{"id":"W4309836816","doi":"10.1007/s40593-022-00318-x","title":"Assessing Teamwork Skills: Can a Computer Algorithm Match Human Experts?","year":2022,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence in Education","topic":"AI in Service Interactions","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; Ontario Tech University","funders":"","keywords":"Teamwork; Computer science; Peer assessment; Artificial intelligence; Algorithm; Psychology; Mathematics education","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":[0.004294388,0.0005784803,0.0006140469,0.002622508,0.0004766958,0.001940619,0.0009897023,0.001417319,0.002681125],"category_scores_gemma":[0.03722685,0.0002066367,0.0003474571,0.0008531132,0.0003840445,0.001752462,0.0009586205,0.0005476382,0.0009979022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004378149,"about_ca_system_score_gemma":0.001001716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001976178,"about_ca_topic_score_gemma":0.00323528,"domain_scores_codex":[0.997925,0.0008594856,0.0001892602,0.0005342765,0.0003714284,0.0001205223],"domain_scores_gemma":[0.9865859,0.008290413,0.001340801,0.0006844505,0.002276884,0.0008216174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001064159,0.001154363,0.5119905,0.000327475,0.0003583862,0.0001399025,0.001421845,0.02952483,0.002894002,0.003150722,0.006483026,0.4414907],"study_design_scores_gemma":[0.0004146814,0.001790386,0.2550159,0.0005527392,0.0003951856,0.001085716,0.005672589,0.6901741,0.005594722,0.03018618,0.008985758,0.0001320745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8089449,0.0006104398,0.1739948,0.001112264,0.000195158,0.0003570433,0.0002503828,0.0005723471,0.0139626],"genre_scores_gemma":[0.9346397,0.0002054163,0.06373154,0.0001459041,0.00003638305,0.0001152667,0.0002078782,0.00003376097,0.0008841297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004294388,"threshold_uncertainty_score":0.0227111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03242304614964824,"score_gpt":0.3855324473376888,"score_spread":0.3531094011880406,"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."}}