{"id":"W4399441490","doi":"10.21203/rs.3.rs-4413910/v1","title":"Automatic Test Case Generation Mechanism with Natural Language based Korean Requirements","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"Computer science; Traceability; Test case; Software engineering; Software requirements specification; Requirements engineering; Natural language; Requirements traceability; Test suite; Requirements analysis; Test script; Requirements elicitation; Software requirements; Automation; User requirements document; Programming language; Software; Requirement; Artificial intelligence; Software development; Software design; Machine learning; Engineering","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":[0.001934781,0.0008036015,0.0004722335,0.001563163,0.0003578838,0.0009058474,0.001469388,0.0006502923,0.005865291],"category_scores_gemma":[0.008720241,0.0004129355,0.0008519913,0.0007004875,0.000361724,0.001381222,0.0009985856,0.0007160467,0.001349744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004170926,"about_ca_system_score_gemma":0.001235707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001336763,"about_ca_topic_score_gemma":0.00170352,"domain_scores_codex":[0.9976694,0.0007322788,0.0003575173,0.0004372778,0.0006462727,0.0001572006],"domain_scores_gemma":[0.9933736,0.003500189,0.0005812807,0.001041046,0.00137135,0.0001325756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001784042,0.001197006,0.01052552,0.001575101,0.0001893151,0.005789476,0.001721027,0.0295908,0.3322017,0.02657281,0.02468022,0.564173],"study_design_scores_gemma":[0.0006477233,0.0006843399,0.006145509,0.0002154874,0.0003655336,0.004487059,0.0007680953,0.6823902,0.2587023,0.01471507,0.03070115,0.0001774728],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09998769,0.0001366248,0.8708861,0.0003524038,0.0000602068,0.001087967,0.001717583,0.02005689,0.005714643],"genre_scores_gemma":[0.5146477,0.00009555274,0.475822,0.0002447969,0.00001941196,0.000610259,0.00483748,0.001130928,0.002591912],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005865291,"threshold_uncertainty_score":0.01962143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06511175925613648,"score_gpt":0.3934296893249604,"score_spread":0.3283179300688239,"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."}}