{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006184702,0.0003483472,0.00031514,0.0004630537,0.0006843678,0.0008200126,0.0007246881,0.0002168169,0.00002461363],"category_scores_gemma":[0.001363627,0.0003567089,0.0001069695,0.001839887,0.0001099575,0.0002659341,0.0005682178,0.0002354499,0.00002130945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004126691,"about_ca_system_score_gemma":0.0007687988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001873828,"about_ca_topic_score_gemma":0.000009405718,"domain_scores_codex":[0.9972275,0.0001453351,0.0007046655,0.0009430493,0.0004672685,0.0005121563],"domain_scores_gemma":[0.9976769,0.0004529297,0.0002357518,0.0009702796,0.0005515423,0.0001126163],"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":[0.00002164542,0.004052535,0.03929709,0.0005798043,0.0001492386,0.000115483,0.003048781,0.1661957,0.1588038,0.06331199,0.03521546,0.5292085],"study_design_scores_gemma":[0.0002511609,0.0001504769,0.0009549832,0.0004476127,0.00004563422,0.00002291502,0.00000385702,0.9688519,0.02654023,0.002062775,0.0003101365,0.0003582877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03381949,0.0003693461,0.9548264,0.0006521331,0.001467352,0.000599968,0.000004080744,0.006740556,0.001520666],"genre_scores_gemma":[0.6734825,0.00002402938,0.3254188,0.0004788775,0.000174477,0.00001168383,0.0000053593,0.00001514723,0.0003891204],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8026562,"threshold_uncertainty_score":0.9998885,"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."}}