{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VZBF524EIDAYKYNXLNUD6SGHMV","short_pith_number":"pith:VZBF524E","schema_version":"1.0","canonical_sha256":"ae425eeb8440c18561b75b683f48c765402acbab1ff4757625adcd38e9b75df8","source":{"kind":"arxiv","id":"2003.04475","version":3},"attestation_state":"computed","paper":{"title":"Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Geoff Gordon, Han Zhao, Remi Tachet, Yu-Xiang Wang","submitted_at":"2020-03-10T00:35:23Z","abstract_excerpt":"Adversarial learning has demonstrated good performance in the unsupervised domain adaptation setting, by learning domain-invariant representations. However, recent work has shown limitations of this approach when label distributions differ between the source and target domains. In this paper, we propose a new assumption, generalized label shift ($GLS$), to improve robustness against mismatched label distributions. $GLS$ states that, conditioned on the label, there exists a representation of the input that is invariant between the source and target domains. Under $GLS$, we provide theoretical g"},"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":"2003.04475","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-10T00:35:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6afa72dcf83aa118b00b112d9ed80e0b47d1d30576dc5a322f4b8598586581dc","abstract_canon_sha256":"b8a0db643be99c55842cb13c31df3a8bf73f5d72ffb9284659208c25a7e308a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:54.921171Z","signature_b64":"nbfBD3scuj0amLEA6gjPwsBH0T6rknAY9Ug2iCebNvm3t/c3RbfxKQWlktw4fTvlGNPFUSPG7XdIu84Hhv67CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae425eeb8440c18561b75b683f48c765402acbab1ff4757625adcd38e9b75df8","last_reissued_at":"2026-07-05T01:58:54.920702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:54.920702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Geoff Gordon, Han Zhao, Remi Tachet, Yu-Xiang Wang","submitted_at":"2020-03-10T00:35:23Z","abstract_excerpt":"Adversarial learning has demonstrated good performance in the unsupervised domain adaptation setting, by learning domain-invariant representations. However, recent work has shown limitations of this approach when label distributions differ between the source and target domains. In this paper, we propose a new assumption, generalized label shift ($GLS$), to improve robustness against mismatched label distributions. $GLS$ states that, conditioned on the label, there exists a representation of the input that is invariant between the source and target domains. Under $GLS$, we provide theoretical g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04475","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/2003.04475/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":"2003.04475","created_at":"2026-07-05T01:58:54.920760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.04475v3","created_at":"2026-07-05T01:58:54.920760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04475","created_at":"2026-07-05T01:58:54.920760+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZBF524EIDAY","created_at":"2026-07-05T01:58:54.920760+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZBF524EIDAYKYNX","created_at":"2026-07-05T01:58:54.920760+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZBF524E","created_at":"2026-07-05T01:58:54.920760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22099","citing_title":"On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV","json":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV.json","graph_json":"https://pith.science/api/pith-number/VZBF524EIDAYKYNXLNUD6SGHMV/graph.json","events_json":"https://pith.science/api/pith-number/VZBF524EIDAYKYNXLNUD6SGHMV/events.json","paper":"https://pith.science/paper/VZBF524E"},"agent_actions":{"view_html":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV","download_json":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV.json","view_paper":"https://pith.science/paper/VZBF524E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.04475&json=true","fetch_graph":"https://pith.science/api/pith-number/VZBF524EIDAYKYNXLNUD6SGHMV/graph.json","fetch_events":"https://pith.science/api/pith-number/VZBF524EIDAYKYNXLNUD6SGHMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV/action/storage_attestation","attest_author":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV/action/author_attestation","sign_citation":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV/action/citation_signature","submit_replication":"https://pith.science/pith/VZBF524EIDAYKYNXLNUD6SGHMV/action/replication_record"}},"created_at":"2026-07-05T01:58:54.920760+00:00","updated_at":"2026-07-05T01:58:54.920760+00:00"}