{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EHZFG66NAM3KDGVCOIJ5W37FBB","short_pith_number":"pith:EHZFG66N","schema_version":"1.0","canonical_sha256":"21f2537bcd0336a19aa27213db6fe508707727dc105a2432cde8bcc6b3685657","source":{"kind":"arxiv","id":"2207.12020","version":2},"attestation_state":"computed","paper":{"title":"Domain-invariant Feature Exploration for Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Haoliang Li, Jindong Wang, Wang Lu, Xing Xie, Yiqiang Chen","submitted_at":"2022-07-25T09:55:55Z","abstract_excerpt":"Deep learning has achieved great success in the past few years. However, the performance of deep learning is likely to impede in face of non-IID situations. Domain generalization (DG) enables a model to generalize to an unseen test distribution, i.e., to learn domain-invariant representations. In this paper, we argue that domain-invariant features should be originating from both internal and mutual sides. Internal invariance means that the features can be learned with a single domain and the features capture intrinsic semantics of data, i.e., the property within a domain, which is agnostic to "},"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":"2207.12020","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-25T09:55:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4f31215b27ceceb59cb5158b9f71b52c904c1388e851922c94f7eca4dabfc393","abstract_canon_sha256":"20b6e99eb32452bfaa909283eb15d3ecc0a3ae267674285a1f4db8562a4c29aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:08.406893Z","signature_b64":"EbW/Fj/z0yqBWevAF1QzGj+CsuFD7JEQMpZrQ9ClGBtAPI3EtSB8AH4F1+bk/5NVdvXnl0R0A8ht+4qqcN+LCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21f2537bcd0336a19aa27213db6fe508707727dc105a2432cde8bcc6b3685657","last_reissued_at":"2026-07-05T05:28:08.406488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:08.406488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-invariant Feature Exploration for Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Haoliang Li, Jindong Wang, Wang Lu, Xing Xie, Yiqiang Chen","submitted_at":"2022-07-25T09:55:55Z","abstract_excerpt":"Deep learning has achieved great success in the past few years. However, the performance of deep learning is likely to impede in face of non-IID situations. Domain generalization (DG) enables a model to generalize to an unseen test distribution, i.e., to learn domain-invariant representations. In this paper, we argue that domain-invariant features should be originating from both internal and mutual sides. Internal invariance means that the features can be learned with a single domain and the features capture intrinsic semantics of data, i.e., the property within a domain, which is agnostic to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12020","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/2207.12020/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":"2207.12020","created_at":"2026-07-05T05:28:08.406554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12020v2","created_at":"2026-07-05T05:28:08.406554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12020","created_at":"2026-07-05T05:28:08.406554+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHZFG66NAM3K","created_at":"2026-07-05T05:28:08.406554+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHZFG66NAM3KDGVC","created_at":"2026-07-05T05:28:08.406554+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHZFG66N","created_at":"2026-07-05T05:28:08.406554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04009","citing_title":"Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB","json":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB.json","graph_json":"https://pith.science/api/pith-number/EHZFG66NAM3KDGVCOIJ5W37FBB/graph.json","events_json":"https://pith.science/api/pith-number/EHZFG66NAM3KDGVCOIJ5W37FBB/events.json","paper":"https://pith.science/paper/EHZFG66N"},"agent_actions":{"view_html":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB","download_json":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB.json","view_paper":"https://pith.science/paper/EHZFG66N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12020&json=true","fetch_graph":"https://pith.science/api/pith-number/EHZFG66NAM3KDGVCOIJ5W37FBB/graph.json","fetch_events":"https://pith.science/api/pith-number/EHZFG66NAM3KDGVCOIJ5W37FBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB/action/storage_attestation","attest_author":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB/action/author_attestation","sign_citation":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB/action/citation_signature","submit_replication":"https://pith.science/pith/EHZFG66NAM3KDGVCOIJ5W37FBB/action/replication_record"}},"created_at":"2026-07-05T05:28:08.406554+00:00","updated_at":"2026-07-05T05:28:08.406554+00:00"}