{"id":"W2901235535","doi":"10.1016/j.media.2018.11.008","title":"CATARACTS: Challenge on automatic tool annotation for cataRACT surgery","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":128,"is_retracted":false,"has_abstract":false,"ca_institutions":"D-Wave Systems (Canada)","funders":"European Regional Development Fund; Centro de Matemática Universidade do Porto; Fundação para a Ciência e a Tecnologia","keywords":"Workflow; Annotation; Context (archaeology); Computer science; Cataracts; Cataract surgery; Artificial intelligence; Medicine; Surgery","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009147189,0.0001386048,0.0005211503,0.0003783,0.0001172223,0.00002885662,0.00006999364,0.0001215709,0.00493086],"category_scores_gemma":[0.003772055,0.0001055527,0.000436549,0.0008146797,0.0001392209,0.0001129891,0.00001356521,0.0001456059,0.0002956978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004427995,"about_ca_system_score_gemma":0.0001086446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004690291,"about_ca_topic_score_gemma":0.0000400907,"domain_scores_codex":[0.9982126,0.00006171672,0.0004592785,0.0003088448,0.000687303,0.000270247],"domain_scores_gemma":[0.9977103,0.001361067,0.0001138106,0.0002892457,0.0002383849,0.0002872087],"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":[0.0005680791,0.001546177,0.01225532,0.0002269448,0.003322814,0.0003689314,0.001080374,0.0000145497,0.00008392089,0.0003617403,0.006303855,0.9738673],"study_design_scores_gemma":[0.00571124,0.001016604,0.1559576,0.0003542848,0.005692694,0.00002036002,0.0004194519,0.7545089,0.0008899729,0.0003542195,0.07441122,0.0006634318],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9564248,0.00007877258,0.02555893,0.009857946,0.0002077233,0.0003773391,0.00002229193,0.0002450092,0.007227226],"genre_scores_gemma":[0.995037,0.00002581808,0.0006928369,0.002843564,0.0005587494,0.00003079144,0.0005211547,0.00001586104,0.0002742167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9732038,"threshold_uncertainty_score":0.9959788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04315227666897925,"score_gpt":0.3584968985668636,"score_spread":0.3153446218978843,"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."}}