{"id":"W4409897988","doi":"10.1017/s0890060425000083","title":"Enhancing TRIZ through environment-based design methodology supported by a large language model","year":2025,"lang":"en","type":"article","venue":"Artificial intelligence for engineering design analysis and manufacturing","topic":"Design Education and Practice","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"TRIZ; Computer science; Architectural engineering; Engineering; Systems engineering; Manufacturing engineering","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":[0.001209299,0.0003054466,0.0004389238,0.0004412447,0.0001404973,0.0001138262,0.0001822249,0.0001495507,0.0001023013],"category_scores_gemma":[0.0001675981,0.0003286392,0.0001758424,0.0003582611,0.0000251179,0.0002225121,0.00002167157,0.0002051148,0.00001061094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008413487,"about_ca_system_score_gemma":0.00003374529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003257509,"about_ca_topic_score_gemma":0.000009706847,"domain_scores_codex":[0.9983529,0.0001050489,0.0005298806,0.0003973384,0.0001259192,0.0004888568],"domain_scores_gemma":[0.9982339,0.001285875,0.00006935558,0.0002953726,0.00002152527,0.00009402866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003857635,0.00004180748,0.000001691026,0.00007109954,0.0004755867,0.00000151873,0.000551304,0.878149,0.1113305,0.0009819641,0.0002166968,0.008140177],"study_design_scores_gemma":[0.00003935555,0.00001526662,0.000002662036,0.000008674603,0.0003635758,3.368056e-7,0.0001830622,0.5104387,0.487267,0.0006934651,0.0008198193,0.0001681404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004072884,0.0005868154,0.9943291,0.0001028939,0.000165583,0.0004197883,0.00002190793,0.0002590744,0.00004193784],"genre_scores_gemma":[0.7033653,0.0001102595,0.2959653,0.0001258069,0.00002748073,0.0001358927,0.00004387491,0.0000365062,0.0001895741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6992924,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05799305597294572,"score_gpt":0.3134753793616325,"score_spread":0.2554823233886868,"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."}}