{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.05905929,0.001687716,0.001735238,0.002558037,0.001905135,0.01067549,0.007849782,0.003645161,0.00423256],"category_scores_gemma":[0.2067754,0.001638396,0.002090564,0.001539646,0.006792325,0.01810911,0.01644694,0.008097724,0.001983619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002004859,"about_ca_system_score_gemma":0.01407201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003189013,"about_ca_topic_score_gemma":0.002791334,"domain_scores_codex":[0.9258714,0.04192147,0.004547816,0.007091979,0.01667063,0.003896686],"domain_scores_gemma":[0.681308,0.1068129,0.01122644,0.1638206,0.03144232,0.005389751],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001549233,0.001628926,0.02703623,0.0007138452,0.0004309192,0.0005131225,0.004516563,0.05993406,0.02623165,0.1076981,0.009473351,0.7602741],"study_design_scores_gemma":[0.0003119132,0.001543641,0.004367799,0.0009957241,0.0003509452,0.0005704177,0.001997667,0.4947152,0.06467047,0.4065229,0.02368202,0.0002712805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1054167,0.0009576652,0.8650485,0.005859485,0.0002557274,0.0004882401,0.0001897703,0.0132391,0.0085448],"genre_scores_gemma":[0.5247551,0.0004052346,0.4681226,0.00114153,0.0001140692,0.0003270748,0.0006098732,0.002673568,0.001851035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9921502,"threshold_uncertainty_score":0.3123391,"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."}}