{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CZ5V4JDGDUTMS2K6S27FTNDDHH","short_pith_number":"pith:CZ5V4JDG","schema_version":"1.0","canonical_sha256":"167b5e24661d26c9695e96be59b46339d125e10cee773e9f17dc94bcf04dc6d9","source":{"kind":"arxiv","id":"2007.10233","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Domain Adaptation in the Absence of Source Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Divya Shanmugam, John Guttag, Roshni Sahoo","submitted_at":"2020-07-20T16:22:14Z","abstract_excerpt":"Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available. As the use of pre-trained models becomes more prevalent, it is reasonable to assume that source data is unavailable. We propose an unsupervised method for adapting a source classifier to a target domain that varies from the source domain along natural axes, such as brightness and contrast. Our method only requires access to unlabeled target instances and the source classifier. We validate our method in scenarios where the distribution shi"},"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":"2007.10233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-20T16:22:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"efbdd5318bdbd96fe5d24f112ed0064f3919237d08554bdd176c59c34513db88","abstract_canon_sha256":"3958d6e646e7afeb2318365f65f12c7ec7124f57aa7eaa045fa1c5bc1e4ce4a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:34.590705Z","signature_b64":"B2YAsrRHlzHigoQ5hiqV4u7+j4K9FQPirI7TmrfUPtNOFznIS/xoNxjstPJPNjh3p2bRrM7mGH8jt7pcYlpOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167b5e24661d26c9695e96be59b46339d125e10cee773e9f17dc94bcf04dc6d9","last_reissued_at":"2026-07-05T01:20:34.590223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:34.590223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Domain Adaptation in the Absence of Source Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Divya Shanmugam, John Guttag, Roshni Sahoo","submitted_at":"2020-07-20T16:22:14Z","abstract_excerpt":"Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available. As the use of pre-trained models becomes more prevalent, it is reasonable to assume that source data is unavailable. We propose an unsupervised method for adapting a source classifier to a target domain that varies from the source domain along natural axes, such as brightness and contrast. Our method only requires access to unlabeled target instances and the source classifier. We validate our method in scenarios where the distribution shi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10233","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/2007.10233/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":"2007.10233","created_at":"2026-07-05T01:20:34.590276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.10233v1","created_at":"2026-07-05T01:20:34.590276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10233","created_at":"2026-07-05T01:20:34.590276+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ5V4JDGDUTM","created_at":"2026-07-05T01:20:34.590276+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ5V4JDGDUTMS2K6","created_at":"2026-07-05T01:20:34.590276+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ5V4JDG","created_at":"2026-07-05T01:20:34.590276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25152","citing_title":"Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23120","citing_title":"Temporal-Spectral Alignment with Frequency Adaptation for Source-Free Time-Series Adaptation","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH","json":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH.json","graph_json":"https://pith.science/api/pith-number/CZ5V4JDGDUTMS2K6S27FTNDDHH/graph.json","events_json":"https://pith.science/api/pith-number/CZ5V4JDGDUTMS2K6S27FTNDDHH/events.json","paper":"https://pith.science/paper/CZ5V4JDG"},"agent_actions":{"view_html":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH","download_json":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH.json","view_paper":"https://pith.science/paper/CZ5V4JDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.10233&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ5V4JDGDUTMS2K6S27FTNDDHH/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ5V4JDGDUTMS2K6S27FTNDDHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH/action/storage_attestation","attest_author":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH/action/author_attestation","sign_citation":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH/action/citation_signature","submit_replication":"https://pith.science/pith/CZ5V4JDGDUTMS2K6S27FTNDDHH/action/replication_record"}},"created_at":"2026-07-05T01:20:34.590276+00:00","updated_at":"2026-07-05T01:20:34.590276+00:00"}