{"id":"W4393142189","doi":"10.1007/s00766-024-00416-3","title":"Improving requirements completeness: automated assistance through large language models","year":2024,"lang":"en","type":"article","venue":"Requirements Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Terminology; Completeness (order theory); Computer science; Natural language; Artificial intelligence; Filter (signal processing); Process (computing); Noise (video); Software engineering; Natural language processing; Programming language; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006545634,0.000372332,0.000299714,0.0003060277,0.0001262938,0.0006382905,0.001150036,0.0001046512,0.00002173669],"category_scores_gemma":[0.000182757,0.0003848682,0.0001183227,0.001091338,0.00001813412,0.00251814,0.000608457,0.0003466139,0.0001043875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004443831,"about_ca_system_score_gemma":0.00009614223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005359967,"about_ca_topic_score_gemma":0.000002049744,"domain_scores_codex":[0.9967229,0.00003312724,0.0004625664,0.0008125836,0.000916035,0.00105278],"domain_scores_gemma":[0.9985477,0.0002288476,0.00004956498,0.0009376295,0.00007584634,0.0001603775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002519504,0.0004695594,0.0013686,0.005905764,0.001258743,0.002719647,0.01046739,0.3295246,0.38076,0.2313021,0.006508935,0.02968955],"study_design_scores_gemma":[0.0003276434,0.00003312217,0.0004506727,0.0004202175,0.00001068819,0.0000175388,0.00002177064,0.9921067,0.003331019,0.0001335888,0.002732939,0.0004141458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02251823,0.002836609,0.9640875,0.00007894549,0.001465405,0.0003118014,0.00002001637,0.008246606,0.0004349056],"genre_scores_gemma":[0.9300019,0.00003022212,0.06932965,0.00005416338,0.0001512058,0.00008299029,0.00001989492,0.00009279387,0.0002371993],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9074836,"threshold_uncertainty_score":0.9998603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03724158375314305,"score_gpt":0.3098539232716619,"score_spread":0.2726123395185188,"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."}}