{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2OTFVIQ3UNVLONUQKQXRLDVWMW","short_pith_number":"pith:2OTFVIQ3","schema_version":"1.0","canonical_sha256":"d3a65aa21ba36ab73690542f158eb665949cd00c9bfeec5d7f9f9edf5e673374","source":{"kind":"arxiv","id":"2503.08155","version":1},"attestation_state":"computed","paper":{"title":"Domain Adaptation and Entanglement: an Optimal Transport Perspective","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Soen, Chao-Kai Chiang, Masashi Sugiyama, Okan Ko\\c{c}","submitted_at":"2025-03-11T08:10:03Z","abstract_excerpt":"Current machine learning systems are brittle in the face of distribution shifts (DS), where the target distribution that the system is tested on differs from the source distribution used to train the system. This problem of robustness to DS has been studied extensively in the field of domain adaptation. For deep neural networks, a popular framework for unsupervised domain adaptation (UDA) is domain matching, in which algorithms\n  try to align the marginal distributions in the feature or output space.\n  The current theoretical understanding of these methods, however, is limited and existing the"},"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":"2503.08155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T08:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"bf3ee5e82f893fcd748c1eb60e72c7dfd953215dfef9d72f12e890d94bce6947","abstract_canon_sha256":"6d142483dd6139f93ea1e75197496f78d9b50641a6642e319099a4aadfa5f86e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:52.421564Z","signature_b64":"XdnL9AB2FjHXamxke2nuZUdOngt7urriN8jB2yDhlmixYHgyi1C1N4UtCBNtz8he7FMmIODA4eit1ykUyUoYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3a65aa21ba36ab73690542f158eb665949cd00c9bfeec5d7f9f9edf5e673374","last_reissued_at":"2026-07-05T10:28:52.421038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:52.421038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation and Entanglement: an Optimal Transport Perspective","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Soen, Chao-Kai Chiang, Masashi Sugiyama, Okan Ko\\c{c}","submitted_at":"2025-03-11T08:10:03Z","abstract_excerpt":"Current machine learning systems are brittle in the face of distribution shifts (DS), where the target distribution that the system is tested on differs from the source distribution used to train the system. This problem of robustness to DS has been studied extensively in the field of domain adaptation. For deep neural networks, a popular framework for unsupervised domain adaptation (UDA) is domain matching, in which algorithms\n  try to align the marginal distributions in the feature or output space.\n  The current theoretical understanding of these methods, however, is limited and existing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08155","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/2503.08155/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":"2503.08155","created_at":"2026-07-05T10:28:52.421093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08155v1","created_at":"2026-07-05T10:28:52.421093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08155","created_at":"2026-07-05T10:28:52.421093+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OTFVIQ3UNVL","created_at":"2026-07-05T10:28:52.421093+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OTFVIQ3UNVLONUQ","created_at":"2026-07-05T10:28:52.421093+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OTFVIQ3","created_at":"2026-07-05T10:28:52.421093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05883","citing_title":"Geometry-Aware Dataset Condensation for Diffusion Model Training","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03877","citing_title":"DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW","json":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW.json","graph_json":"https://pith.science/api/pith-number/2OTFVIQ3UNVLONUQKQXRLDVWMW/graph.json","events_json":"https://pith.science/api/pith-number/2OTFVIQ3UNVLONUQKQXRLDVWMW/events.json","paper":"https://pith.science/paper/2OTFVIQ3"},"agent_actions":{"view_html":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW","download_json":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW.json","view_paper":"https://pith.science/paper/2OTFVIQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08155&json=true","fetch_graph":"https://pith.science/api/pith-number/2OTFVIQ3UNVLONUQKQXRLDVWMW/graph.json","fetch_events":"https://pith.science/api/pith-number/2OTFVIQ3UNVLONUQKQXRLDVWMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW/action/storage_attestation","attest_author":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW/action/author_attestation","sign_citation":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW/action/citation_signature","submit_replication":"https://pith.science/pith/2OTFVIQ3UNVLONUQKQXRLDVWMW/action/replication_record"}},"created_at":"2026-07-05T10:28:52.421093+00:00","updated_at":"2026-07-05T10:28:52.421093+00:00"}