{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LO24FIYIKFK57Z4KKVGTL62ECF","short_pith_number":"pith:LO24FIYI","schema_version":"1.0","canonical_sha256":"5bb5c2a3085155dfe78a554d35fb441156f5518627bcbe0efb1df70ffa90fb7f","source":{"kind":"arxiv","id":"2507.09640","version":1},"attestation_state":"computed","paper":{"title":"Disentanglement and Assessment of Shortcuts in Ophthalmological Retinal Imaging Exams","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaime S. Cardoso, Jo\\~ao Matos, Leonor Fernandes, Luis Filipe Nakayama, Tiago Gon\\c{c}alves","submitted_at":"2025-07-13T14:11:41Z","abstract_excerpt":"Diabetic retinopathy (DR) is a leading cause of vision loss in working-age adults. While screening reduces the risk of blindness, traditional imaging is often costly and inaccessible. Artificial intelligence (AI) algorithms present a scalable diagnostic solution, but concerns regarding fairness and generalization persist. This work evaluates the fairness and performance of image-trained models in DR prediction, as well as the impact of disentanglement as a bias mitigation technique, using the diverse mBRSET fundus dataset. Three models, ConvNeXt V2, DINOv2, and Swin V2, were trained on macula "},"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":"2507.09640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T14:11:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a8db8dbd99595f915f7dd7e51e31c85f1bf9943d461400484b2246b7e92a1a85","abstract_canon_sha256":"a2b003c96b9525966234c64dc63995e3cabf1fed49ba5a1f7bcb9244b342c667"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:37.250398Z","signature_b64":"oeXxjO9h2bjZ1ngK9BL/JzMht0f8ACt1Buj19AAo+YTtzjlqGemO6lANdx2zoX1Do/UmugBgyDAxN62vTukPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bb5c2a3085155dfe78a554d35fb441156f5518627bcbe0efb1df70ffa90fb7f","last_reissued_at":"2026-07-05T11:36:37.249981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:37.249981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentanglement and Assessment of Shortcuts in Ophthalmological Retinal Imaging Exams","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaime S. Cardoso, Jo\\~ao Matos, Leonor Fernandes, Luis Filipe Nakayama, Tiago Gon\\c{c}alves","submitted_at":"2025-07-13T14:11:41Z","abstract_excerpt":"Diabetic retinopathy (DR) is a leading cause of vision loss in working-age adults. While screening reduces the risk of blindness, traditional imaging is often costly and inaccessible. Artificial intelligence (AI) algorithms present a scalable diagnostic solution, but concerns regarding fairness and generalization persist. This work evaluates the fairness and performance of image-trained models in DR prediction, as well as the impact of disentanglement as a bias mitigation technique, using the diverse mBRSET fundus dataset. Three models, ConvNeXt V2, DINOv2, and Swin V2, were trained on macula "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09640","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/2507.09640/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":"2507.09640","created_at":"2026-07-05T11:36:37.250042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09640v1","created_at":"2026-07-05T11:36:37.250042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09640","created_at":"2026-07-05T11:36:37.250042+00:00"},{"alias_kind":"pith_short_12","alias_value":"LO24FIYIKFK5","created_at":"2026-07-05T11:36:37.250042+00:00"},{"alias_kind":"pith_short_16","alias_value":"LO24FIYIKFK57Z4K","created_at":"2026-07-05T11:36:37.250042+00:00"},{"alias_kind":"pith_short_8","alias_value":"LO24FIYI","created_at":"2026-07-05T11:36:37.250042+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/LO24FIYIKFK57Z4KKVGTL62ECF","json":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF.json","graph_json":"https://pith.science/api/pith-number/LO24FIYIKFK57Z4KKVGTL62ECF/graph.json","events_json":"https://pith.science/api/pith-number/LO24FIYIKFK57Z4KKVGTL62ECF/events.json","paper":"https://pith.science/paper/LO24FIYI"},"agent_actions":{"view_html":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF","download_json":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF.json","view_paper":"https://pith.science/paper/LO24FIYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09640&json=true","fetch_graph":"https://pith.science/api/pith-number/LO24FIYIKFK57Z4KKVGTL62ECF/graph.json","fetch_events":"https://pith.science/api/pith-number/LO24FIYIKFK57Z4KKVGTL62ECF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF/action/storage_attestation","attest_author":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF/action/author_attestation","sign_citation":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF/action/citation_signature","submit_replication":"https://pith.science/pith/LO24FIYIKFK57Z4KKVGTL62ECF/action/replication_record"}},"created_at":"2026-07-05T11:36:37.250042+00:00","updated_at":"2026-07-05T11:36:37.250042+00:00"}