{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5RGN6ATYB4KZPQZB4HRAE4ZZEM","short_pith_number":"pith:5RGN6ATY","schema_version":"1.0","canonical_sha256":"ec4cdf02780f1597c321e1e2027339232087a6823a42061283d0752eeb0d62b0","source":{"kind":"arxiv","id":"2412.05152","version":1},"attestation_state":"computed","paper":{"title":"Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonia W\\\"ust, David Steinmann, Felix Divo, Felix Friedrich, Kristian Kersting, Lukas Struppek, Maurice Kraus","submitted_at":"2024-12-06T16:10:13Z","abstract_excerpt":"Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in this area, however, remains fragmented across various terminologies, hindering the progress of the field as a whole. Consequently, we introduce a unifying taxonomy of shortcut learning by providing a formal definition of shortcuts and bridging the diverse terms used in the literature. In doing so, we further establish important connections between shortcuts and related fields, "},"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":"2412.05152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T16:10:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ea16b1a6eb427d8d17cbb670364919dafa8fc9d8f85ce06d11fae4682e29f55","abstract_canon_sha256":"e662b801d6fe41521dbe9852f85718678197c8818f9a0bc73d28723f44fced66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:29.451532Z","signature_b64":"qSCVqQTL8mbyRByPppGBpbCS1UwGX0ZvVkK5DhtZM5BurffV1Q+7/Lha8YwqqIGmHY0j0Phg/aVRApuzAr4VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec4cdf02780f1597c321e1e2027339232087a6823a42061283d0752eeb0d62b0","last_reissued_at":"2026-07-05T09:45:29.451050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:29.451050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonia W\\\"ust, David Steinmann, Felix Divo, Felix Friedrich, Kristian Kersting, Lukas Struppek, Maurice Kraus","submitted_at":"2024-12-06T16:10:13Z","abstract_excerpt":"Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in this area, however, remains fragmented across various terminologies, hindering the progress of the field as a whole. Consequently, we introduce a unifying taxonomy of shortcut learning by providing a formal definition of shortcuts and bridging the diverse terms used in the literature. In doing so, we further establish important connections between shortcuts and related fields, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05152","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/2412.05152/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":"2412.05152","created_at":"2026-07-05T09:45:29.451108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05152v1","created_at":"2026-07-05T09:45:29.451108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05152","created_at":"2026-07-05T09:45:29.451108+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RGN6ATYB4KZ","created_at":"2026-07-05T09:45:29.451108+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RGN6ATYB4KZPQZB","created_at":"2026-07-05T09:45:29.451108+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RGN6ATY","created_at":"2026-07-05T09:45:29.451108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28194","citing_title":"COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26855","citing_title":"Receipt Replay OOD: A Small Benchmark for Screen Replay Detection Under Domain Shift","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18502","citing_title":"Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26676","citing_title":"A Toolkit for Detecting Spurious Correlations in Speech Datasets","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14477","citing_title":"Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04717","citing_title":"The Infinite-Dimensional Nature of Spectroscopy and Why Models Succeed, Fail, and Mislead","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM","json":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM.json","graph_json":"https://pith.science/api/pith-number/5RGN6ATYB4KZPQZB4HRAE4ZZEM/graph.json","events_json":"https://pith.science/api/pith-number/5RGN6ATYB4KZPQZB4HRAE4ZZEM/events.json","paper":"https://pith.science/paper/5RGN6ATY"},"agent_actions":{"view_html":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM","download_json":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM.json","view_paper":"https://pith.science/paper/5RGN6ATY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05152&json=true","fetch_graph":"https://pith.science/api/pith-number/5RGN6ATYB4KZPQZB4HRAE4ZZEM/graph.json","fetch_events":"https://pith.science/api/pith-number/5RGN6ATYB4KZPQZB4HRAE4ZZEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM/action/storage_attestation","attest_author":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM/action/author_attestation","sign_citation":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM/action/citation_signature","submit_replication":"https://pith.science/pith/5RGN6ATYB4KZPQZB4HRAE4ZZEM/action/replication_record"}},"created_at":"2026-07-05T09:45:29.451108+00:00","updated_at":"2026-07-05T09:45:29.451108+00:00"}