{"id":"W4408162739","doi":"10.1007/978-3-031-73143-3_5","title":"Detecting Defects in Natural Language Requirements Specifications","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Sheridan College; University of Waterloo","funders":"","keywords":"Computer science; Natural (archaeology); Programming language; History; Archaeology","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":[0.001250457,0.0007354508,0.0004598781,0.001498464,0.0002524761,0.001157669,0.001237284,0.0009520027,0.006766391],"category_scores_gemma":[0.009326797,0.0006341349,0.0009046428,0.0007560682,0.0005934219,0.001920082,0.0008394772,0.001109294,0.002993287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005131376,"about_ca_system_score_gemma":0.0005811415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001430076,"about_ca_topic_score_gemma":0.002930385,"domain_scores_codex":[0.9982499,0.0003190241,0.00009834212,0.0002056527,0.001047694,0.00007933604],"domain_scores_gemma":[0.9930609,0.005111358,0.0003551386,0.0005975179,0.0008360013,0.00003900146],"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":[0.0001106398,0.0001734057,0.004864041,0.000829974,0.00004531013,0.001181047,0.0007540987,0.01930026,0.03938987,0.05020783,0.03419071,0.8489529],"study_design_scores_gemma":[0.00006490762,0.0004643911,0.009491868,0.0009698265,0.0001378013,0.008142491,0.001032949,0.4853353,0.1508425,0.1851956,0.1581869,0.0001354233],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04118354,0.0008115043,0.9162846,0.0007927365,0.0001537551,0.0002164734,0.0008421439,0.008894529,0.0308208],"genre_scores_gemma":[0.1951195,0.0009740957,0.7559483,0.0004342051,0.00006361613,0.0001248168,0.003805372,0.002124337,0.04140579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006766391,"threshold_uncertainty_score":0.02263582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04183263579618568,"score_gpt":0.2915067177688678,"score_spread":0.2496740819726821,"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."}}