{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001778377,0.000266325,0.0002097626,0.000536177,0.0001899116,0.001168116,0.0009159408,0.000190338,0.00004427442],"category_scores_gemma":[0.000560133,0.0002117536,0.00007685021,0.0006198282,0.00003659594,0.0002582359,0.00164688,0.00173165,0.00005795867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002856056,"about_ca_system_score_gemma":0.0004250427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004890891,"about_ca_topic_score_gemma":0.0001080931,"domain_scores_codex":[0.9971423,0.0002666745,0.000231668,0.0007433858,0.001142779,0.0004732475],"domain_scores_gemma":[0.9975216,0.0006759424,0.00008000174,0.00128737,0.0002969618,0.0001380562],"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":[0.00004537337,0.001345169,0.0004768193,0.02600959,0.0007961517,0.1692183,0.01471772,0.004457127,0.01578396,0.08940642,0.04414493,0.6335984],"study_design_scores_gemma":[0.0001201766,0.0002804109,0.00002288679,0.000994991,0.0000157737,0.0003789797,0.00005215953,0.9888853,0.006594309,0.002166831,0.0001879962,0.0003001887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1904768,0.003294502,0.7906268,0.00354402,0.00164522,0.003188058,0.0001343486,0.006391876,0.0006983944],"genre_scores_gemma":[0.8627592,0.00001775191,0.1363875,0.00003698522,0.000226712,0.0002757956,0.00006718337,0.00004245908,0.0001863805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9844282,"threshold_uncertainty_score":0.9998688,"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."}}