{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7YVZ6ZMRSP2JFAJHPTFXBOCBEZ","short_pith_number":"pith:7YVZ6ZMR","schema_version":"1.0","canonical_sha256":"fe2b9f659193f49281277ccb70b841265173b8ba51616d84fbe91bbb010f69bd","source":{"kind":"arxiv","id":"2101.12727","version":3},"attestation_state":"computed","paper":{"title":"Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Samarth Mishra, Venkatesh Saligrama","submitted_at":"2021-01-29T18:40:17Z","abstract_excerpt":"Most modern unsupervised domain adaptation (UDA) approaches are rooted in domain alignment, i.e., learning to align source and target features to learn a target domain classifier using source labels. In semi-supervised domain adaptation (SSDA), when the learner can access few target domain labels, prior approaches have followed UDA theory to use domain alignment for learning. We show that the case of SSDA is different and a good target classifier can be learned without needing alignment. We use self-supervised pretraining (via rotation prediction) and consistency regularization to achieve well"},"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":"2101.12727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-29T18:40:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04973d45918cc2b1c6f7f806ca6c09d7dc70d09bd0fe3d53a957a37ef50bfe3e","abstract_canon_sha256":"675bb7f8a5a312314937c7b8f63f7a3d8ef1b0d79222fcfffd7293f785eb33cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:27.522610Z","signature_b64":"wtNijvy5ex2PfI0xId+evqAMvjbHA2yNmLoAWU/oCpjPhxjS8FDCIxNl3Qu9C7kSR6Fmx3aSpJ+fW38f0aiZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe2b9f659193f49281277ccb70b841265173b8ba51616d84fbe91bbb010f69bd","last_reissued_at":"2026-07-05T03:35:27.522082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:27.522082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Samarth Mishra, Venkatesh Saligrama","submitted_at":"2021-01-29T18:40:17Z","abstract_excerpt":"Most modern unsupervised domain adaptation (UDA) approaches are rooted in domain alignment, i.e., learning to align source and target features to learn a target domain classifier using source labels. In semi-supervised domain adaptation (SSDA), when the learner can access few target domain labels, prior approaches have followed UDA theory to use domain alignment for learning. We show that the case of SSDA is different and a good target classifier can be learned without needing alignment. We use self-supervised pretraining (via rotation prediction) and consistency regularization to achieve well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.12727","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/2101.12727/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":"2101.12727","created_at":"2026-07-05T03:35:27.522158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.12727v3","created_at":"2026-07-05T03:35:27.522158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.12727","created_at":"2026-07-05T03:35:27.522158+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YVZ6ZMRSP2J","created_at":"2026-07-05T03:35:27.522158+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YVZ6ZMRSP2JFAJH","created_at":"2026-07-05T03:35:27.522158+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YVZ6ZMR","created_at":"2026-07-05T03:35:27.522158+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/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ","json":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ.json","graph_json":"https://pith.science/api/pith-number/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/graph.json","events_json":"https://pith.science/api/pith-number/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/events.json","paper":"https://pith.science/paper/7YVZ6ZMR"},"agent_actions":{"view_html":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ","download_json":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ.json","view_paper":"https://pith.science/paper/7YVZ6ZMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.12727&json=true","fetch_graph":"https://pith.science/api/pith-number/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/action/storage_attestation","attest_author":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/action/author_attestation","sign_citation":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/action/citation_signature","submit_replication":"https://pith.science/pith/7YVZ6ZMRSP2JFAJHPTFXBOCBEZ/action/replication_record"}},"created_at":"2026-07-05T03:35:27.522158+00:00","updated_at":"2026-07-05T03:35:27.522158+00:00"}