{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002453581,0.001503206,0.0006295375,0.001873883,0.0003121854,0.001040898,0.002423378,0.001197946,0.003728988],"category_scores_gemma":[0.02050791,0.0005374316,0.0009827206,0.0008529376,0.0006720114,0.001359207,0.001648649,0.001199314,0.001649812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000672764,"about_ca_system_score_gemma":0.001623476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001917999,"about_ca_topic_score_gemma":0.002730194,"domain_scores_codex":[0.996437,0.001152287,0.0002557518,0.0005695011,0.001293384,0.0002921917],"domain_scores_gemma":[0.984841,0.008543209,0.0008537556,0.002475083,0.002897556,0.0003893363],"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":[0.0009361898,0.001325676,0.02370911,0.0009257607,0.0002533793,0.002590376,0.0006291416,0.1724784,0.09230539,0.0126732,0.03507987,0.6570935],"study_design_scores_gemma":[0.0002250563,0.0004642255,0.003315279,0.0000783808,0.00005993319,0.0008772137,0.0001352396,0.8769232,0.09681966,0.009610995,0.01143174,0.00005905462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1325165,0.0003435961,0.8040942,0.00049731,0.0001269695,0.0007617167,0.002292083,0.05437401,0.00499366],"genre_scores_gemma":[0.4766448,0.0001890554,0.5066499,0.0004589709,0.00003764297,0.0008865075,0.00828789,0.004094905,0.002750355],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003728988,"threshold_uncertainty_score":0.01297593,"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."}}