{"id":"W2531397669","doi":"10.1016/j.amjsurg.2016.09.050","title":"Psychometric properties of the Global Operative Assessment of Laparoscopic Skills (GOALS) using item response theory","year":2016,"lang":"en","type":"article","venue":"The American Journal of Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Discriminative model; Item response theory; Psychology; Psychometrics; Perception; Applied psychology; Clinical psychology; Artificial intelligence; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.002879289,0.000103031,0.0006118384,0.0001705111,0.00005664704,0.000007464105,0.0001477568,0.00001900758,0.00007527402],"category_scores_gemma":[0.001918441,0.0000376532,0.0002886529,0.001031331,0.0006554098,0.00007760229,0.00003464364,0.0001205045,6.684517e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001072877,"about_ca_system_score_gemma":0.0004367011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008946374,"about_ca_topic_score_gemma":1.493905e-7,"domain_scores_codex":[0.9977137,0.0008966914,0.0006637443,0.00008061929,0.0004960172,0.0001491973],"domain_scores_gemma":[0.9956633,0.002664029,0.001046484,0.0002265706,0.0003218793,0.00007767941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004718279,0.0002544737,0.9114373,0.00001890403,0.00034328,0.000008007693,0.0003922076,0.0001286939,0.03212554,0.0001924081,0.00001573313,0.0503652],"study_design_scores_gemma":[0.001100239,0.000219226,0.9873024,0.001080664,0.0001044136,0.00009801776,0.001013883,0.00004579149,0.008733762,0.0001239457,0.0001138694,0.00006373924],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978167,0.000282695,0.000398107,0.0009999519,0.0002095082,0.00009116778,0.000004987978,0.000004133635,0.0001927349],"genre_scores_gemma":[0.9993476,0.00007609629,0.0001412297,0.0003055844,0.00006562309,8.280246e-7,5.51544e-8,0.000008882514,0.00005412554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07586517,"threshold_uncertainty_score":0.2414885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06618306346438398,"score_gpt":0.3717688282257346,"score_spread":0.3055857647613507,"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."}}