{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IRUFBSKZK6RN2F4BYGE2F44J5Z","short_pith_number":"pith:IRUFBSKZ","schema_version":"1.0","canonical_sha256":"446850c95957a2dd1781c189a2f389ee643e91c7e8240cec4b70ec6a9fcd1417","source":{"kind":"arxiv","id":"1807.08479","version":1},"attestation_state":"computed","paper":{"title":"Domain Generalization via Conditional Invariant Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Mingming Gong, Tongliang Liu, Xinmei Tian, Ya Li","submitted_at":"2018-07-23T08:33:46Z","abstract_excerpt":"Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: training data and test data have different distributions, and the training set contains heterogeneous samples from different distributions. Let $X$ denote the features, and $Y$ be the class labels. Existing domain generalization methods address the dataset bias problem by learning a domain-invariant representation $h(X)$ that has the same marginal distribution $\\mathbb{P}(h(X))$ across multiple source domains. The functional relati"},"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":"1807.08479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-07-23T08:33:46Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"524b689d7e78c4a0f260d5c8f97e193832c9da1a99c7fa4a3c02c622f6162b9b","abstract_canon_sha256":"9b0a0bf7d4d4ca815ac1655cdd6e99ee60aa4494bf24794601d28921fd10488a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:07.874078Z","signature_b64":"zcP2zLRW17RKHTRnJKuH78sTBB+xUK/AAXyc8LdDhWmyFJQKCxGC9HcpTU8eOdksPogFm0xTNbZCvalF5z9TDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446850c95957a2dd1781c189a2f389ee643e91c7e8240cec4b70ec6a9fcd1417","last_reissued_at":"2026-05-18T00:10:07.873662Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:07.873662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Generalization via Conditional Invariant Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Mingming Gong, Tongliang Liu, Xinmei Tian, Ya Li","submitted_at":"2018-07-23T08:33:46Z","abstract_excerpt":"Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: training data and test data have different distributions, and the training set contains heterogeneous samples from different distributions. Let $X$ denote the features, and $Y$ be the class labels. Existing domain generalization methods address the dataset bias problem by learning a domain-invariant representation $h(X)$ that has the same marginal distribution $\\mathbb{P}(h(X))$ across multiple source domains. The functional relati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08479","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":""},"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":"1807.08479","created_at":"2026-05-18T00:10:07.873729+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.08479v1","created_at":"2026-05-18T00:10:07.873729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08479","created_at":"2026-05-18T00:10:07.873729+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRUFBSKZK6RN","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRUFBSKZK6RN2F4B","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRUFBSKZ","created_at":"2026-05-18T12:32:31.084164+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/IRUFBSKZK6RN2F4BYGE2F44J5Z","json":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z.json","graph_json":"https://pith.science/api/pith-number/IRUFBSKZK6RN2F4BYGE2F44J5Z/graph.json","events_json":"https://pith.science/api/pith-number/IRUFBSKZK6RN2F4BYGE2F44J5Z/events.json","paper":"https://pith.science/paper/IRUFBSKZ"},"agent_actions":{"view_html":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z","download_json":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z.json","view_paper":"https://pith.science/paper/IRUFBSKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.08479&json=true","fetch_graph":"https://pith.science/api/pith-number/IRUFBSKZK6RN2F4BYGE2F44J5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/IRUFBSKZK6RN2F4BYGE2F44J5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z/action/storage_attestation","attest_author":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z/action/author_attestation","sign_citation":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z/action/citation_signature","submit_replication":"https://pith.science/pith/IRUFBSKZK6RN2F4BYGE2F44J5Z/action/replication_record"}},"created_at":"2026-05-18T00:10:07.873729+00:00","updated_at":"2026-05-18T00:10:07.873729+00:00"}