{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LCSHYDZ7V7FO32VDOR7ZE3LPGG","short_pith_number":"pith:LCSHYDZ7","schema_version":"1.0","canonical_sha256":"58a47c0f3fafcaedeaa3747f926d6f31aa81fe0dbee3556769fadee3599318b4","source":{"kind":"arxiv","id":"2201.12919","version":2},"attestation_state":"computed","paper":{"title":"Provable Domain Generalization via Invariant-Feature Subspace Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Han Zhao, Haoxiang Wang, Haozhe Si","submitted_at":"2022-01-30T21:22:47Z","abstract_excerpt":"Domain generalization asks for models trained over a set of training environments to perform well in unseen test environments. Recently, a series of algorithms such as Invariant Risk Minimization (IRM) has been proposed for domain generalization. However, Rosenfeld et al. (2021) shows that in a simple linear data model, even if non-convexity issues are ignored, IRM and its extensions cannot generalize to unseen environments with less than $d_s+1$ training environments, where $d_s$ is the dimension of the spurious-feature subspace. In this paper, we propose to achieve domain generalization with"},"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":"2201.12919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-30T21:22:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"89209013bbd38a9b3458574077d386142dcc78a809670ad70b461c063808db5c","abstract_canon_sha256":"cf3a29c4f0bdac96c3d970192488e12b40b45dc2611dca6b39cf94774dad76b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:13.737780Z","signature_b64":"TFVSvjQMYgD9SSwRoi1/V7UgrW57Snb8ggGVPB4vs2dPNOQGMBGPzmcQZAQCyYwmx6B8HoQT8jH1A2z62BsMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58a47c0f3fafcaedeaa3747f926d6f31aa81fe0dbee3556769fadee3599318b4","last_reissued_at":"2026-07-05T04:38:13.737434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:13.737434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Domain Generalization via Invariant-Feature Subspace Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Han Zhao, Haoxiang Wang, Haozhe Si","submitted_at":"2022-01-30T21:22:47Z","abstract_excerpt":"Domain generalization asks for models trained over a set of training environments to perform well in unseen test environments. Recently, a series of algorithms such as Invariant Risk Minimization (IRM) has been proposed for domain generalization. However, Rosenfeld et al. (2021) shows that in a simple linear data model, even if non-convexity issues are ignored, IRM and its extensions cannot generalize to unseen environments with less than $d_s+1$ training environments, where $d_s$ is the dimension of the spurious-feature subspace. In this paper, we propose to achieve domain generalization with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12919","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/2201.12919/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":"2201.12919","created_at":"2026-07-05T04:38:13.737491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12919v2","created_at":"2026-07-05T04:38:13.737491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12919","created_at":"2026-07-05T04:38:13.737491+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCSHYDZ7V7FO","created_at":"2026-07-05T04:38:13.737491+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCSHYDZ7V7FO32VD","created_at":"2026-07-05T04:38:13.737491+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCSHYDZ7","created_at":"2026-07-05T04:38:13.737491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07378","citing_title":"Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG","json":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG.json","graph_json":"https://pith.science/api/pith-number/LCSHYDZ7V7FO32VDOR7ZE3LPGG/graph.json","events_json":"https://pith.science/api/pith-number/LCSHYDZ7V7FO32VDOR7ZE3LPGG/events.json","paper":"https://pith.science/paper/LCSHYDZ7"},"agent_actions":{"view_html":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG","download_json":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG.json","view_paper":"https://pith.science/paper/LCSHYDZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12919&json=true","fetch_graph":"https://pith.science/api/pith-number/LCSHYDZ7V7FO32VDOR7ZE3LPGG/graph.json","fetch_events":"https://pith.science/api/pith-number/LCSHYDZ7V7FO32VDOR7ZE3LPGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG/action/storage_attestation","attest_author":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG/action/author_attestation","sign_citation":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG/action/citation_signature","submit_replication":"https://pith.science/pith/LCSHYDZ7V7FO32VDOR7ZE3LPGG/action/replication_record"}},"created_at":"2026-07-05T04:38:13.737491+00:00","updated_at":"2026-07-05T04:38:13.737491+00:00"}