{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000425702,0.0002850001,0.0003546778,0.0002498848,0.001355295,0.0003790437,0.001997838,0.0001947744,2.977897e-7],"category_scores_gemma":[0.0006591997,0.0002529593,0.0001811046,0.000265125,0.0002313362,0.0004686175,0.0009450107,0.000383485,1.482797e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008892671,"about_ca_system_score_gemma":0.000394396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002953795,"about_ca_topic_score_gemma":0.00001023949,"domain_scores_codex":[0.9986812,0.000009420968,0.0006113906,0.0002159736,0.0002314675,0.0002504921],"domain_scores_gemma":[0.9966273,0.001864239,0.0004790586,0.0005494218,0.000442134,0.00003788427],"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":[0.000001453207,0.00001281539,0.0000772065,0.0005598232,0.00009807952,9.090972e-8,0.001429372,0.8423688,0.000005923539,0.08846105,0.001215561,0.06576986],"study_design_scores_gemma":[0.0001767504,0.00005026281,0.0000341798,0.0006081871,0.00003550354,0.00000765475,0.000001085274,0.9799621,0.00005433349,0.008686919,0.01008813,0.0002949586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002992717,0.0001304723,0.9963837,0.0009831651,0.0004598917,0.0006222427,0.00004960191,0.0007904907,0.0005505633],"genre_scores_gemma":[0.002900906,0.00001124903,0.996263,0.0005255631,0.0001294992,0.00005453016,0.00003731201,0.00001525737,0.00006273316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1375933,"threshold_uncertainty_score":0.9999923,"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."}}