{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GLZEE7MDL47GRRUDJVQRIQFOS7","short_pith_number":"pith:GLZEE7MD","schema_version":"1.0","canonical_sha256":"32f2427d835f3e68c6834d611440ae97ed869a7dfff1fdb270f8ce9333105a2c","source":{"kind":"arxiv","id":"2509.09558","version":1},"attestation_state":"computed","paper":{"title":"Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Akshit Achara, Alexander Hammers, Andrew P. King, Esther Puyol Anton","submitted_at":"2025-09-11T15:48:30Z","abstract_excerpt":"Magnetic resonance imaging (MRI) is the gold standard for brain imaging. Deep learning (DL) algorithms have been proposed to aid in the diagnosis of diseases such as Alzheimer's disease (AD) from MRI scans. However, DL algorithms can suffer from shortcut learning, in which spurious features, not directly related to the output label, are used for prediction. When these features are related to protected attributes, they can lead to performance bias against underrepresented protected groups, such as those defined by race and sex. In this work, we explore the potential for shortcut learning and de"},"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":"2509.09558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T15:48:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f7b3599fbbd843ed837493f573ec3a8fd7b04c823cb3b61cf442cd5b2475dbf","abstract_canon_sha256":"1f3d53b84042ef1e70b4185b1c97594e762d932d5a15b09d62498d95c86992f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:38.145358Z","signature_b64":"s7Rbm8Lu0sMrmY6++/U2cz4+UWx9dDdI97YEd8cHiGEht/ehfWXQNxEcyz0/PHbsVJtlUKsU2h84KBQDGV0pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32f2427d835f3e68c6834d611440ae97ed869a7dfff1fdb270f8ce9333105a2c","last_reissued_at":"2026-07-05T12:09:38.144705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:38.144705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Akshit Achara, Alexander Hammers, Andrew P. King, Esther Puyol Anton","submitted_at":"2025-09-11T15:48:30Z","abstract_excerpt":"Magnetic resonance imaging (MRI) is the gold standard for brain imaging. Deep learning (DL) algorithms have been proposed to aid in the diagnosis of diseases such as Alzheimer's disease (AD) from MRI scans. However, DL algorithms can suffer from shortcut learning, in which spurious features, not directly related to the output label, are used for prediction. When these features are related to protected attributes, they can lead to performance bias against underrepresented protected groups, such as those defined by race and sex. In this work, we explore the potential for shortcut learning and de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09558","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/2509.09558/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":"2509.09558","created_at":"2026-07-05T12:09:38.144787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09558v1","created_at":"2026-07-05T12:09:38.144787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09558","created_at":"2026-07-05T12:09:38.144787+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLZEE7MDL47G","created_at":"2026-07-05T12:09:38.144787+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLZEE7MDL47GRRUD","created_at":"2026-07-05T12:09:38.144787+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLZEE7MD","created_at":"2026-07-05T12:09:38.144787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11161","citing_title":"Interpretability Can Be Actionable","ref_index":136,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7","json":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7.json","graph_json":"https://pith.science/api/pith-number/GLZEE7MDL47GRRUDJVQRIQFOS7/graph.json","events_json":"https://pith.science/api/pith-number/GLZEE7MDL47GRRUDJVQRIQFOS7/events.json","paper":"https://pith.science/paper/GLZEE7MD"},"agent_actions":{"view_html":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7","download_json":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7.json","view_paper":"https://pith.science/paper/GLZEE7MD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09558&json=true","fetch_graph":"https://pith.science/api/pith-number/GLZEE7MDL47GRRUDJVQRIQFOS7/graph.json","fetch_events":"https://pith.science/api/pith-number/GLZEE7MDL47GRRUDJVQRIQFOS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7/action/storage_attestation","attest_author":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7/action/author_attestation","sign_citation":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7/action/citation_signature","submit_replication":"https://pith.science/pith/GLZEE7MDL47GRRUDJVQRIQFOS7/action/replication_record"}},"created_at":"2026-07-05T12:09:38.144787+00:00","updated_at":"2026-07-05T12:09:38.144787+00:00"}