{"id":"W4391974543","doi":"10.1109/tse.2024.3368208","title":"Software Testing With Large Language Models: Survey, Landscape, and Vision","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":394,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Software engineering; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004307948,0.0002758799,0.0002043153,0.0003335048,0.0001739915,0.000356657,0.0002940583,0.000100362,0.000004650301],"category_scores_gemma":[0.0001307121,0.0002414727,0.00004782404,0.0008946389,0.00001908114,0.0006385835,0.00001028966,0.0004129281,0.00001037041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004373556,"about_ca_system_score_gemma":0.00005627131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007347211,"about_ca_topic_score_gemma":0.00001836886,"domain_scores_codex":[0.9985636,0.00003535745,0.0001922715,0.0005519171,0.0002780079,0.0003788106],"domain_scores_gemma":[0.9979014,0.001423628,0.00002564287,0.0004460401,0.00007669147,0.0001265968],"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":[0.00004930575,0.0003161851,0.004695001,0.001078558,0.0002237394,0.0007250738,0.004010785,0.4715207,0.0002554365,0.0005504697,0.002971538,0.5136032],"study_design_scores_gemma":[0.0002335854,0.0002505039,0.001153659,0.0008959645,0.00002088192,0.0001627627,0.000007736919,0.9957085,0.0006930251,0.0002500827,0.0001439881,0.0004793389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009641844,0.0006335574,0.965713,0.00001924298,0.0003717317,0.0001313164,0.00004195171,0.02343378,0.00001352697],"genre_scores_gemma":[0.5931725,0.00001074565,0.4066329,0.00003383341,0.00002607447,0.00003106284,0.000003327154,0.00004493156,0.0000446815],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5835306,"threshold_uncertainty_score":0.9846971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01712040667441351,"score_gpt":0.2519216021540697,"score_spread":0.2348011954796562,"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."}}