{"id":"W7125648772","doi":"10.1109/cascon66301.2025.00080","title":"Reverse Engineering User Stories from Code using Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reverse engineering; Code (set theory); Source code; Modeling language; Natural language; User interface","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":[0.002439017,0.0009090374,0.0003470961,0.001670859,0.0008615958,0.002210372,0.001190438,0.001244224,0.005131367],"category_scores_gemma":[0.04304043,0.0006103762,0.0006740395,0.0009511993,0.001098142,0.004465644,0.00201252,0.002162728,0.001729563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007563218,"about_ca_system_score_gemma":0.001217126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004220371,"about_ca_topic_score_gemma":0.008705552,"domain_scores_codex":[0.9961234,0.001961447,0.0001368617,0.0003220533,0.001313662,0.0001425227],"domain_scores_gemma":[0.9412203,0.04689437,0.001780464,0.004425503,0.005340095,0.0003394011],"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":[0.0017774,0.001316643,0.0333884,0.002901829,0.0002859373,0.009648502,0.07463522,0.03696661,0.06794515,0.08288073,0.06874869,0.619505],"study_design_scores_gemma":[0.0001859635,0.000723796,0.01302843,0.001235664,0.0004198573,0.006761429,0.02087864,0.4704447,0.1329703,0.08100915,0.2720117,0.0003302552],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3926302,0.0006044714,0.5580548,0.004844539,0.0002859801,0.0006422255,0.005486568,0.01003076,0.0274205],"genre_scores_gemma":[0.7787774,0.0004696585,0.1976826,0.0006783277,0.00007437766,0.0003018822,0.005842495,0.003512652,0.01266058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005131367,"threshold_uncertainty_score":0.01716614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02473777147898867,"score_gpt":0.2903271838431037,"score_spread":0.2655894123641151,"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."}}