{"id":"W4404837934","doi":"10.1016/j.procs.2024.09.568","title":"Automating Software Documentation: Employing LLMs for Precise Use Case Description","year":2024,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Software Engineering Research","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"Centre National pour la Recherche Scientifique et Technique","keywords":"Computer science; Documentation; Software; Software engineering; Software documentation; Data science; Programming language; Software development; Software development process","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":[0.007220865,0.0009073746,0.0005132755,0.005216151,0.0009077958,0.003329399,0.001688362,0.001243617,0.003203977],"category_scores_gemma":[0.03002698,0.0008675375,0.001036951,0.002169327,0.00119484,0.003585062,0.003090634,0.00151475,0.001996235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001270518,"about_ca_system_score_gemma":0.002820768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001871345,"about_ca_topic_score_gemma":0.003851613,"domain_scores_codex":[0.9910978,0.005132962,0.0007698478,0.0008107543,0.001994918,0.0001937106],"domain_scores_gemma":[0.9743882,0.01548801,0.001939193,0.005889356,0.002066309,0.000229002],"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":[0.0001337498,0.0002999046,0.004861024,0.0009872003,0.00006076523,0.001466334,0.01230944,0.02123868,0.04568926,0.05399889,0.005080872,0.8538738],"study_design_scores_gemma":[0.0001159936,0.0003199786,0.004609942,0.001652637,0.0001303732,0.003851312,0.004277124,0.6317528,0.1109785,0.08184901,0.1602271,0.0002352084],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007232264,0.00008798126,0.9873104,0.0001523054,0.000010106,0.0003433792,0.0001332408,0.002698394,0.002031851],"genre_scores_gemma":[0.05262882,0.0001015963,0.9449503,0.00003714295,0.000006942165,0.0003685541,0.0004259112,0.0003276547,0.001153167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007220865,"threshold_uncertainty_score":0.03818804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04452629760129762,"score_gpt":0.3145313374387538,"score_spread":0.2700050398374562,"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."}}