{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003977588,0.0001886629,0.0003339073,0.00008293164,0.001537408,0.0007940024,0.001091486,0.0001057549,0.0006085995],"category_scores_gemma":[0.0006403052,0.0001732625,0.00004340159,0.0001387955,0.0001261,0.0003118086,0.000290649,0.0004509483,0.0001529436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007962825,"about_ca_system_score_gemma":0.0001533436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00123202,"about_ca_topic_score_gemma":0.0000344386,"domain_scores_codex":[0.9980906,0.0007074429,0.0002996714,0.0003717445,0.0001746469,0.0003559151],"domain_scores_gemma":[0.9980375,0.000219415,0.000523451,0.0009328384,0.0002311586,0.00005565483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0009926518,0.002553533,0.1497961,0.0005744937,0.002017282,0.0004961301,0.2773632,0.003114149,0.1168001,0.2139628,0.01928677,0.2130428],"study_design_scores_gemma":[0.03423782,0.002411588,0.5241501,0.008116278,0.0008951158,0.0002690268,0.04821527,0.04293151,0.05386512,0.05007857,0.2255765,0.009253105],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4898146,0.00007256417,0.06409484,0.0007530724,0.0007611138,0.00107398,0.000008022974,0.0001165204,0.4433053],"genre_scores_gemma":[0.693159,2.030594e-7,0.3035442,0.0001832299,0.0001041029,0.00004000868,0.000003302261,0.00004064726,0.002925319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.44038,"threshold_uncertainty_score":0.9997625,"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."}}