{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CODLIVC3YVY4CF75HACUGIM7MS","short_pith_number":"pith:CODLIVC3","schema_version":"1.0","canonical_sha256":"1386b4545bc571c117fd380543219f648d05e6e50a625bca4857ac03e84d5af3","source":{"kind":"arxiv","id":"2107.00520","version":5},"attestation_state":"computed","paper":{"title":"Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aahlad Puli, Eric K. Oermann, Lily H. Zhang, Rajesh Ranganath","submitted_at":"2021-06-29T18:12:59Z","abstract_excerpt":"In many prediction problems, spurious correlations are induced by a changing relationship between the label and a nuisance variable that is also correlated with the covariates. For example, in classifying animals in natural images, the background, which is a nuisance, can predict the type of animal. This nuisance-label relationship does not always hold, and the performance of a model trained under one such relationship may be poor on data with a different nuisance-label relationship. To build predictive models that perform well regardless of the nuisance-label relationship, we develop Nuisance"},"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":"2107.00520","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T18:12:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"81b1934e00a8a9e93e0ee98331909cc2e26e348543ed77cb1830d59d376bcc5d","abstract_canon_sha256":"0e820602a2afd62411dd81b41575c117e8463ff9c17a0e276b1ec7c1787dc8c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:43.000369Z","signature_b64":"6B7q0J3X/isa1SpKfCclGC32mYdZbK14eQ51iVfVSQ+7sPuDcR78CKjdMdDviXF8TWM+7i0MGC0pkdcX47/CBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1386b4545bc571c117fd380543219f648d05e6e50a625bca4857ac03e84d5af3","last_reissued_at":"2026-07-05T05:40:42.999857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:42.999857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aahlad Puli, Eric K. Oermann, Lily H. Zhang, Rajesh Ranganath","submitted_at":"2021-06-29T18:12:59Z","abstract_excerpt":"In many prediction problems, spurious correlations are induced by a changing relationship between the label and a nuisance variable that is also correlated with the covariates. For example, in classifying animals in natural images, the background, which is a nuisance, can predict the type of animal. This nuisance-label relationship does not always hold, and the performance of a model trained under one such relationship may be poor on data with a different nuisance-label relationship. To build predictive models that perform well regardless of the nuisance-label relationship, we develop Nuisance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00520","kind":"arxiv","version":5},"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/2107.00520/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":"2107.00520","created_at":"2026-07-05T05:40:42.999920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00520v5","created_at":"2026-07-05T05:40:42.999920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00520","created_at":"2026-07-05T05:40:42.999920+00:00"},{"alias_kind":"pith_short_12","alias_value":"CODLIVC3YVY4","created_at":"2026-07-05T05:40:42.999920+00:00"},{"alias_kind":"pith_short_16","alias_value":"CODLIVC3YVY4CF75","created_at":"2026-07-05T05:40:42.999920+00:00"},{"alias_kind":"pith_short_8","alias_value":"CODLIVC3","created_at":"2026-07-05T05:40:42.999920+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/CODLIVC3YVY4CF75HACUGIM7MS","json":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS.json","graph_json":"https://pith.science/api/pith-number/CODLIVC3YVY4CF75HACUGIM7MS/graph.json","events_json":"https://pith.science/api/pith-number/CODLIVC3YVY4CF75HACUGIM7MS/events.json","paper":"https://pith.science/paper/CODLIVC3"},"agent_actions":{"view_html":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS","download_json":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS.json","view_paper":"https://pith.science/paper/CODLIVC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00520&json=true","fetch_graph":"https://pith.science/api/pith-number/CODLIVC3YVY4CF75HACUGIM7MS/graph.json","fetch_events":"https://pith.science/api/pith-number/CODLIVC3YVY4CF75HACUGIM7MS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS/action/storage_attestation","attest_author":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS/action/author_attestation","sign_citation":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS/action/citation_signature","submit_replication":"https://pith.science/pith/CODLIVC3YVY4CF75HACUGIM7MS/action/replication_record"}},"created_at":"2026-07-05T05:40:42.999920+00:00","updated_at":"2026-07-05T05:40:42.999920+00:00"}