{"id":"W4376632359","doi":"10.48550/arxiv.2305.07097","title":"Automated Smell Detection and Recommendation in Natural Language Requirements","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Usability; Ambiguity; Natural language; Quality (philosophy); Natural language processing; Requirements elicitation; Code smell; Domain (mathematical analysis); Recall; Requirements management; Requirements analysis; Non-functional testing; Artificial intelligence; Precision and recall; Natural (archaeology); Requirements engineering; Software engineering; Human–computer interaction; Software quality; Programming language; Linguistics; Software; Software development","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004670071,0.001296122,0.001046466,0.004441355,0.0005818634,0.001754396,0.001645499,0.001549868,0.001843008],"category_scores_gemma":[0.03479614,0.0009452169,0.001500987,0.001640194,0.0006143592,0.002267933,0.001279996,0.001143284,0.001555584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009962782,"about_ca_system_score_gemma":0.00168335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003913121,"about_ca_topic_score_gemma":0.008297211,"domain_scores_codex":[0.989819,0.004028173,0.001134588,0.001861913,0.002870268,0.000286008],"domain_scores_gemma":[0.9481021,0.03240288,0.007840171,0.004973589,0.006192361,0.0004889496],"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":[0.0007712948,0.001023699,0.03694795,0.003956252,0.0003187566,0.002864545,0.003259011,0.03676593,0.1550047,0.004236357,0.0213235,0.733528],"study_design_scores_gemma":[0.000173478,0.0006343409,0.02949902,0.0005228451,0.0001850768,0.002431789,0.001506845,0.8034135,0.1263766,0.008007957,0.02701735,0.0002311529],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1707434,0.0006451164,0.7789332,0.00099631,0.00006135614,0.001025788,0.003480692,0.04102043,0.003093684],"genre_scores_gemma":[0.2847356,0.0003038926,0.7053513,0.0003157555,0.00002254657,0.0004169427,0.006134427,0.0008221666,0.001897406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004670071,"threshold_uncertainty_score":0.02469796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07626307219116117,"score_gpt":0.2386387302149671,"score_spread":0.162375658023806,"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."}}