{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YZ7JDGWXN53UKXABBKL5BZG4UI","short_pith_number":"pith:YZ7JDGWX","schema_version":"1.0","canonical_sha256":"c67e919ad76f77455c010a97d0e4dca22ef5bbab63cbb99c1f2da372e614f757","source":{"kind":"arxiv","id":"2006.07544","version":2},"attestation_state":"computed","paper":{"title":"Risk Variance Penalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuanlong Xie, Fei Chen, Haotian Ye, Rui Sun, Yue Liu, Zhenguo Li","submitted_at":"2020-06-13T03:20:49Z","abstract_excerpt":"The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains. The variance risk extrapolation (V-REx) is a practical OOD method, which depends on a domain-level regularization but lacks theoretical verifications about its motivation and utility. This article provides theoretical insights into V-REx by studying a variance-based regularizer. We propose Risk Variance Penalization (RVP), which slightly changes the regularization of V-REx but addresses the theory concerns about V-REx. We provide theoretical explanations and a theory-ins"},"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":"2006.07544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T03:20:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"27df1c4fe78e3b0e0ecabccaa4d53ed3e68fc29d4efe32766d8306d2bdbab00d","abstract_canon_sha256":"333218f5c57d437eb4cd825cabd26a840be3405f5f14bb7091680bca73c2efb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:28.803711Z","signature_b64":"Xgc3YI65HIylZe0mTCPjaCR34juagqOdP0c67bKxQFs9Dd/iQB0o84nq8/3XpShRc9QfDHKgoN+AWY2w8matAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c67e919ad76f77455c010a97d0e4dca22ef5bbab63cbb99c1f2da372e614f757","last_reissued_at":"2026-07-05T02:30:28.803017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:28.803017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk Variance Penalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuanlong Xie, Fei Chen, Haotian Ye, Rui Sun, Yue Liu, Zhenguo Li","submitted_at":"2020-06-13T03:20:49Z","abstract_excerpt":"The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains. The variance risk extrapolation (V-REx) is a practical OOD method, which depends on a domain-level regularization but lacks theoretical verifications about its motivation and utility. This article provides theoretical insights into V-REx by studying a variance-based regularizer. We propose Risk Variance Penalization (RVP), which slightly changes the regularization of V-REx but addresses the theory concerns about V-REx. We provide theoretical explanations and a theory-ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07544","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/2006.07544/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":"2006.07544","created_at":"2026-07-05T02:30:28.803117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07544v2","created_at":"2026-07-05T02:30:28.803117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07544","created_at":"2026-07-05T02:30:28.803117+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZ7JDGWXN53U","created_at":"2026-07-05T02:30:28.803117+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZ7JDGWXN53UKXAB","created_at":"2026-07-05T02:30:28.803117+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZ7JDGWX","created_at":"2026-07-05T02:30:28.803117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08404","citing_title":"Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI","json":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI.json","graph_json":"https://pith.science/api/pith-number/YZ7JDGWXN53UKXABBKL5BZG4UI/graph.json","events_json":"https://pith.science/api/pith-number/YZ7JDGWXN53UKXABBKL5BZG4UI/events.json","paper":"https://pith.science/paper/YZ7JDGWX"},"agent_actions":{"view_html":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI","download_json":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI.json","view_paper":"https://pith.science/paper/YZ7JDGWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07544&json=true","fetch_graph":"https://pith.science/api/pith-number/YZ7JDGWXN53UKXABBKL5BZG4UI/graph.json","fetch_events":"https://pith.science/api/pith-number/YZ7JDGWXN53UKXABBKL5BZG4UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI/action/storage_attestation","attest_author":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI/action/author_attestation","sign_citation":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI/action/citation_signature","submit_replication":"https://pith.science/pith/YZ7JDGWXN53UKXABBKL5BZG4UI/action/replication_record"}},"created_at":"2026-07-05T02:30:28.803117+00:00","updated_at":"2026-07-05T02:30:28.803117+00:00"}