{"id":"W4411337744","doi":"10.1109/designing66910.2025.00007","title":"Assessing LLMs for Front-end Software Architecture Knowledge","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Front and back ends; Computer science; Architecture; Software; Software engineering; Computer architecture; Operating system; History","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":[0.01542892,0.0009383426,0.0004617056,0.004248029,0.0005551002,0.003636536,0.001214352,0.001674478,0.00261518],"category_scores_gemma":[0.1157753,0.0004120496,0.0006635003,0.001432464,0.001074363,0.007458733,0.003978769,0.001233794,0.0007926464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001856736,"about_ca_system_score_gemma":0.001808968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003703141,"about_ca_topic_score_gemma":0.00385076,"domain_scores_codex":[0.9895628,0.004916131,0.001154146,0.001191998,0.002803648,0.0003712136],"domain_scores_gemma":[0.8795103,0.09787039,0.00651645,0.00763732,0.006397218,0.002068426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001742772,0.001698,0.2239442,0.001527613,0.0003543981,0.0002320497,0.00804021,0.05221248,0.01933632,0.01263662,0.003209415,0.6750659],"study_design_scores_gemma":[0.000165195,0.003837012,0.1532852,0.0006287426,0.0002947546,0.0005239357,0.007746281,0.7459889,0.04654386,0.02995096,0.01079095,0.0002440688],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8924518,0.0004364335,0.09079755,0.0005168132,0.00002848144,0.0005913976,0.0006894796,0.00236542,0.01212251],"genre_scores_gemma":[0.928274,0.00008816978,0.06989015,0.00005728646,0.000005278339,0.000278176,0.0007163638,0.00005217563,0.0006383929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01542892,"threshold_uncertainty_score":0.08159685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02297468073865381,"score_gpt":0.3274210602717075,"score_spread":0.3044463795330537,"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."}}