{"id":"W2943714016","doi":"10.1145/3300115.3309529","title":"Answering the Correct Question","year":2019,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Python (programming language); Computer science; Isolation (microbiology); Focus (optics); Code (set theory); Test (biology); Unit testing; Group (periodic table); Mathematics education; Programming language; Software; Psychology","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":[0.0004066089,0.00003499498,0.00003194947,0.00001564557,0.0000757239,0.0001359852,0.0003256706,0.00001333375,0.00001538785],"category_scores_gemma":[0.00002208665,0.00002087496,0.00001904026,0.00008952949,0.000005914611,0.0001301114,0.00006419269,0.000123613,0.00029695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008180621,"about_ca_system_score_gemma":0.000008221873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009060369,"about_ca_topic_score_gemma":0.000003747014,"domain_scores_codex":[0.9996032,0.00005986174,0.00004377915,0.0001124087,0.00008098912,0.00009975259],"domain_scores_gemma":[0.9996456,0.00006228136,0.00001728835,0.0002509183,0.000008909611,0.00001500544],"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":[4.366119e-7,0.000006030545,0.008051002,0.000002212095,0.000002463545,6.255971e-7,0.001129613,0.00068458,0.0001425572,0.06478404,0.0002626833,0.9249338],"study_design_scores_gemma":[0.0001786662,0.0001293535,0.03111327,0.00003671198,0.000002502296,0.00002879166,0.0002306367,0.1476118,0.0004960949,0.0003538488,0.819599,0.0002192444],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0702296,0.00003802902,0.9197264,0.001272339,0.0007084613,0.00006157342,9.831457e-9,0.0004495878,0.007514042],"genre_scores_gemma":[0.9720359,6.103928e-7,0.02358248,0.0001824465,0.00002558766,0.000001654781,1.392185e-7,0.000002326677,0.004168844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9247145,"threshold_uncertainty_score":0.381679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005263112405284215,"score_gpt":0.2264986367655399,"score_spread":0.2212355243602557,"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."}}