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JPBCBLOMBEV","created_at":"2026-07-05T01:54:27.353919+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JPBCBLOMBEVAREC","created_at":"2026-07-05T01:54:27.353919+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JPBCBLO","created_at":"2026-07-05T01:54:27.353919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11626","citing_title":"Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without Labels","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17433","citing_title":"VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05347","citing_title":"TopoPult-SSL: Gland-Mask-Free Cross-Device Meibomian Gland Segmentation via Self-Distilled Weak Clinical Priors","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17433","citing_title":"VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2002.05709","citing_title":"A Simple Framework for Contrastive Learning of Visual Representations","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12387","citing_title":"A Semi-Supervised Framework for Speech Confidence Detection using Whisper","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2404.08471","citing_title":"Revisiting Feature Prediction for Learning Visual Representations from Video","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08519","citing_title":"SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA","json":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA.json","graph_json":"https://pith.science/api/pith-number/6JPBCBLOMBEVARECDBC3PRTJSA/graph.json","events_json":"https://pith.science/api/pith-number/6JPBCBLOMBEVARECDBC3PRTJSA/events.json","paper":"https://pith.science/paper/6JPBCBLO"},"agent_actions":{"view_html":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA","download_json":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA.json","view_paper":"https://pith.science/paper/6JPBCBLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07685&json=true","fetch_graph":"https://pith.science/api/pith-number/6JPBCBLOMBEVARECDBC3PRTJSA/graph.json","fetch_events":"https://pith.science/api/pith-number/6JPBCBLOMBEVARECDBC3PRTJSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA/action/storage_attestation","attest_author":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA/action/author_attestation","sign_citation":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA/action/citation_signature","submit_replication":"https://pith.science/pith/6JPBCBLOMBEVARECDBC3PRTJSA/action/replication_record"}},"created_at":"2026-07-05T01:54:27.353919+00:00","updated_at":"2026-07-05T01:54:27.353919+00:00"}