{"id":"W4392564669","doi":"10.1145/3626252.3630909","title":"Prompt Problems: A New Programming Exercise for the Generative AI Era","year":2024,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Ulla Tuomisen Säätiö","keywords":"Generative grammar; Computer science; Artificial intelligence; Programming language","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006605759,0.0001574552,0.0001240308,0.00007133974,0.0003875233,0.001891255,0.000671305,0.00004878301,0.00001010762],"category_scores_gemma":[0.00005105545,0.00009197607,0.0001192994,0.0003942833,0.00003161451,0.0004197176,0.0001427422,0.0003764968,0.00004146855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003011974,"about_ca_system_score_gemma":0.0002194751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001634272,"about_ca_topic_score_gemma":0.00002425312,"domain_scores_codex":[0.9987233,0.00004332771,0.0001788646,0.0004716412,0.0001981735,0.0003847009],"domain_scores_gemma":[0.9992414,0.0002167578,0.00003091959,0.0003723134,0.00004658009,0.00009203851],"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":[0.000001806842,0.00001835121,0.00001281467,0.0000515253,0.00002542283,0.000002720625,0.007598419,0.0004912005,0.00002141154,0.03779076,0.007993352,0.9459922],"study_design_scores_gemma":[0.000119023,0.00009390913,0.00001914352,0.0001445589,0.00001910435,0.00001246829,0.0000955294,0.1990064,0.0001259597,0.001442171,0.7987672,0.0001544729],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000734761,0.003181446,0.9746284,0.01913084,0.0005102824,0.001035832,3.157156e-7,0.00132405,0.0001152949],"genre_scores_gemma":[0.06224227,0.00001927486,0.9170027,0.0005991441,0.0004571914,0.0006658575,0.000003348292,0.00003348948,0.01897676],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9458377,"threshold_uncertainty_score":0.9991449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02639252194379686,"score_gpt":0.2911855269503672,"score_spread":0.2647930050065703,"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."}}