{"id":"W4402023450","doi":"10.1016/j.jmir.2024.101745","title":"From code sharing to sharing of implementations: Advancing reproducible AI development for medical imaging through federated testing","year":2024,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Implementation; Computer science; Code (set theory); Medical imaging; Software engineering; Programming language; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03264195,0.0001289482,0.0003119141,0.0006513093,0.0006234574,0.001778919,0.001249616,0.00002964702,0.0001740156],"category_scores_gemma":[0.03347569,0.00008953743,0.00006915305,0.001725194,0.0002018917,0.001300166,0.0005475695,0.0002184345,0.000006261537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007292127,"about_ca_system_score_gemma":0.0008198276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001757693,"about_ca_topic_score_gemma":0.00003614901,"domain_scores_codex":[0.9928627,0.00007853492,0.001702332,0.0008905806,0.004122796,0.0003430546],"domain_scores_gemma":[0.9947432,0.003538242,0.0005136151,0.0002779636,0.0005670112,0.0003599797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001274147,0.00003666086,0.02410798,0.00003527338,0.0000310079,0.00003422935,0.004654165,0.00115003,0.0005036894,0.0004842268,0.03950225,0.9294478],"study_design_scores_gemma":[0.0005584249,0.00003877676,0.004186231,0.001339145,0.0000300732,0.00009995824,0.01407784,0.903038,0.001280416,0.01522863,0.05993083,0.0001916309],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2588933,0.003830745,0.6775982,0.05540434,0.003779214,0.0001954832,0.00001476426,0.00005063678,0.0002333502],"genre_scores_gemma":[0.931432,0.00008122122,0.06567644,0.001762348,0.0009323152,0.000007164829,0.000006791054,0.0000114676,0.00009021744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9292561,"threshold_uncertainty_score":0.9992573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1391681261849896,"score_gpt":0.4764190222022526,"score_spread":0.3372508960172629,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}