{"id":"W7153576139","doi":"10.1145/3779657.3779658","title":"From Scenario to Code: Structured Prompting for LLM-Based Unit Test Generation","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières; Innovation and Economic Development Trois Rivières","funders":"","keywords":"Unit testing; Test case; Code (set theory); Readability; Test (biology); Java; Software; Relevance (law); Code coverage","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006528637,0.000418258,0.0004071706,0.0003764249,0.0006742901,0.001088859,0.001216929,0.0002470769,0.00004339067],"category_scores_gemma":[0.004266439,0.0004148539,0.0001279152,0.001200177,0.00006219623,0.000240371,0.0003703343,0.0002426124,0.00001640349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001628136,"about_ca_system_score_gemma":0.0009060899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001034557,"about_ca_topic_score_gemma":0.0003461461,"domain_scores_codex":[0.9970551,0.0001002286,0.000679168,0.00122701,0.0003404533,0.0005980533],"domain_scores_gemma":[0.9955482,0.002178953,0.0001995452,0.001217859,0.000663795,0.0001915868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007959019,0.0006280155,0.02333568,0.0002463113,0.00009890533,0.00001142023,0.001658422,0.006718171,0.02290487,0.006574432,0.3349923,0.6027519],"study_design_scores_gemma":[0.0006544622,0.0004490528,0.001748499,0.0004876064,0.00004675479,0.000001045552,0.000006845553,0.9102795,0.0574977,0.02506248,0.003294726,0.0004712943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01621728,0.00009681044,0.9676535,0.005054992,0.001398279,0.001513463,0.00009059226,0.007681234,0.0002938441],"genre_scores_gemma":[0.4273968,5.46292e-7,0.5685072,0.002794992,0.0002462084,0.0001212144,0.00004453329,0.00001908912,0.0008694224],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9035614,"threshold_uncertainty_score":0.9999481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05725744101598945,"score_gpt":0.327343913897419,"score_spread":0.2700864728814296,"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."}}