{"id":"W4393106735","doi":"10.1007/978-3-031-50308-5_121","title":"A PoDFA Benchmarking Study Between Manual and AI-supervised Machine Learning Methods to Evaluate Inclusions in Wrought and Foundry Aluminum Alloys","year":2024,"lang":"en","type":"book-chapter","venue":"˜The œminerals, metals & materials series","topic":"Aluminum Alloy Microstructure Properties","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Rio Tinto (Canada)","funders":"","keywords":"Benchmarking; Computer science; Polishing; Foundry; Artificial intelligence; Repeatability; Machine vision; Machine learning; Pattern recognition (psychology); Engineering drawing; Engineering; Mechanical engineering; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008802692,0.001513553,0.001132761,0.002566804,0.001114903,0.0016309,0.003061278,0.002149306,0.004915121],"category_scores_gemma":[0.01811693,0.000374654,0.0009470333,0.001848478,0.00103997,0.002270213,0.001577476,0.001141806,0.001797575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001809557,"about_ca_system_score_gemma":0.0008898905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01307301,"about_ca_topic_score_gemma":0.02142875,"domain_scores_codex":[0.9943343,0.002312618,0.0004733614,0.0008698091,0.00174752,0.0002624348],"domain_scores_gemma":[0.9804073,0.009544506,0.0005279824,0.003060128,0.006034056,0.0004259238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004267917,0.003017914,0.02632352,0.001683238,0.0008872129,0.000364656,0.0003575453,0.1576012,0.01256679,0.005752609,0.1078814,0.679296],"study_design_scores_gemma":[0.000397952,0.002753821,0.03850496,0.0002870778,0.0001741452,0.0005360885,0.0005713262,0.9072329,0.02312506,0.003587222,0.02274284,0.00008667168],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8542371,0.01471255,0.06222643,0.001109943,0.001783328,0.0005287779,0.008206464,0.009768563,0.04742688],"genre_scores_gemma":[0.8787135,0.001062187,0.06267059,0.0003828762,0.0002448289,0.0002361524,0.02805218,0.001139551,0.02749818],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01307301,"threshold_uncertainty_score":0.04655367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02324227165128921,"score_gpt":0.2869924178988994,"score_spread":0.2637501462476102,"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."}}