{"id":"W7117154141","doi":"10.1145/3756681.3756991","title":"PRIMG : Efficient LLM-driven Test Generation Using Mutant Prioritization","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Prioritization; Test case; Process (computing); Mutation; Code coverage; Code (set theory); Test (biology); Software","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002920238,0.001450087,0.0008297691,0.001618822,0.0003505666,0.0009125098,0.002486398,0.001011429,0.002777019],"category_scores_gemma":[0.01242154,0.0005935758,0.0009810593,0.0006427039,0.00108194,0.001405967,0.002092842,0.001486075,0.0009954078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076692,"about_ca_system_score_gemma":0.002268292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003519351,"about_ca_topic_score_gemma":0.004445635,"domain_scores_codex":[0.9971924,0.0009782242,0.0001459659,0.0004531823,0.0009960884,0.0002341259],"domain_scores_gemma":[0.9944634,0.003191144,0.000517041,0.0009849684,0.000677017,0.0001664215],"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":[0.000402559,0.0004246017,0.008781786,0.0004162085,0.0001197034,0.0007115957,0.000316272,0.2781396,0.04893909,0.01822348,0.01158931,0.6319357],"study_design_scores_gemma":[0.00005681938,0.00009049169,0.0004131474,0.00001966487,0.00002153428,0.0001428788,0.00001865127,0.9699533,0.01742909,0.009479126,0.002356825,0.00001848677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01483977,0.0001312695,0.9616749,0.0001822944,0.00002855361,0.0002423624,0.0001869206,0.02174039,0.0009736292],"genre_scores_gemma":[0.31413,0.0001098796,0.6813448,0.0002890954,0.00002412431,0.0003926544,0.000972161,0.001460544,0.001276789],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003519351,"threshold_uncertainty_score":0.01544386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03586475559047253,"score_gpt":0.2990342536693706,"score_spread":0.2631694980788981,"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."}}