{"id":"W3149190779","doi":"10.1145/3448139.3448175","title":"Combining Data-Driven Models and Expert Knowledge for Personalized Support to Foster Computational Thinking Skills","year":2021,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Mitacs","keywords":"Personalization; Computational thinking; Computer science; Personalized learning; Human–computer interaction; Artificial intelligence; Data science; Mathematics education; Psychology; Teaching method; World Wide Web; Cooperative learning; Open learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005694824,0.0001315023,0.0001894756,0.00006876409,0.0003387646,0.0005072696,0.0006474417,0.00004531686,0.00001572743],"category_scores_gemma":[0.00009114392,0.000124987,0.00004501285,0.0001488369,0.00002558693,0.0005846483,0.001016992,0.0001315236,0.00001202958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002231103,"about_ca_system_score_gemma":0.0001358764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008916491,"about_ca_topic_score_gemma":0.0000103849,"domain_scores_codex":[0.9986057,0.00009827396,0.0001947069,0.0006132989,0.0002085569,0.0002795051],"domain_scores_gemma":[0.9988523,0.0004130247,0.00004488302,0.0004249421,0.0001338324,0.0001310387],"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":[0.00001831815,0.000326633,0.000385653,0.00005821654,0.0001118752,0.00002937847,0.1605509,0.01657977,0.00009567093,0.2113177,0.02074169,0.5897841],"study_design_scores_gemma":[0.0008657961,0.00008964558,0.00009262975,0.00006298786,0.000008250926,0.00006155487,0.000785441,0.8322166,0.00003344526,0.0034903,0.1620207,0.0002727003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002326575,0.0001895309,0.9934999,0.002703701,0.0002196276,0.0001576256,0.000005140992,0.00024083,0.0006570306],"genre_scores_gemma":[0.1701847,0.00000227536,0.8255296,0.002307429,0.00006268913,0.00002043521,0.00009743753,0.00001430707,0.001781128],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8156368,"threshold_uncertainty_score":0.5096824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07569740317886438,"score_gpt":0.3458418922662319,"score_spread":0.2701444890873675,"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."}}