{"id":"W4399860921","doi":"10.1145/3660650.3660664","title":"An Initial Exploration of Code Diagram Query Effectiveness","year":2024,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Programming language; Notional amount; Visualization; Program comprehension; Diagrammatic reasoning; Python (programming language); Software engineering; Artificial intelligence; Software; Software system","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":[0.02445089,0.0007301651,0.0007556955,0.003511278,0.0007898611,0.003478735,0.001422482,0.0009757887,0.003109143],"category_scores_gemma":[0.22771,0.0003766207,0.0006940809,0.001748762,0.001327087,0.005093636,0.002675258,0.001443784,0.0008261985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001740349,"about_ca_system_score_gemma":0.001075963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002142527,"about_ca_topic_score_gemma":0.002447029,"domain_scores_codex":[0.9730844,0.01225459,0.002610321,0.002822368,0.008050809,0.001177449],"domain_scores_gemma":[0.6052537,0.3401223,0.01182018,0.007411116,0.03222882,0.003163905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003616116,0.00364241,0.3349727,0.003420465,0.0003011344,0.0004555725,0.09412496,0.003519215,0.02687417,0.00165646,0.005323211,0.5220937],"study_design_scores_gemma":[0.0004489484,0.01317695,0.769973,0.001366884,0.0005810611,0.001070459,0.07809269,0.03279677,0.06194236,0.003326505,0.03682463,0.0003997373],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863889,0.0004875168,0.005251306,0.0004649403,0.00002230037,0.0003792619,0.0004609558,0.0005139421,0.006030924],"genre_scores_gemma":[0.9900775,0.0003180963,0.00687841,0.0001111252,0.00001558095,0.0003121833,0.0006329576,0.000160461,0.001493754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02445089,"threshold_uncertainty_score":0.1293102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04202554863068285,"score_gpt":0.3533535432281289,"score_spread":0.311327994597446,"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."}}