{"id":"W4388196622","doi":"10.22318/cscl2023.978554","title":"Towards Developing Scalable Assessments of Higher-Order Learning","year":2023,"lang":"en","type":"article","venue":"Computer-supported collaborative learning/˜The œComputer-Supported Collaborative Learning Conference","topic":"Educational Strategies and Epistemologies","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Scalability; Computer science; Class (philosophy); Order (exchange); Cognition; Path (computing); Engineering ethics; Mathematics education; Artificial intelligence; Psychology; Engineering; Programming language","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":[0.04802746,0.001224486,0.0007867991,0.002373179,0.0007612489,0.006103556,0.002085444,0.002040238,0.003352212],"category_scores_gemma":[0.08278731,0.0004427707,0.0006870682,0.001346396,0.00107204,0.005793986,0.005541841,0.002720868,0.001467673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519032,"about_ca_system_score_gemma":0.00680709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001769394,"about_ca_topic_score_gemma":0.003970874,"domain_scores_codex":[0.9729498,0.01472954,0.001739069,0.00178218,0.008248454,0.0005509423],"domain_scores_gemma":[0.9271062,0.03093181,0.004801202,0.007014769,0.02752072,0.002625351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003743592,0.001179808,0.05164045,0.001364041,0.0002142451,0.0001022425,0.00490583,0.007442896,0.02833214,0.02563912,0.009162915,0.8696418],"study_design_scores_gemma":[0.001068619,0.006886704,0.2376842,0.005901154,0.0005436392,0.001079555,0.02431883,0.1491581,0.139912,0.2381778,0.1944136,0.0008558272],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1180197,0.0008660115,0.8499243,0.003700064,0.0003295155,0.005203471,0.00117084,0.002964469,0.01782147],"genre_scores_gemma":[0.159617,0.0003463944,0.834593,0.0003283576,0.00006290447,0.002486433,0.0006891172,0.0001196859,0.00175718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04802746,"threshold_uncertainty_score":0.2539965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04595326024166136,"score_gpt":0.3592451922201849,"score_spread":0.3132919319785235,"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."}}