{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KK4B6ZQVVNLDKCLLP4MRTA5BVR","short_pith_number":"pith:KK4B6ZQV","schema_version":"1.0","canonical_sha256":"52b81f6615ab5635096b7f191983a1ac785ef8cff49633ac87b6a735989fc87a","source":{"kind":"arxiv","id":"2106.04732","version":2},"attestation_state":"computed","paper":{"title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alex Kurakin, David Berthelot, Kihyuk Sohn, Nicholas Carlini, Rebecca Roelofs","submitted_at":"2021-06-08T23:39:12Z","abstract_excerpt":"We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one. With the goal of generality, we introduce AdaMatch, a method that unifies the tasks of unsupervised domain adaptation (UDA), semi-supervised learning (SSL), and semi-supervised domain adaptation (SSDA). In an extensive experimental study, we compare its behavior with respective state-of-the-art techniques from SSL, SSDA, and UDA on vision classification tasks. We find AdaMatch either matches or significantly exceed"},"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":"2106.04732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T23:39:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"08ce2439a3ca24cbab2e79739eb9fc2a3eb0a51bff5e6d3ca30d71b437ea74d4","abstract_canon_sha256":"26d180eed203b0dfa8ad40bcbee084fe7838ac3b6beb13ffd1d13f7208a00bae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:11.739483Z","signature_b64":"Cr8BL180Sd48ud7xr6p50XfmCaqGqUMdQa/Q5gZJ3n5ZpnCFfFsmZ4DNNraXBjgro1MAF8zIaz/eTA+K1jLSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b81f6615ab5635096b7f191983a1ac785ef8cff49633ac87b6a735989fc87a","last_reissued_at":"2026-07-05T04:05:11.738962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:11.738962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alex Kurakin, David Berthelot, Kihyuk Sohn, Nicholas Carlini, Rebecca Roelofs","submitted_at":"2021-06-08T23:39:12Z","abstract_excerpt":"We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one. With the goal of generality, we introduce AdaMatch, a method that unifies the tasks of unsupervised domain adaptation (UDA), semi-supervised learning (SSL), and semi-supervised domain adaptation (SSDA). In an extensive experimental study, we compare its behavior with respective state-of-the-art techniques from SSL, SSDA, and UDA on vision classification tasks. We find AdaMatch either matches or significantly exceed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04732","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/2106.04732/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":"2106.04732","created_at":"2026-07-05T04:05:11.739021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04732v2","created_at":"2026-07-05T04:05:11.739021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04732","created_at":"2026-07-05T04:05:11.739021+00:00"},{"alias_kind":"pith_short_12","alias_value":"KK4B6ZQVVNLD","created_at":"2026-07-05T04:05:11.739021+00:00"},{"alias_kind":"pith_short_16","alias_value":"KK4B6ZQVVNLDKCLL","created_at":"2026-07-05T04:05:11.739021+00:00"},{"alias_kind":"pith_short_8","alias_value":"KK4B6ZQV","created_at":"2026-07-05T04:05:11.739021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00358","citing_title":"PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21605","citing_title":"$\\mu$Match: Foundation Models for Semi-supervised Learning and Domain Adaptation in EM","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR","json":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR.json","graph_json":"https://pith.science/api/pith-number/KK4B6ZQVVNLDKCLLP4MRTA5BVR/graph.json","events_json":"https://pith.science/api/pith-number/KK4B6ZQVVNLDKCLLP4MRTA5BVR/events.json","paper":"https://pith.science/paper/KK4B6ZQV"},"agent_actions":{"view_html":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR","download_json":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR.json","view_paper":"https://pith.science/paper/KK4B6ZQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04732&json=true","fetch_graph":"https://pith.science/api/pith-number/KK4B6ZQVVNLDKCLLP4MRTA5BVR/graph.json","fetch_events":"https://pith.science/api/pith-number/KK4B6ZQVVNLDKCLLP4MRTA5BVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR/action/storage_attestation","attest_author":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR/action/author_attestation","sign_citation":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR/action/citation_signature","submit_replication":"https://pith.science/pith/KK4B6ZQVVNLDKCLLP4MRTA5BVR/action/replication_record"}},"created_at":"2026-07-05T04:05:11.739021+00:00","updated_at":"2026-07-05T04:05:11.739021+00:00"}