{"id":"W4379982989","doi":"10.1177/09544119231177834","title":"A convolutional neural network for high throughput screening of femoral stem taper corrosion","year":2023,"lang":"en","type":"article","venue":"Proceedings of the Institution of Mechanical Engineers Part H Journal of Engineering in Medicine","topic":"Orthopaedic implants and arthroplasty","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Modular design; Corrosion; Deep learning; Artificial intelligence; Computer science; Pattern recognition (psychology); Materials science; Metallurgy","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0007889189,0.00128985,0.0008151322,0.0008764146,0.0004271702,0.0006190792,0.001253163,0.000913448,0.001704709],"category_scores_gemma":[0.001819334,0.0006096204,0.0007446588,0.0007209535,0.0003045056,0.0006338861,0.000707193,0.0009236104,0.0008567611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0016021,"about_ca_system_score_gemma":0.001449743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02773406,"about_ca_topic_score_gemma":0.02770313,"domain_scores_codex":[0.9996054,0.00005771829,0.00002150484,0.0001275532,0.0001042221,0.00008364879],"domain_scores_gemma":[0.9994566,0.0002088058,0.00005475148,0.00005859693,0.0001914711,0.00002978593],"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":[0.0008421618,0.0005792211,0.0100661,0.0003476327,0.0005013216,0.000425558,0.00008906223,0.3580231,0.07119957,0.002310113,0.01675583,0.5388603],"study_design_scores_gemma":[0.00001167547,0.00005641176,0.001126719,0.000006622301,0.00002997544,0.00002648382,0.000006571417,0.9896628,0.007943299,0.000411945,0.0007050559,0.00001245281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3503735,0.004091673,0.6101525,0.001127129,0.000357112,0.0003964554,0.004327383,0.02211562,0.007058552],"genre_scores_gemma":[0.7371092,0.000989916,0.2446253,0.000520449,0.00005787031,0.0004173463,0.006788252,0.0001900698,0.009301617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02773406,"threshold_uncertainty_score":0.05514526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03056353827651579,"score_gpt":0.2590587207627875,"score_spread":0.2284951824862717,"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."}}