{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000261767,0.00009374071,0.00009679952,0.0001268608,0.0002665342,0.0004046171,0.0005334092,0.00004803122,0.00000928662],"category_scores_gemma":[0.0001399566,0.00008684504,0.00004834536,0.0003972004,0.00002274224,0.0002558504,0.000244525,0.0002539437,0.00004041908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002789176,"about_ca_system_score_gemma":0.00005277552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001432691,"about_ca_topic_score_gemma":0.00008216668,"domain_scores_codex":[0.9991198,0.00007303419,0.0001465072,0.0003042231,0.0001170869,0.0002393896],"domain_scores_gemma":[0.9993273,0.0001342194,0.00003137676,0.0004179832,0.00003395103,0.00005514096],"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":[5.164823e-7,0.00002407499,0.007730912,0.000002810393,0.00001307445,0.000002991301,0.0003065825,0.00009685445,0.0000356001,0.1231472,0.0001833831,0.868456],"study_design_scores_gemma":[0.0003416574,0.00004259769,0.04590838,0.0002106038,0.00001602179,0.000003267063,0.0001705217,0.02573992,0.0002880708,0.00373437,0.9232161,0.0003284527],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007420577,0.0001675238,0.9829651,0.001491062,0.0002747262,0.00008265954,1.828335e-7,0.001297235,0.006300951],"genre_scores_gemma":[0.5406998,0.000001094723,0.4576761,0.0002140398,0.00002725442,0.00001163859,0.000001744162,0.000003204707,0.001365115],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9230328,"threshold_uncertainty_score":0.3901733,"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."}}