{"id":"W4406842754","doi":"10.3390/educsci15020156","title":"Engineered Prompts in ChatGPT for Educational Assessment in Software Engineering and Computer Science","year":2025,"lang":"en","type":"article","venue":"Education Sciences","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; Lakehead University; Western University","funders":"","keywords":"Computer science; Computer software; Software engineering; Software; Educational software; Computer-Assisted Instruction; Science education; Mathematics education; Social software engineering; Engineering education; Software development; Engineering management; Multimedia; Software construction; Engineering; Programming language; 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":[0.0008032723,0.00007238746,0.00008792409,0.0007709723,0.000132978,0.0002758672,0.0005104052,0.00002042584,0.000001272241],"category_scores_gemma":[0.0002997001,0.00006943531,0.00001256861,0.001870276,0.0001099737,0.0005208569,0.00009258935,0.00009080013,8.029105e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000976136,"about_ca_system_score_gemma":0.002439864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002327166,"about_ca_topic_score_gemma":0.000009613347,"domain_scores_codex":[0.9990397,0.00001329039,0.0001719779,0.000373462,0.0001939436,0.0002076187],"domain_scores_gemma":[0.9994615,0.0002307115,0.00003789861,0.0001363489,0.00009100841,0.000042511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.797674e-7,0.0004126848,0.1969556,0.0001139168,0.00000348924,2.842179e-7,0.001987294,0.02755437,0.0004174003,0.6549838,0.0002983777,0.1172718],"study_design_scores_gemma":[0.0001119723,0.00002515388,0.2918729,0.0001519408,8.154432e-7,0.000001268098,0.0000724552,0.7008318,0.00008799405,0.006326605,0.0004272253,0.00008981451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6305908,0.0002550807,0.3397399,0.02696731,0.001821004,0.0003672867,0.000001003393,0.00005822416,0.0001993365],"genre_scores_gemma":[0.6954558,0.000004339938,0.3042023,0.000122242,0.00004328259,0.0000401168,0.00000107167,0.000001333593,0.0001294301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6732775,"threshold_uncertainty_score":0.4328213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01157442256148195,"score_gpt":0.3452300099482893,"score_spread":0.3336555873868073,"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."}}