{"id":"W6931937542","doi":"10.5522/04/26531686","title":"PitVis-2023 Challenge: Endoscopic Pituitary Surgery videos","year":2024,"lang":"en","type":"dataset","venue":"University College London","topic":"Intensive Care Unit Cognitive Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Wellcome Trust","keywords":"Workflow; Annotation; Metadata; Scripting language; Endoscopic surgery; Multidisciplinary team; Baseline (sea)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008599595,0.004257099,0.001396749,0.002384594,0.001076529,0.001918199,0.003236703,0.00354857,0.02385047],"category_scores_gemma":[0.003836598,0.0005328009,0.00194191,0.002981868,0.0005164992,0.001449985,0.002325393,0.002486745,0.04149725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002386805,"about_ca_system_score_gemma":0.00229565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04111282,"about_ca_topic_score_gemma":0.101191,"domain_scores_codex":[0.9986711,0.0002218695,0.0001062997,0.0003816369,0.0004034245,0.0002157407],"domain_scores_gemma":[0.9987634,0.0002587299,0.00008751795,0.0003155041,0.0003757567,0.0001990541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002972451,0.0001448248,0.001076742,0.0007680251,0.00006748403,0.000154807,0.0000389311,0.001023766,0.000714217,0.0003220671,0.9757392,0.0196526],"study_design_scores_gemma":[0.0006578564,0.0003120662,0.02057626,0.0009664626,0.0001402183,0.001675927,0.0005013077,0.01497996,0.005514208,0.00300221,0.9515069,0.0001666621],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.004681842,0.001311225,0.001387179,0.0004900909,0.000359204,0.0002294037,0.981194,0.005633547,0.004713464],"genre_scores_gemma":[0.002698531,0.0001680935,0.001979661,0.000122962,0.00002951108,0.0001404858,0.9928952,0.0001600981,0.001805432],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04111282,"threshold_uncertainty_score":0.081747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01445041144805364,"score_gpt":0.235778514017935,"score_spread":0.2213281025698813,"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."}}