{"id":"W4411551806","doi":"10.1109/icse55347.2025.00141","title":"Feature-Driven End-to-End Test Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"End-to-end principle; Computer science; Test (biology); Feature (linguistics); Artificial intelligence; Geology","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":[0.0001425046,0.00008608825,0.00008225856,0.0001446684,0.0001067263,0.0001771211,0.0004941022,0.00004840847,0.00001018213],"category_scores_gemma":[0.0004143892,0.00007449406,0.0000279853,0.0004856163,0.00001274174,0.00013029,0.0002144863,0.00007881334,0.00004828993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003437379,"about_ca_system_score_gemma":0.00006143732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005616687,"about_ca_topic_score_gemma":0.00002283096,"domain_scores_codex":[0.9993281,0.00001974059,0.00008104704,0.0002856452,0.0001338114,0.0001516012],"domain_scores_gemma":[0.9991491,0.0002342305,0.00002028187,0.000470379,0.00007723245,0.00004876148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.296432e-7,0.00003171165,0.007026919,0.000004171126,0.000004484115,0.000004922615,0.00007578314,0.00004453865,0.003316022,0.02674616,0.8739598,0.08878508],"study_design_scores_gemma":[0.000426978,0.0003785074,0.02720151,0.0001689602,0.00001999157,0.00003884495,0.000004420412,0.6408201,0.1358571,0.04309738,0.1511449,0.0008411613],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001075351,0.00002952236,0.9688978,0.008214894,0.0002592372,0.0001073035,8.601611e-7,0.009459448,0.0119556],"genre_scores_gemma":[0.354536,0.000001416636,0.6372688,0.002954567,0.0000623316,0.00001951003,0.0000023044,0.000003527898,0.005151626],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7228149,"threshold_uncertainty_score":0.3037779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02046683678632496,"score_gpt":0.2770269417471696,"score_spread":0.2565601049608447,"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."}}