{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007680452,0.0001583944,0.000196373,0.0008725041,0.0002542159,0.000704622,0.00217427,0.00004600072,0.0003032574],"category_scores_gemma":[0.00007320025,0.0001733441,0.0001330891,0.0006367631,0.00004830309,0.001707432,0.0003985979,0.0005471812,0.00001624252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001080243,"about_ca_system_score_gemma":0.0006793725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004113954,"about_ca_topic_score_gemma":0.00008218003,"domain_scores_codex":[0.9972007,0.0002258185,0.001096536,0.00029186,0.000953595,0.0002314786],"domain_scores_gemma":[0.9978166,0.0002277628,0.0007369933,0.0002864814,0.0008348068,0.0000973136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008164124,0.001559206,0.0008767676,0.000002464628,0.00004084561,0.0000590706,0.00975302,0.008443327,0.0008648999,0.01450929,0.0009242188,0.9629588],"study_design_scores_gemma":[0.0002887748,0.0008403519,0.006752949,0.0006672402,0.00003780806,0.003674341,0.07551745,0.4881714,0.0138407,0.3878554,0.02103452,0.001319005],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1862018,0.00007744547,0.7894458,0.007528067,0.01630629,0.0001351219,0.000003883903,0.00003779985,0.0002637208],"genre_scores_gemma":[0.8733814,0.00001421837,0.1240248,0.001201709,0.001264816,0.00003394769,0.000009481373,0.00001552413,0.00005414324],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9616397,"threshold_uncertainty_score":0.7068769,"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."}}