{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RCIWQND74YYSJ3VFDXAUNCCPF3","short_pith_number":"pith:RCIWQND7","schema_version":"1.0","canonical_sha256":"889168347fe63124eea51dc146884f2ef0fb22bf9316fe803dce224a6c3cfbd9","source":{"kind":"arxiv","id":"2107.13469","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"C.-C. Jay Kuo, Fangxu Xing, Georges El Fakhri, Jane You, Jonghye Woo, Site Li, Xiaofeng Liu, Zhenhua Guo","submitted_at":"2021-07-28T16:28:01Z","abstract_excerpt":"In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r.t. both $p(x|y)$ and $p(y)$. Since the label is inaccessible in the target domain, the conventional adversarial UDA assumes $p(y)$ is invariant across domains, and relies on aligning $p(x)$ as an alternative to the $p(x|y)$ alignment. To address this, we provide a thorough theoretical and empirical analysis of the conventional adversarial UDA methods under both conditional and label shifts, and propose a novel and p"},"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":"2107.13469","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-28T16:28:01Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"e0713851e7d1e141d1fc3ab3d4695327a6bcc51b5461db63a380d494f300cd77","abstract_canon_sha256":"a8ecd825c4d4e02fb1b1336b122735b8f4780f472a31286573d6d55843f9aaf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:17.942536Z","signature_b64":"EraS62MYQk6esWGD4n3Wx5CMgzhAhBLVGA9syBu9fM94MQbTrHRTvkgDqUBJE+ommBPjqnk+qKWs14kaAJpIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"889168347fe63124eea51dc146884f2ef0fb22bf9316fe803dce224a6c3cfbd9","last_reissued_at":"2026-07-05T03:02:17.942082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:17.942082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"C.-C. Jay Kuo, Fangxu Xing, Georges El Fakhri, Jane You, Jonghye Woo, Site Li, Xiaofeng Liu, Zhenhua Guo","submitted_at":"2021-07-28T16:28:01Z","abstract_excerpt":"In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r.t. both $p(x|y)$ and $p(y)$. Since the label is inaccessible in the target domain, the conventional adversarial UDA assumes $p(y)$ is invariant across domains, and relies on aligning $p(x)$ as an alternative to the $p(x|y)$ alignment. To address this, we provide a thorough theoretical and empirical analysis of the conventional adversarial UDA methods under both conditional and label shifts, and propose a novel and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13469","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/2107.13469/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":"2107.13469","created_at":"2026-07-05T03:02:17.942139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13469v2","created_at":"2026-07-05T03:02:17.942139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13469","created_at":"2026-07-05T03:02:17.942139+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCIWQND74YYS","created_at":"2026-07-05T03:02:17.942139+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCIWQND74YYSJ3VF","created_at":"2026-07-05T03:02:17.942139+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCIWQND7","created_at":"2026-07-05T03:02:17.942139+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/RCIWQND74YYSJ3VFDXAUNCCPF3","json":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3.json","graph_json":"https://pith.science/api/pith-number/RCIWQND74YYSJ3VFDXAUNCCPF3/graph.json","events_json":"https://pith.science/api/pith-number/RCIWQND74YYSJ3VFDXAUNCCPF3/events.json","paper":"https://pith.science/paper/RCIWQND7"},"agent_actions":{"view_html":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3","download_json":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3.json","view_paper":"https://pith.science/paper/RCIWQND7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13469&json=true","fetch_graph":"https://pith.science/api/pith-number/RCIWQND74YYSJ3VFDXAUNCCPF3/graph.json","fetch_events":"https://pith.science/api/pith-number/RCIWQND74YYSJ3VFDXAUNCCPF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3/action/storage_attestation","attest_author":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3/action/author_attestation","sign_citation":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3/action/citation_signature","submit_replication":"https://pith.science/pith/RCIWQND74YYSJ3VFDXAUNCCPF3/action/replication_record"}},"created_at":"2026-07-05T03:02:17.942139+00:00","updated_at":"2026-07-05T03:02:17.942139+00:00"}