{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QVACMBIA5EFZHC5JIOD7JB4UKY","short_pith_number":"pith:QVACMBIA","schema_version":"1.0","canonical_sha256":"8540260500e90b938ba94387f48794563bc4b07c85b9ff8acf784c45e2241fc2","source":{"kind":"arxiv","id":"1910.04597","version":1},"attestation_state":"computed","paper":{"title":"Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","q-bio.NC"],"primary_cat":"eess.IV","authors_text":"Ben Glocker, Daniel C. Castro, Ender Konukoglu, Qi Dou, Robert Robinson","submitted_at":"2019-10-10T14:24:42Z","abstract_excerpt":"This is an empirical study to investigate the impact of scanner effects when using machine learning on multi-site neuroimaging data. We utilize structural T1-weighted brain MRI obtained from two different studies, Cam-CAN and UK Biobank. For the purpose of our investigation, we construct a dataset consisting of brain scans from 592 age- and sex-matched individuals, 296 subjects from each original study. Our results demonstrate that even after careful pre-processing with state-of-the-art neuroimaging pipelines a classifier can easily distinguish between the origin of the data with very high acc"},"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":"1910.04597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2019-10-10T14:24:42Z","cross_cats_sorted":["cs.CV","cs.LG","q-bio.NC"],"title_canon_sha256":"5e6d43cb8ac902890b03b4816fdacfc9cfe7f061297dbe397e6afb37609daf2b","abstract_canon_sha256":"d884061e65c35ed35a815a0569ff23ee1260e8b5eb699a33cb3ef5d43c098401"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:09.794174Z","signature_b64":"+z0ItNBSRNyGFp30KCuV1tkWTlfOCGsjFzWTD+wm0qOEhQ8Aw8K69pA/UWYu7oiTYlp6+VMyMGE8UjmiBGmKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8540260500e90b938ba94387f48794563bc4b07c85b9ff8acf784c45e2241fc2","last_reissued_at":"2026-07-05T00:11:09.793677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:09.793677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","q-bio.NC"],"primary_cat":"eess.IV","authors_text":"Ben Glocker, Daniel C. Castro, Ender Konukoglu, Qi Dou, Robert Robinson","submitted_at":"2019-10-10T14:24:42Z","abstract_excerpt":"This is an empirical study to investigate the impact of scanner effects when using machine learning on multi-site neuroimaging data. We utilize structural T1-weighted brain MRI obtained from two different studies, Cam-CAN and UK Biobank. For the purpose of our investigation, we construct a dataset consisting of brain scans from 592 age- and sex-matched individuals, 296 subjects from each original study. Our results demonstrate that even after careful pre-processing with state-of-the-art neuroimaging pipelines a classifier can easily distinguish between the origin of the data with very high acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04597","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/1910.04597/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":"1910.04597","created_at":"2026-07-05T00:11:09.793734+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.04597v1","created_at":"2026-07-05T00:11:09.793734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04597","created_at":"2026-07-05T00:11:09.793734+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVACMBIA5EFZ","created_at":"2026-07-05T00:11:09.793734+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVACMBIA5EFZHC5J","created_at":"2026-07-05T00:11:09.793734+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVACMBIA","created_at":"2026-07-05T00:11:09.793734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25685","citing_title":"Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deployment","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01563","citing_title":"Multi-Dataset Cross-Domain Knowledge Distillation for Unified Medical Image Segmentation, Classification, and Detection","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00904","citing_title":"Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY","json":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY.json","graph_json":"https://pith.science/api/pith-number/QVACMBIA5EFZHC5JIOD7JB4UKY/graph.json","events_json":"https://pith.science/api/pith-number/QVACMBIA5EFZHC5JIOD7JB4UKY/events.json","paper":"https://pith.science/paper/QVACMBIA"},"agent_actions":{"view_html":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY","download_json":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY.json","view_paper":"https://pith.science/paper/QVACMBIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.04597&json=true","fetch_graph":"https://pith.science/api/pith-number/QVACMBIA5EFZHC5JIOD7JB4UKY/graph.json","fetch_events":"https://pith.science/api/pith-number/QVACMBIA5EFZHC5JIOD7JB4UKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY/action/storage_attestation","attest_author":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY/action/author_attestation","sign_citation":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY/action/citation_signature","submit_replication":"https://pith.science/pith/QVACMBIA5EFZHC5JIOD7JB4UKY/action/replication_record"}},"created_at":"2026-07-05T00:11:09.793734+00:00","updated_at":"2026-07-05T00:11:09.793734+00:00"}