{"id":"W4393110811","doi":"10.1038/s41598-024-57498-w","title":"Optimising the manufacturing of a β-Ti alloy produced via direct energy deposition using small dataset machine learning","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Additive Manufacturing Materials and Processes","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"RMIT University; Australian Research Council; Ontario Ministry of Natural Resources and Forestry","keywords":"Mean squared error; Laser power scaling; Artificial neural network; Grain size; Power (physics); Materials science; Energy (signal processing); Laser; Deposition (geology); Computer science; Regression; Process (computing); Linear regression; Layer (electronics); Biological system; Artificial intelligence; Statistics; Mathematics; Machine learning; Composite material; Optics; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009477244,0.0001885561,0.0001908586,0.0001651534,0.0003183501,0.0005529904,0.0001333155,0.00004810359,0.00009496201],"category_scores_gemma":[0.00004403847,0.000138917,0.00005983677,0.0002131745,0.00008948742,0.0002298691,0.0001025607,0.0001348897,0.000003245882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004765699,"about_ca_system_score_gemma":0.00003285848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002001682,"about_ca_topic_score_gemma":0.00003016582,"domain_scores_codex":[0.998499,0.00004979026,0.0004080499,0.0004771716,0.0002718491,0.0002940906],"domain_scores_gemma":[0.9993274,0.00006056776,0.0001086011,0.0004143063,0.00003894721,0.0000501858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006236856,0.00001258356,0.0000236596,0.0006167729,0.0000797596,0.0003106043,0.0002968585,0.2591375,0.7287659,0.000006657884,0.0009420435,0.009801365],"study_design_scores_gemma":[0.00002124349,0.000008682045,0.00002389107,0.0001942358,0.00004339228,0.0002788392,0.00001351565,0.05576828,0.9175417,0.0002728349,0.02567195,0.0001613689],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9727802,0.002073052,0.0177012,0.00002803712,0.00617729,0.0001849202,0.00010777,0.0004507798,0.0004967124],"genre_scores_gemma":[0.9978572,0.00002442511,0.0009692899,0.00000522319,0.0001423092,0.000009642811,0.0007987841,0.00004343015,0.0001497545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2033693,"threshold_uncertainty_score":0.566487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01595596376395102,"score_gpt":0.2185812960255057,"score_spread":0.2026253322615546,"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."}}