{"id":"W6979295305","doi":"","title":"Mutation-Guided Unit Test Generation with a Large Language Model","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Animal health and immunology","field":"Veterinary","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mutation; Unit testing; Test (biology); Code (set theory); Focus (optics); Test case; Mutation testing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00193643,0.0009370673,0.0005510692,0.0006690829,0.0002331403,0.0006645037,0.001518704,0.000839174,0.001623068],"category_scores_gemma":[0.01000613,0.0003295976,0.0006433569,0.000360644,0.0007828037,0.001084535,0.0009356671,0.0008997152,0.0004692131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006637464,"about_ca_system_score_gemma":0.001581328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00190914,"about_ca_topic_score_gemma":0.003334575,"domain_scores_codex":[0.998377,0.0008252169,0.00006938622,0.0002621857,0.0003456634,0.0001205552],"domain_scores_gemma":[0.9937415,0.004583813,0.0003839596,0.0006340658,0.000517485,0.0001392492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007115256,0.0005041443,0.01189396,0.0004309815,0.00009597284,0.0007231748,0.0004177216,0.5906366,0.05315433,0.01038822,0.005938445,0.325105],"study_design_scores_gemma":[0.0000664582,0.0003275982,0.0005074539,0.00001917125,0.00003281431,0.000184376,0.00004262201,0.9786404,0.01255923,0.006026735,0.001575259,0.00001777789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1715302,0.000429402,0.8095812,0.0005265048,0.0000711552,0.0002467027,0.0002797452,0.01526128,0.002073702],"genre_scores_gemma":[0.734166,0.0001049897,0.2629325,0.0002980611,0.00002480166,0.0002046623,0.0005000075,0.0005425626,0.001226536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00193643,"threshold_uncertainty_score":0.01024097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1316224685814053,"score_gpt":0.2648505726771767,"score_spread":0.1332281040957714,"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."}}