{"id":"W7125610271","doi":"10.1109/cascon66301.2025.00076","title":"Multi-Label Ambiguity Detection in Software Requirements Using Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Vagueness; Ambiguity; Software requirements specification; Scope (computer science); Software requirements; Natural language; Set (abstract data type); Software; Focus (optics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006496515,0.001792239,0.000951062,0.003916373,0.0009378635,0.001670982,0.001632881,0.001771745,0.0007569188],"category_scores_gemma":[0.01856471,0.0004910448,0.002020472,0.001699682,0.0006332666,0.002409317,0.00208771,0.002116733,0.0009027963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00144293,"about_ca_system_score_gemma":0.001529387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007402692,"about_ca_topic_score_gemma":0.01268625,"domain_scores_codex":[0.9921952,0.003607072,0.0006598117,0.001832419,0.00137796,0.0003276069],"domain_scores_gemma":[0.9815726,0.01306296,0.001136032,0.001705067,0.002234283,0.0002889854],"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":[0.001665152,0.001438668,0.04182371,0.001712974,0.0004286704,0.001866507,0.002254758,0.1315505,0.04873433,0.005034608,0.03076397,0.7327262],"study_design_scores_gemma":[0.0001105382,0.0002985261,0.01049754,0.0001179208,0.000137395,0.0005345848,0.0006496026,0.9457651,0.02227615,0.007168153,0.01234832,0.00009630655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5098052,0.002787867,0.4580037,0.001442472,0.00031399,0.0005651761,0.005492614,0.01717211,0.004416791],"genre_scores_gemma":[0.7230288,0.0004006166,0.2544035,0.0005155177,0.00009989107,0.0005103248,0.01819319,0.0005192058,0.002328917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007402692,"threshold_uncertainty_score":0.03435731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08411771468295513,"score_gpt":0.3581302819086264,"score_spread":0.2740125672256712,"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."}}