{"id":"W7084074799","doi":"10.1109/iri66576.2025.00009","title":"Leveraging LLMs for Automatic Feature Extraction in Embedded Systems to Support Software Reuse","year":2025,"lang":"en","type":"article","venue":"","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; Trent University","funders":"","keywords":"Reuse; Software; Feature extraction; Benchmark (surveying); Feature (linguistics); Cluster analysis; Scalability; Cosine similarity; Thresholding","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":[0.00104388,0.001566714,0.0007902673,0.003485832,0.0005091164,0.0009283048,0.001165243,0.0005914834,0.000934325],"category_scores_gemma":[0.005520011,0.000683634,0.001839131,0.001662609,0.0004887098,0.002166717,0.001630947,0.001041414,0.0009528511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221103,"about_ca_system_score_gemma":0.001706481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009002965,"about_ca_topic_score_gemma":0.0144578,"domain_scores_codex":[0.9987796,0.0002165037,0.0001086079,0.0003687468,0.0004313548,0.00009525203],"domain_scores_gemma":[0.9979664,0.0008259114,0.0003058104,0.0004698625,0.0003793579,0.00005259715],"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":[0.0002155416,0.00023606,0.02136764,0.0006162489,0.000243105,0.0006126527,0.0009960685,0.1603459,0.05231247,0.00530062,0.006493724,0.75126],"study_design_scores_gemma":[0.0000137549,0.00008322826,0.002417543,0.00004825701,0.00006807867,0.0001404145,0.0001286039,0.9568906,0.02766688,0.007609257,0.004900318,0.00003322832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05159386,0.0002864457,0.9263366,0.000174111,0.00001593124,0.0001163659,0.0007545667,0.01998679,0.0007353522],"genre_scores_gemma":[0.4195549,0.0002099623,0.5722741,0.000145725,0.00001681085,0.0002734888,0.004244763,0.001736776,0.001543483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009002965,"threshold_uncertainty_score":0.01790112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01429696621296739,"score_gpt":0.287380087005104,"score_spread":0.2730831207921366,"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."}}