{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001370491,0.0007497611,0.0007569347,0.0002921194,0.000283763,0.0005951308,0.000923474,0.001226156,0.001078],"category_scores_gemma":[0.006697836,0.000560125,0.0004854257,0.0002487321,0.0009413241,0.001078944,0.001575165,0.00141973,0.0001915262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005393138,"about_ca_system_score_gemma":0.0009176845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002406492,"about_ca_topic_score_gemma":0.002617862,"domain_scores_codex":[0.999473,0.0001705791,0.00003600155,0.0001312271,0.0001300954,0.00005907861],"domain_scores_gemma":[0.9969138,0.002136397,0.0003460796,0.000265373,0.000204169,0.0001342433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007460868,0.0000415599,0.0008696014,0.00005814742,0.0000162166,0.00008178585,0.00005418866,0.9637419,0.003419662,0.001855595,0.0002528749,0.02953382],"study_design_scores_gemma":[0.000005069901,0.00004245118,0.0002537208,0.000005518698,0.000003175745,0.00001929349,0.000006058065,0.997437,0.0009574292,0.001145384,0.0001192439,0.00000565295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.093083,0.0001791718,0.9047453,0.0003117429,0.00001938798,0.00005766265,0.0000677668,0.0003486688,0.001187442],"genre_scores_gemma":[0.8988504,0.0001396567,0.0988072,0.0001028263,0.00002678012,0.0001367923,0.0001751625,0.00005285137,0.001708333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002406492,"threshold_uncertainty_score":0.007247925,"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."}}