{"id":"W7104053409","doi":"10.6084/m9.figshare.30527891","title":"Additional file 1 of Evaluating the performance of five large language models in answering Delphi consensus questions relating to patellar instability and medial patellofemoral ligament reconstruction","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Lower Extremity Biomechanics and Pathologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of Calgary; University of Ottawa; McMaster University","funders":"","keywords":"Medial patellofemoral ligament; Delphi; Delphi method; Ligament","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007343974,0.001119022,0.001081727,0.002924783,0.001388338,0.001850955,0.001571229,0.001427852,0.8544392],"category_scores_gemma":[0.130122,0.0006196006,0.001069022,0.002654762,0.0004125953,0.001695815,0.00153467,0.001164945,0.1345116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001654079,"about_ca_system_score_gemma":0.002667595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005572421,"about_ca_topic_score_gemma":0.01360241,"domain_scores_codex":[0.9967348,0.001396375,0.0006880231,0.0003587497,0.0005778775,0.000244201],"domain_scores_gemma":[0.8023866,0.1773764,0.004088487,0.004585344,0.01054761,0.00101557],"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":[0.0009403387,0.0005381986,0.004497779,0.002946805,0.0000659244,0.00007487237,0.0005194918,0.000582415,0.00007734646,0.00121097,0.9568501,0.03169571],"study_design_scores_gemma":[0.02545425,0.002303577,0.1007004,0.01353647,0.0007229873,0.00106189,0.008846588,0.01141779,0.002525709,0.03436587,0.7984747,0.000589894],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.003184921,0.00003203128,0.001735795,0.0004598402,0.0001144355,0.001664281,0.9867781,0.0007207702,0.005309776],"genre_scores_gemma":[0.07093111,0.0002516256,0.03775458,0.002059496,0.000213256,0.0725654,0.7745765,0.002134391,0.0395136],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.1455608,"threshold_uncertainty_score":0.2076249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03566170264384019,"score_gpt":0.2719358646680268,"score_spread":0.2362741620241866,"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."}}