{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CRAAJNMEU4RKAUBMPB2ZIMO4NH","short_pith_number":"pith:CRAAJNME","schema_version":"1.0","canonical_sha256":"144004b584a722a0502c78759431dc69e56990b6dc36c3c6b6d37c47cb3b797b","source":{"kind":"arxiv","id":"2506.00407","version":1},"attestation_state":"computed","paper":{"title":"Bias as a Virtue: Rethinking Generalization under Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiahui Xiao, Ruixuan Chen, Wentao Li, Xiaonan Wang, Yimin Tang, Yuchen Li","submitted_at":"2025-05-31T05:54:49Z","abstract_excerpt":"Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that higher in-distribution (ID) bias can lead to better out-of-distribution (OOD) generalization. Our Adaptive Distribution Bridge (ADB) framework implements this insight by introducing controlled statistical diversity during training, enabling models to develop bias profiles that effectively generalize across distributions. Empirically, we observe a robust negative correlation where higher ID bias corresponds to lower OOD "},"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":"2506.00407","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T05:54:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"27da7f30a09c4682dcbfcdb113a6bc47ceb906eb2ae7e051c175c0129972311f","abstract_canon_sha256":"04ee44c54c05dbaef1d678841196f295b408456e8f42ea2afce1b0b121a564c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:34.248623Z","signature_b64":"8mX813SDbYZ3/th9Hc3TCv3yZmEj7bKDbclbEvNpGQue/+X2qHg3NMK2SoftCeCCpflv0WO3AnXcxTToQKjfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"144004b584a722a0502c78759431dc69e56990b6dc36c3c6b6d37c47cb3b797b","last_reissued_at":"2026-07-05T11:13:34.248194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:34.248194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bias as a Virtue: Rethinking Generalization under Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiahui Xiao, Ruixuan Chen, Wentao Li, Xiaonan Wang, Yimin Tang, Yuchen Li","submitted_at":"2025-05-31T05:54:49Z","abstract_excerpt":"Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that higher in-distribution (ID) bias can lead to better out-of-distribution (OOD) generalization. Our Adaptive Distribution Bridge (ADB) framework implements this insight by introducing controlled statistical diversity during training, enabling models to develop bias profiles that effectively generalize across distributions. Empirically, we observe a robust negative correlation where higher ID bias corresponds to lower OOD "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00407","kind":"arxiv","version":1},"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/2506.00407/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":"2506.00407","created_at":"2026-07-05T11:13:34.248257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00407v1","created_at":"2026-07-05T11:13:34.248257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00407","created_at":"2026-07-05T11:13:34.248257+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRAAJNMEU4RK","created_at":"2026-07-05T11:13:34.248257+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRAAJNMEU4RKAUBM","created_at":"2026-07-05T11:13:34.248257+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRAAJNME","created_at":"2026-07-05T11:13:34.248257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH","json":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH.json","graph_json":"https://pith.science/api/pith-number/CRAAJNMEU4RKAUBMPB2ZIMO4NH/graph.json","events_json":"https://pith.science/api/pith-number/CRAAJNMEU4RKAUBMPB2ZIMO4NH/events.json","paper":"https://pith.science/paper/CRAAJNME"},"agent_actions":{"view_html":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH","download_json":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH.json","view_paper":"https://pith.science/paper/CRAAJNME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00407&json=true","fetch_graph":"https://pith.science/api/pith-number/CRAAJNMEU4RKAUBMPB2ZIMO4NH/graph.json","fetch_events":"https://pith.science/api/pith-number/CRAAJNMEU4RKAUBMPB2ZIMO4NH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH/action/storage_attestation","attest_author":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH/action/author_attestation","sign_citation":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH/action/citation_signature","submit_replication":"https://pith.science/pith/CRAAJNMEU4RKAUBMPB2ZIMO4NH/action/replication_record"}},"created_at":"2026-07-05T11:13:34.248257+00:00","updated_at":"2026-07-05T11:13:34.248257+00:00"}