{"id":"W4408162729","doi":"10.1007/978-3-031-73143-3_14","title":"Empirical Evaluation of Tools for Hairy Natural Language Requirements Engineering Tasks","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language; Software engineering; Linguistics; Natural language processing; Philosophy","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":[0.007880617,0.0008257465,0.000488731,0.001859548,0.0006232558,0.001544381,0.002034987,0.0010908,0.005756217],"category_scores_gemma":[0.09306299,0.0004485975,0.0004332101,0.001401183,0.0008248467,0.002709444,0.00270306,0.001373625,0.002655894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009933175,"about_ca_system_score_gemma":0.000995193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002921692,"about_ca_topic_score_gemma":0.004521383,"domain_scores_codex":[0.9902789,0.006045463,0.0007624538,0.0007618912,0.00186403,0.0002872846],"domain_scores_gemma":[0.7732897,0.2048865,0.004229289,0.009401738,0.006525549,0.001667196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01144626,0.01307219,0.03152568,0.004533608,0.0002874374,0.0009102696,0.01372177,0.01732249,0.02466507,0.005587536,0.03155995,0.8453677],"study_design_scores_gemma":[0.009008178,0.03543958,0.2734838,0.002622077,0.001083668,0.002985485,0.02982932,0.4390621,0.0787191,0.02021726,0.1069132,0.000636279],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9491134,0.00101844,0.02940136,0.000370087,0.00009864925,0.0009632435,0.001919117,0.003581991,0.01353364],"genre_scores_gemma":[0.9252781,0.0004879163,0.06042643,0.0001961303,0.00003691609,0.0009035452,0.005434962,0.000624423,0.006611648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007880617,"threshold_uncertainty_score":0.04167718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09265498278320823,"score_gpt":0.3723471088161209,"score_spread":0.2796921260329127,"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."}}