{"id":"W4200389846","doi":"10.1016/j.mlwa.2021.100245","title":"Multistep networks for roll force prediction in hot strip rolling mill","year":2021,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Metallurgy and Material Forming","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Essar Steel Algoma (Canada); McGill University","funders":"Mitacs","keywords":"Mill; Process (computing); Rolling mill; Steel mill; Engineering; Strip steel; Stability (learning theory); Mechanical engineering; Computer science; Materials science; Metallurgy; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0001521999,0.0001199737,0.0001485147,0.00005751897,0.0001449061,0.000036445,0.00006986284,0.00007311404,0.00003815611],"category_scores_gemma":[0.00002548849,0.0001187247,0.00003399514,0.0002417251,0.00001088784,0.00007951334,0.00001594197,0.0002254762,0.000008703963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003695412,"about_ca_system_score_gemma":0.00001261573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000238888,"about_ca_topic_score_gemma":0.0001496759,"domain_scores_codex":[0.9993083,0.00002018031,0.0002042422,0.0001879578,0.00006607268,0.0002131773],"domain_scores_gemma":[0.9996412,0.00007758184,0.00003756507,0.0001554879,0.00003941757,0.00004875224],"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":[0.00002914539,0.00001590834,0.001369891,0.00005157593,0.00001785956,0.000001179802,0.00006295723,0.9898046,0.002399738,0.0006314254,0.0000189673,0.005596785],"study_design_scores_gemma":[0.0006424558,0.00002724411,0.001438453,0.00003354385,0.00002302015,0.000009794793,0.00003309506,0.9553704,0.0009450757,0.0001078588,0.0412368,0.000132291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03430568,0.0004913784,0.9630276,0.00002724935,0.00009969107,0.000474653,0.000019438,0.0002906685,0.00126362],"genre_scores_gemma":[0.980845,0.0000624371,0.01656638,0.00002064806,0.0001529231,0.0007520789,0.0004473899,0.00004515321,0.001107994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9465393,"threshold_uncertainty_score":0.4841453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006460774580200423,"score_gpt":0.20653405277259,"score_spread":0.2000732781923896,"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."}}