{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A6BAEY7CLEEITPJYETLL4TA7KD","short_pith_number":"pith:A6BAEY7C","schema_version":"1.0","canonical_sha256":"07820263e2590889bd3824d6be4c1f50d66e66de83933b460c10627cd44ffde5","source":{"kind":"arxiv","id":"2206.05263","version":4},"attestation_state":"computed","paper":{"title":"Causal Balancing for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hongyang Zhang, Jiachen Li, Kun Zhang, Michael Saxon, William Yang Wang, Xinyi Wang","submitted_at":"2022-06-10T17:59:11Z","abstract_excerpt":"While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. "},"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":"2206.05263","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-10T17:59:11Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"d57a72ebc085f80b5f3c4899b0cc2f89dc3dd0e5248dac7163a7a29b00573a75","abstract_canon_sha256":"e8b96726384e84ce629dd0c5d74d34914185acec7efb35706b5f89076dc9cc36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:11.858470Z","signature_b64":"WG6BinJBZveAHCOohPwo8Ka6BE/2ZbarRLgf1gsKBZOGBfDU962MUDMVlFF+hVSlimIlGtFAiUp8eEUqliXuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07820263e2590889bd3824d6be4c1f50d66e66de83933b460c10627cd44ffde5","last_reissued_at":"2026-07-05T05:43:11.858034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:11.858034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Balancing for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hongyang Zhang, Jiachen Li, Kun Zhang, Michael Saxon, William Yang Wang, Xinyi Wang","submitted_at":"2022-06-10T17:59:11Z","abstract_excerpt":"While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05263","kind":"arxiv","version":4},"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/2206.05263/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":"2206.05263","created_at":"2026-07-05T05:43:11.858088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.05263v4","created_at":"2026-07-05T05:43:11.858088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05263","created_at":"2026-07-05T05:43:11.858088+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6BAEY7CLEEI","created_at":"2026-07-05T05:43:11.858088+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6BAEY7CLEEITPJY","created_at":"2026-07-05T05:43:11.858088+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6BAEY7C","created_at":"2026-07-05T05:43:11.858088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21363","citing_title":"Subgroups Matter for Robust Bias Mitigation","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD","json":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD.json","graph_json":"https://pith.science/api/pith-number/A6BAEY7CLEEITPJYETLL4TA7KD/graph.json","events_json":"https://pith.science/api/pith-number/A6BAEY7CLEEITPJYETLL4TA7KD/events.json","paper":"https://pith.science/paper/A6BAEY7C"},"agent_actions":{"view_html":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD","download_json":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD.json","view_paper":"https://pith.science/paper/A6BAEY7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.05263&json=true","fetch_graph":"https://pith.science/api/pith-number/A6BAEY7CLEEITPJYETLL4TA7KD/graph.json","fetch_events":"https://pith.science/api/pith-number/A6BAEY7CLEEITPJYETLL4TA7KD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD/action/storage_attestation","attest_author":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD/action/author_attestation","sign_citation":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD/action/citation_signature","submit_replication":"https://pith.science/pith/A6BAEY7CLEEITPJYETLL4TA7KD/action/replication_record"}},"created_at":"2026-07-05T05:43:11.858088+00:00","updated_at":"2026-07-05T05:43:11.858088+00:00"}