{"id":"W4387605156","doi":"10.48185/jaai.v4i1.838","title":"Hybrid Neural Network Models for the Optimization of Induction Hardening Processes","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Artificial Intelligence","topic":"Laser and Thermal Forming Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Korea Electrotechnology Research Institute","keywords":"Interpretability; Induction heating; Artificial neural network; Black box; Induction hardening; Computer science; Process (computing); White box; Machine learning; Artificial intelligence; Engineering; Materials science","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":[0.0003580045,0.00007644982,0.000129221,0.00007093053,0.0000790581,0.0000295387,0.0001779692,0.0000311601,0.000006570864],"category_scores_gemma":[0.00002887727,0.0000553736,0.00005430889,0.000277422,0.0000316036,0.0001587187,0.00001640001,0.0001226435,0.000001410971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001575453,"about_ca_system_score_gemma":0.00002019888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001441402,"about_ca_topic_score_gemma":0.000001247004,"domain_scores_codex":[0.9992716,0.000004211308,0.0003982668,0.00005399323,0.0001344096,0.0001374735],"domain_scores_gemma":[0.9994779,0.0001338323,0.0001366071,0.00007435037,0.0001541961,0.00002312096],"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":[0.00005832913,0.000005882661,6.095445e-7,0.00004412789,0.00002167521,5.850439e-7,0.0002606976,0.9649709,0.001234778,0.003767889,0.000320451,0.02931408],"study_design_scores_gemma":[0.00001007045,0.00003393664,9.121505e-7,0.00002802514,0.0000185347,0.000004952904,0.000136182,0.7544928,0.1806349,0.06449825,0.00009290346,0.00004854421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04184351,0.0001078668,0.9569512,0.00005369269,0.0004392886,0.000188609,0.000003178109,0.0001162527,0.0002964063],"genre_scores_gemma":[0.9924222,0.0002098616,0.006926563,0.00001000593,0.0003916733,0.00001483781,0.000002093826,0.00001844881,0.0000043132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9505787,"threshold_uncertainty_score":0.225807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05258047746933752,"score_gpt":0.269330008614428,"score_spread":0.2167495311450905,"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."}}