{"id":"W4410780386","doi":"10.1002/adts.202401565","title":"Accurate and Efficient Behavioral Modeling of GaN HEMTs Using An Optimized Light Gradient Boosting Machine","year":2025,"lang":"en","type":"article","venue":"Advanced Theory and Simulations","topic":"GaN-based semiconductor devices and materials","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Nazarbayev University","keywords":"Gradient boosting; Boosting (machine learning); Materials science; Computer science; Optoelectronics; Artificial intelligence; Electronic engineering; Engineering; Random forest","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000153153,0.0001102911,0.0001816613,0.00006122213,0.0002139918,0.00003107006,0.00004252076,0.00002102939,0.00003055715],"category_scores_gemma":[0.00000735503,0.0001001999,0.0000287814,0.00007728761,0.00002985107,0.0001320836,0.0000295271,0.00005051152,9.869171e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006514923,"about_ca_system_score_gemma":0.00001617327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004081361,"about_ca_topic_score_gemma":0.000002315098,"domain_scores_codex":[0.9993562,0.00007202518,0.0002291543,0.0001773892,0.00003930458,0.0001259628],"domain_scores_gemma":[0.9995912,0.00009794111,0.00008524627,0.0001288601,0.00005003134,0.0000467464],"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":[0.00005689841,0.00007515391,0.0005186663,0.00001370296,0.00001531278,1.866443e-7,0.0003704753,0.8982173,0.07547604,0.02443712,4.415044e-8,0.000819054],"study_design_scores_gemma":[0.0008651345,0.00002611763,0.00004402669,0.00007563306,0.00008701882,2.787183e-7,0.0005663765,0.9678464,0.0145785,0.01577794,0.00001265467,0.0001199021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.945214,0.0001661776,0.05413862,0.000008889995,0.00008434213,0.0001657496,0.00006679778,0.00001473191,0.0001407248],"genre_scores_gemma":[0.9979982,0.000002024687,0.001894462,0.00001388866,0.0000180062,0.000003744772,0.0000405607,0.000008509659,0.00002057057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06962907,"threshold_uncertainty_score":0.4086031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02377020727741912,"score_gpt":0.3199211227707149,"score_spread":0.2961509154932958,"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."}}