{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CONSPGZ2DF426VEFCV4JM7J7GR","short_pith_number":"pith:CONSPGZ2","schema_version":"1.0","canonical_sha256":"139b279b3a1979af54851578967d3f345120179a9c1d282b0fc1a986a4323e8b","source":{"kind":"arxiv","id":"2106.00417","version":1},"attestation_state":"computed","paper":{"title":"Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Deng, Haojian Zhang, Kui Jia, Lei Zhang, Shuai Li, Yabin Zhang","submitted_at":"2021-06-01T11:59:48Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) are two typical strategies to reduce expensive manual annotations in machine learning. In order to learn effective models for a target task, UDA utilizes the available labeled source data, which may have different distributions from unlabeled samples in the target domain, while SSL employs few manually annotated target samples. Although UDA and SSL are seemingly very different strategies, we find that they are closely related in terms of task objectives and solutions, and SSL is a special case of UDA problems. Based on thi"},"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":"2106.00417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T11:59:48Z","cross_cats_sorted":[],"title_canon_sha256":"9972fd26e880c9734c0fbf4b897babaa8d875ac0bdbf497ebf587b23a25d1f70","abstract_canon_sha256":"1e5df8b33977821e7508f44d86abf36f8827d751a9afd205e04aff775c881520"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:04.438454Z","signature_b64":"BEajzcoqDZqeUbCpL+MR0rrDjXeb5k6wFGYc4bU/nT+RoRmuGBv8FVFXJPelOAlcl3yeaxrlwevLe0exNb5WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"139b279b3a1979af54851578967d3f345120179a9c1d282b0fc1a986a4323e8b","last_reissued_at":"2026-07-05T02:45:04.438063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:04.438063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Deng, Haojian Zhang, Kui Jia, Lei Zhang, Shuai Li, Yabin Zhang","submitted_at":"2021-06-01T11:59:48Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) are two typical strategies to reduce expensive manual annotations in machine learning. In order to learn effective models for a target task, UDA utilizes the available labeled source data, which may have different distributions from unlabeled samples in the target domain, while SSL employs few manually annotated target samples. Although UDA and SSL are seemingly very different strategies, we find that they are closely related in terms of task objectives and solutions, and SSL is a special case of UDA problems. Based on thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00417","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/2106.00417/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":"2106.00417","created_at":"2026-07-05T02:45:04.438128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00417v1","created_at":"2026-07-05T02:45:04.438128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00417","created_at":"2026-07-05T02:45:04.438128+00:00"},{"alias_kind":"pith_short_12","alias_value":"CONSPGZ2DF42","created_at":"2026-07-05T02:45:04.438128+00:00"},{"alias_kind":"pith_short_16","alias_value":"CONSPGZ2DF426VEF","created_at":"2026-07-05T02:45:04.438128+00:00"},{"alias_kind":"pith_short_8","alias_value":"CONSPGZ2","created_at":"2026-07-05T02:45:04.438128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15431","citing_title":"Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR","json":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR.json","graph_json":"https://pith.science/api/pith-number/CONSPGZ2DF426VEFCV4JM7J7GR/graph.json","events_json":"https://pith.science/api/pith-number/CONSPGZ2DF426VEFCV4JM7J7GR/events.json","paper":"https://pith.science/paper/CONSPGZ2"},"agent_actions":{"view_html":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR","download_json":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR.json","view_paper":"https://pith.science/paper/CONSPGZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00417&json=true","fetch_graph":"https://pith.science/api/pith-number/CONSPGZ2DF426VEFCV4JM7J7GR/graph.json","fetch_events":"https://pith.science/api/pith-number/CONSPGZ2DF426VEFCV4JM7J7GR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR/action/storage_attestation","attest_author":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR/action/author_attestation","sign_citation":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR/action/citation_signature","submit_replication":"https://pith.science/pith/CONSPGZ2DF426VEFCV4JM7J7GR/action/replication_record"}},"created_at":"2026-07-05T02:45:04.438128+00:00","updated_at":"2026-07-05T02:45:04.438128+00:00"}