{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EIQWE4WJ57FRUHD33AHCHA4LPC","short_pith_number":"pith:EIQWE4WJ","schema_version":"1.0","canonical_sha256":"22216272c9efcb1a1c7bd80e23838b78ab12c586147bb18cd0a8d5a7acf201ee","source":{"kind":"arxiv","id":"2505.15246","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Spurious Correlations with Causal Logit Perturbation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rui Xie, Shikun Zhang, Wei Ye, Xiaoling Zhou","submitted_at":"2025-05-21T08:21:02Z","abstract_excerpt":"Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness, relying on spurious correlations for predictions. Addressing these limitations is of paramount importance, necessitating the development of methods that can disentangle spurious correlations. {This study attempts to implement causal models via logit perturbations and introduces a novel Causal Logit Perturbation (CLP) framework to train classifiers with generated causal logit perturbations for individual samples, the"},"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":"2505.15246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T08:21:02Z","cross_cats_sorted":[],"title_canon_sha256":"49219b7954f95190f8802141edc7eff2e2a15f8aa97b2f345730649f120a998d","abstract_canon_sha256":"625a6c6548cf586ca5665f7ce3e1f0bb5d293967918887433c6d1035c8e1c054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:42.679051Z","signature_b64":"YPwE2QRVbNWNIefESwLnhU/4VcfJcjBSwe8hf90f7PxrnyshW7nObdjG4USsrVjqYUG7SelVFJM6a1Si3BBMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22216272c9efcb1a1c7bd80e23838b78ab12c586147bb18cd0a8d5a7acf201ee","last_reissued_at":"2026-07-05T11:06:42.678574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:42.678574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Spurious Correlations with Causal Logit Perturbation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rui Xie, Shikun Zhang, Wei Ye, Xiaoling Zhou","submitted_at":"2025-05-21T08:21:02Z","abstract_excerpt":"Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness, relying on spurious correlations for predictions. Addressing these limitations is of paramount importance, necessitating the development of methods that can disentangle spurious correlations. {This study attempts to implement causal models via logit perturbations and introduces a novel Causal Logit Perturbation (CLP) framework to train classifiers with generated causal logit perturbations for individual samples, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15246","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/2505.15246/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":"2505.15246","created_at":"2026-07-05T11:06:42.678631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15246v1","created_at":"2026-07-05T11:06:42.678631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15246","created_at":"2026-07-05T11:06:42.678631+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIQWE4WJ57FR","created_at":"2026-07-05T11:06:42.678631+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIQWE4WJ57FRUHD3","created_at":"2026-07-05T11:06:42.678631+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIQWE4WJ","created_at":"2026-07-05T11:06:42.678631+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/EIQWE4WJ57FRUHD33AHCHA4LPC","json":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC.json","graph_json":"https://pith.science/api/pith-number/EIQWE4WJ57FRUHD33AHCHA4LPC/graph.json","events_json":"https://pith.science/api/pith-number/EIQWE4WJ57FRUHD33AHCHA4LPC/events.json","paper":"https://pith.science/paper/EIQWE4WJ"},"agent_actions":{"view_html":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC","download_json":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC.json","view_paper":"https://pith.science/paper/EIQWE4WJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15246&json=true","fetch_graph":"https://pith.science/api/pith-number/EIQWE4WJ57FRUHD33AHCHA4LPC/graph.json","fetch_events":"https://pith.science/api/pith-number/EIQWE4WJ57FRUHD33AHCHA4LPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC/action/storage_attestation","attest_author":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC/action/author_attestation","sign_citation":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC/action/citation_signature","submit_replication":"https://pith.science/pith/EIQWE4WJ57FRUHD33AHCHA4LPC/action/replication_record"}},"created_at":"2026-07-05T11:06:42.678631+00:00","updated_at":"2026-07-05T11:06:42.678631+00:00"}