{"id":"W2751826809","doi":"10.1177/2332858417728046","title":"Measuring Collaborative Problem Solving Using Mathematics-Based Tasks","year":2017,"lang":"en","type":"article","venue":"AERA Open","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Mathematics education; Process (computing); Computer science; Psychology","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":[0.003344442,0.0007077634,0.0006164978,0.002848264,0.0007036304,0.001755844,0.001320554,0.0005911765,0.001897723],"category_scores_gemma":[0.02501235,0.0002483579,0.0004295484,0.00187292,0.0004593418,0.001732262,0.002132094,0.0007883786,0.0007483242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004963287,"about_ca_system_score_gemma":0.001164458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001220271,"about_ca_topic_score_gemma":0.002244945,"domain_scores_codex":[0.994187,0.001956223,0.0006488525,0.0007148887,0.002199558,0.0002934756],"domain_scores_gemma":[0.9766355,0.0116375,0.004664915,0.002542453,0.003396994,0.001122694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004782451,0.005312442,0.551288,0.0004627605,0.0003111417,0.0001725161,0.00866328,0.008608097,0.0229042,0.001800469,0.0009358287,0.3990629],"study_design_scores_gemma":[0.0001662322,0.002572893,0.9214618,0.0001171563,0.0001085161,0.0006013308,0.00441258,0.02360046,0.0345019,0.00454715,0.007740841,0.0001692303],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9722112,0.00005814003,0.02286726,0.00003813101,0.000009758537,0.0005346782,0.0002468599,0.0001096265,0.003924392],"genre_scores_gemma":[0.937951,0.0001122394,0.05946787,0.00002386,0.00001708152,0.0007197478,0.0005295904,0.00002025059,0.001158432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003344442,"threshold_uncertainty_score":0.01768732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2384607898107124,"score_gpt":0.4618191385617934,"score_spread":0.223358348751081,"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."}}