{"id":"W4407416591","doi":"10.1007/978-3-031-81573-7_6","title":"Leveraging Conversational AI for Accelerating User-Driven Software Testing","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Software testing; Human–computer interaction; Software; Software engineering; Programming language","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":[0.001959268,0.0009695049,0.0006732589,0.0008924365,0.0007122023,0.002171555,0.002506349,0.001222788,0.008417781],"category_scores_gemma":[0.01126111,0.000618449,0.0006856491,0.0004904154,0.001112493,0.003580527,0.002831414,0.002814444,0.002697595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004937598,"about_ca_system_score_gemma":0.001054426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002040979,"about_ca_topic_score_gemma":0.003108156,"domain_scores_codex":[0.9970493,0.001207992,0.0001375992,0.0004414504,0.0009138968,0.0002496428],"domain_scores_gemma":[0.9912572,0.006302937,0.0002286274,0.001207483,0.0007505875,0.0002531906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007598666,0.0007987246,0.002638201,0.0004617636,0.0001586722,0.0005626878,0.001748034,0.04164641,0.105094,0.06026279,0.01398773,0.7718811],"study_design_scores_gemma":[0.00004947549,0.0001670081,0.0003095036,0.00004382842,0.00006242655,0.0002333521,0.0001775967,0.8914639,0.0342398,0.05666563,0.01653931,0.00004809508],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01643689,0.0002906382,0.9576495,0.0003001785,0.0002073592,0.0001276587,0.00008040517,0.0146478,0.01025962],"genre_scores_gemma":[0.3852567,0.0002190881,0.6025667,0.0003886629,0.0001361532,0.0002069447,0.0002788545,0.001659565,0.009287364],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.008417781,"threshold_uncertainty_score":0.02816027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04890575513938641,"score_gpt":0.2681314680830162,"score_spread":0.2192257129436298,"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."}}