{"id":"W4411272438","doi":"10.1109/msr66628.2025.00111","title":"Inferring Questions from Programming Screenshots","year":2025,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Programming language; Information retrieval; Software engineering","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":[0.001734793,0.001161849,0.0003554948,0.001155463,0.0003094687,0.001440956,0.0008493537,0.001065351,0.005977269],"category_scores_gemma":[0.02974945,0.0003068887,0.0005770401,0.0003803534,0.0004991072,0.002449375,0.001423655,0.00108553,0.001583584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000612815,"about_ca_system_score_gemma":0.0003716303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001268131,"about_ca_topic_score_gemma":0.002549827,"domain_scores_codex":[0.9983752,0.0008974122,0.00004981942,0.0003639862,0.0002405615,0.00007301468],"domain_scores_gemma":[0.9764836,0.01969153,0.0006546872,0.001341506,0.001502389,0.0003263981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00193543,0.0009542431,0.04342159,0.00280178,0.0001435717,0.001687562,0.02384141,0.02996315,0.09029603,0.01361488,0.0358031,0.7555373],"study_design_scores_gemma":[0.0002020423,0.001227945,0.03828579,0.0007061551,0.0001744814,0.001199019,0.01326288,0.6998355,0.09335417,0.0458207,0.1057112,0.0002201251],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4485359,0.0005809476,0.4931226,0.001285626,0.000208015,0.0009829933,0.004031495,0.03403505,0.01721724],"genre_scores_gemma":[0.7967634,0.0002117222,0.1943297,0.000306805,0.00004915597,0.0003766063,0.003310656,0.001169357,0.003482627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005977269,"threshold_uncertainty_score":0.01999599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01273483785795469,"score_gpt":0.2800907305610675,"score_spread":0.2673558927031128,"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."}}