{"id":"W4416400492","doi":"10.1016/j.eswa.2025.130457","title":"Industrial steel slag flow data loading method for deep learning applications","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Deep learning; Slag (welding); Flow (mathematics); Data modeling","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021436,0.0002884226,0.0004343646,0.0001904537,0.001185256,0.0005435054,0.001879843,0.0001701137,0.0001011529],"category_scores_gemma":[0.0002676888,0.0002466947,0.00004374421,0.0007921442,0.000146661,0.0003784303,0.0003925539,0.0002459952,0.0001728922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001287172,"about_ca_system_score_gemma":0.0002361559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003102886,"about_ca_topic_score_gemma":0.00003423377,"domain_scores_codex":[0.9969469,0.0003243456,0.0006421448,0.001186525,0.0003827616,0.0005173482],"domain_scores_gemma":[0.9966172,0.0007948741,0.000382745,0.001827683,0.0002353811,0.0001421321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001585022,0.0002674989,0.0008742152,0.0004204642,0.0000885796,0.000001256971,0.001123783,0.08436124,0.7946636,0.06787739,0.0126422,0.03752123],"study_design_scores_gemma":[0.0006537595,0.00004590442,0.00003001575,0.000101855,0.00004281151,0.00001459854,0.0006530913,0.2875646,0.005405401,0.00019581,0.7049566,0.0003355636],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003395524,0.0005932772,0.9911267,0.0006034636,0.000472787,0.003843119,0.0001369623,0.0004605786,0.002423539],"genre_scores_gemma":[0.09102223,0.0000300782,0.8675895,0.0003411148,0.001934938,0.03355969,0.0006853681,0.0001047031,0.004732426],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7892582,"threshold_uncertainty_score":0.9999985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04090611458481985,"score_gpt":0.3491765939039998,"score_spread":0.3082704793191799,"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."}}