{"id":"W7125019428","doi":"10.1109/aiware69974.2025.00018","title":"Software Testing with Large Language Models: An Interview Study with Practitioners","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Test strategy; System integration testing; Process (computing); Qualitative research; Test (biology); Thematic analysis; Software; Personal software process; Manual testing","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":[0.0375014,0.001057863,0.001174121,0.002594193,0.007412371,0.004649197,0.001760246,0.003366582,0.001863334],"category_scores_gemma":[0.05983222,0.001255245,0.0004865686,0.002420854,0.00843175,0.007479182,0.007187146,0.004826381,0.0005186635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005967379,"about_ca_system_score_gemma":0.005132913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006204258,"about_ca_topic_score_gemma":0.007873149,"domain_scores_codex":[0.9664369,0.02613649,0.0009574734,0.001597194,0.001729247,0.003142724],"domain_scores_gemma":[0.9313324,0.05386433,0.003318246,0.001283982,0.006315089,0.003885914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002674083,0.00007943497,0.002965732,0.00006089573,0.000002472487,0.0007001613,0.9897664,0.00008265588,0.0008374825,0.0005844253,0.0003188417,0.004574693],"study_design_scores_gemma":[0.00000869286,0.000189203,0.0008970816,0.0001617504,0.000004458055,0.0003260516,0.9921215,0.0004517476,0.0002931691,0.0004098296,0.005119162,0.00001738457],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9847623,0.000670233,0.008873368,0.002721829,0.00004048059,0.000246457,0.00003188918,0.00003411305,0.002619298],"genre_scores_gemma":[0.9940839,0.0005580382,0.002883863,0.0009856909,0.00001857043,0.0002573305,0.00003032189,0.00003163719,0.001150665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0375014,"threshold_uncertainty_score":0.1983287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04037925872012102,"score_gpt":0.3093107558454273,"score_spread":0.2689314971253063,"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."}}