{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WOFGLY57ZZ5PV55C7ERNKSYUWU","short_pith_number":"pith:WOFGLY57","schema_version":"1.0","canonical_sha256":"b38a65e3bfce7afaf7a2f922d54b14b52263375aeed087b0daff59c8e2d8a15f","source":{"kind":"arxiv","id":"2309.10301","version":3},"attestation_state":"computed","paper":{"title":"Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithms","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bin Yu, Keru Wu, Wooseok Ha, Yuansi Chen","submitted_at":"2023-09-19T04:04:59Z","abstract_excerpt":"Domain adaptation (DA) is a statistical learning problem that arises when the distribution of the source data used to train a model differs from that of the target data used to evaluate the model. While many DA algorithms have demonstrated considerable empirical success, blindly applying these algorithms can often lead to worse performance on new datasets. To address this, it is crucial to clarify the assumptions under which a DA algorithm has good target performance. In this work, we focus on the assumption of the presence of conditionally invariant components (CICs), which are relevant for 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":"2309.10301","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-19T04:04:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fcf855932b9f4a2c9b9edffdda664466ffe4d3f058e8149024937e2f8428bcab","abstract_canon_sha256":"0f8adf0705c9a625ab3020aa9e6efdb410bc95ebc51fcd8fdfa22fd9aa2f9269"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:59.037872Z","signature_b64":"XemNgGDs4XZTQamUopfF/WivLa8uGs6z3xAg65ou2VfKzBXCBjQXJmxNGG5YYVO/YBLZNWUYrrEmIpcKEtQZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b38a65e3bfce7afaf7a2f922d54b14b52263375aeed087b0daff59c8e2d8a15f","last_reissued_at":"2026-07-05T11:37:59.037199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:59.037199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithms","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bin Yu, Keru Wu, Wooseok Ha, Yuansi Chen","submitted_at":"2023-09-19T04:04:59Z","abstract_excerpt":"Domain adaptation (DA) is a statistical learning problem that arises when the distribution of the source data used to train a model differs from that of the target data used to evaluate the model. While many DA algorithms have demonstrated considerable empirical success, blindly applying these algorithms can often lead to worse performance on new datasets. To address this, it is crucial to clarify the assumptions under which a DA algorithm has good target performance. In this work, we focus on the assumption of the presence of conditionally invariant components (CICs), which are relevant for p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10301","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/2309.10301/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":"2309.10301","created_at":"2026-07-05T11:37:59.037273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10301v3","created_at":"2026-07-05T11:37:59.037273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10301","created_at":"2026-07-05T11:37:59.037273+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOFGLY57ZZ5P","created_at":"2026-07-05T11:37:59.037273+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOFGLY57ZZ5PV55C","created_at":"2026-07-05T11:37:59.037273+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOFGLY57","created_at":"2026-07-05T11:37:59.037273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12680","citing_title":"How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU","json":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU.json","graph_json":"https://pith.science/api/pith-number/WOFGLY57ZZ5PV55C7ERNKSYUWU/graph.json","events_json":"https://pith.science/api/pith-number/WOFGLY57ZZ5PV55C7ERNKSYUWU/events.json","paper":"https://pith.science/paper/WOFGLY57"},"agent_actions":{"view_html":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU","download_json":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU.json","view_paper":"https://pith.science/paper/WOFGLY57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10301&json=true","fetch_graph":"https://pith.science/api/pith-number/WOFGLY57ZZ5PV55C7ERNKSYUWU/graph.json","fetch_events":"https://pith.science/api/pith-number/WOFGLY57ZZ5PV55C7ERNKSYUWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU/action/storage_attestation","attest_author":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU/action/author_attestation","sign_citation":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU/action/citation_signature","submit_replication":"https://pith.science/pith/WOFGLY57ZZ5PV55C7ERNKSYUWU/action/replication_record"}},"created_at":"2026-07-05T11:37:59.037273+00:00","updated_at":"2026-07-05T11:37:59.037273+00:00"}