{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:43DPVC5VL6QMESMHSVOMKDAC5Q","short_pith_number":"pith:43DPVC5V","schema_version":"1.0","canonical_sha256":"e6c6fa8bb55fa0c24987955cc50c02ec3ef6775a4d2e19a77d30b2c70c7b96f2","source":{"kind":"arxiv","id":"2007.10573","version":2},"attestation_state":"computed","paper":{"title":"Domain Generalization via Optimal Transport with Metric Similarity Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boyu Wang, Brahim Chaib-draa, Changjian Shui, Fan Zhou, Zhuqing Jiang","submitted_at":"2020-07-21T02:56:05Z","abstract_excerpt":"Generalizing knowledge to unseen domains, where data and labels are unavailable, is crucial for machine learning models. We tackle the domain generalization problem to learn from multiple source domains and generalize to a target domain with unknown statistics. The crucial idea is to extract the underlying invariant features across all the domains. Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indisting"},"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":"2007.10573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-21T02:56:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7137c0882ee6eb680fb1863e2fe30a47ef480060db0de20b02b750c650ef145","abstract_canon_sha256":"9e019d9d94f5e034d100c9f2335565ea24d98f75ae4bffc9445938853642171c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:23.331144Z","signature_b64":"7+7yiKRUPQurHIaFnAPM/gNaAvPb34bXmG7yClnob21mikjczBY2FSJ1JoGvltu/XezDCTGQiahO3UYw98p5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6c6fa8bb55fa0c24987955cc50c02ec3ef6775a4d2e19a77d30b2c70c7b96f2","last_reissued_at":"2026-07-05T04:11:23.330705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:23.330705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Generalization via Optimal Transport with Metric Similarity Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boyu Wang, Brahim Chaib-draa, Changjian Shui, Fan Zhou, Zhuqing Jiang","submitted_at":"2020-07-21T02:56:05Z","abstract_excerpt":"Generalizing knowledge to unseen domains, where data and labels are unavailable, is crucial for machine learning models. We tackle the domain generalization problem to learn from multiple source domains and generalize to a target domain with unknown statistics. The crucial idea is to extract the underlying invariant features across all the domains. Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indisting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10573","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/2007.10573/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":"2007.10573","created_at":"2026-07-05T04:11:23.330757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.10573v2","created_at":"2026-07-05T04:11:23.330757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10573","created_at":"2026-07-05T04:11:23.330757+00:00"},{"alias_kind":"pith_short_12","alias_value":"43DPVC5VL6QM","created_at":"2026-07-05T04:11:23.330757+00:00"},{"alias_kind":"pith_short_16","alias_value":"43DPVC5VL6QMESMH","created_at":"2026-07-05T04:11:23.330757+00:00"},{"alias_kind":"pith_short_8","alias_value":"43DPVC5V","created_at":"2026-07-05T04:11:23.330757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01109","citing_title":"BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q","json":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q.json","graph_json":"https://pith.science/api/pith-number/43DPVC5VL6QMESMHSVOMKDAC5Q/graph.json","events_json":"https://pith.science/api/pith-number/43DPVC5VL6QMESMHSVOMKDAC5Q/events.json","paper":"https://pith.science/paper/43DPVC5V"},"agent_actions":{"view_html":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q","download_json":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q.json","view_paper":"https://pith.science/paper/43DPVC5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.10573&json=true","fetch_graph":"https://pith.science/api/pith-number/43DPVC5VL6QMESMHSVOMKDAC5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/43DPVC5VL6QMESMHSVOMKDAC5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q/action/storage_attestation","attest_author":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q/action/author_attestation","sign_citation":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q/action/citation_signature","submit_replication":"https://pith.science/pith/43DPVC5VL6QMESMHSVOMKDAC5Q/action/replication_record"}},"created_at":"2026-07-05T04:11:23.330757+00:00","updated_at":"2026-07-05T04:11:23.330757+00:00"}