{"id":"W4414304292","doi":"10.1016/j.bspc.2025.108487","title":"Learning from imperfect demonstrations in a surgical training task","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Northern Alberta Institute of Technology; University of Alberta","funders":"","keywords":"Imperfect; Robustness (evolution); Robotics; Task (project management); Probabilistic logic; Scalability; Robot","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":[0.0003632165,0.0001306098,0.0003542595,0.0001625576,0.0001680655,0.00005861975,0.00004096613,0.0001630695,0.0001648438],"category_scores_gemma":[0.000174808,0.00010292,0.00006405867,0.0004090209,0.0001903518,0.00006146719,0.00001346777,0.0004233952,0.000003971538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002900798,"about_ca_system_score_gemma":0.0002463301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004512467,"about_ca_topic_score_gemma":0.000004852749,"domain_scores_codex":[0.9987751,0.00009292604,0.0003438725,0.000291412,0.0002293886,0.0002672561],"domain_scores_gemma":[0.999087,0.0005697921,0.00004709426,0.00004642649,0.00003861932,0.0002110059],"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":[0.0004238048,0.0001204787,0.02217807,0.00003560587,0.0000464415,0.0001563537,0.0004894249,0.00003226399,0.002181142,0.0001551929,0.00000668909,0.9741746],"study_design_scores_gemma":[0.05650334,0.0008179687,0.09109252,0.002441157,0.0004163744,0.0001067012,0.00371013,0.7666159,0.0001599342,0.002450226,0.07507647,0.0006092346],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9510757,0.002800063,0.02967311,0.003526322,0.00007194001,0.000303033,0.000005745801,0.0002000287,0.01234409],"genre_scores_gemma":[0.9989451,0.00001381818,0.000135868,0.000558443,0.0001490707,0.00002020727,0.00003000724,0.000007729932,0.0001397578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9735653,"threshold_uncertainty_score":0.4196957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01727867509229432,"score_gpt":0.2856794596945484,"score_spread":0.2684007846022541,"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."}}