{"id":"W4382515967","doi":"10.1145/3587103.3594211","title":"Conducting Multi-Institutional Studies of Parsons Problems","year":2023,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Scratch; Computer science; Code (set theory); Coding (social sciences); Publication; Order (exchange); Programming language; Mathematics education; Software engineering; Human–computer interaction; Psychology; Sociology","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":[0.000603239,0.00006053912,0.0001040395,0.00008165157,0.0002011253,0.00003099794,0.0002445399,0.00001823651,0.000001907514],"category_scores_gemma":[0.0002823769,0.0000443678,0.00003762312,0.0003785406,0.00006950014,0.0001629936,0.0001723914,0.0001067699,0.00004642721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001138283,"about_ca_system_score_gemma":0.00003333636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004494502,"about_ca_topic_score_gemma":0.000009040937,"domain_scores_codex":[0.9993566,0.00004701353,0.0001331356,0.0001685811,0.000134974,0.0001597569],"domain_scores_gemma":[0.9995826,0.0001361298,0.00005226556,0.0001511274,0.00005236936,0.00002544556],"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":[0.000001403018,0.0001577979,0.01520764,0.000222593,0.0002082875,0.00002694866,0.03829306,0.02817894,0.004456643,0.2353782,0.002151187,0.6757173],"study_design_scores_gemma":[0.003256395,0.000569354,0.02643494,0.0009881951,0.00005186472,0.0001428632,0.01987178,0.5782167,0.01017547,0.003020897,0.35566,0.001611584],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1885882,0.0004739926,0.8057098,0.001941895,0.0007973999,0.0001592735,7.003188e-7,0.001778699,0.0005499893],"genre_scores_gemma":[0.8097686,0.000008057771,0.1890054,0.00002240564,0.0000195477,0.000008481724,9.609523e-7,0.000002672121,0.001163851],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6741058,"threshold_uncertainty_score":0.1809267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3230945578174528,"score_gpt":0.3792800844996193,"score_spread":0.05618552668216648,"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."}}