{"id":"W4387738797","doi":"10.1002/jrs.6608","title":"A machine learning approach for the automated classification of bulk sp<sup>2</sup> and sp<sup>3</sup> carbon materials","year":2023,"lang":"en","type":"article","venue":"Journal of Raman Spectroscopy","topic":"Diamond and Carbon-based Materials Research","field":"Materials Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Raman spectroscopy; Glassy carbon; Carbon fibers; Amorphous carbon; Materials science; Crystallinity; Highly oriented pyrolytic graphite; Graphite; Analytical Chemistry (journal); Principal component analysis; Amorphous solid; Pyrolytic carbon; Pyrolysis; Chemistry; Artificial intelligence; Crystallography; Computer science; Composite material; Physical chemistry; Organic chemistry; Physics; Optics","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":[0.003875415,0.0003091069,0.0007476682,0.000367775,0.0002746098,0.0004361547,0.00061601,0.000163483,0.0002051343],"category_scores_gemma":[0.0004420478,0.0002123652,0.0001528473,0.0004562321,0.0002712115,0.0002343628,0.0001454579,0.0002974366,0.00001572812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001103393,"about_ca_system_score_gemma":0.0002080232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000130907,"about_ca_topic_score_gemma":0.000001811367,"domain_scores_codex":[0.9967079,0.0004205082,0.001013072,0.0003855497,0.0008118864,0.000661138],"domain_scores_gemma":[0.997955,0.0004244632,0.0007640221,0.0003824659,0.0002928742,0.0001811248],"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":[0.0007136571,0.0001054754,0.000459149,0.0002885495,0.0000608011,0.00001297206,0.0006995357,0.009758975,0.9867144,0.0002794952,0.0007073777,0.0001996233],"study_design_scores_gemma":[0.001630791,0.0008312822,0.001579695,0.0001268605,0.0001225431,0.00006959881,0.00103188,0.2717904,0.7215608,0.000460673,0.0005450585,0.0002504582],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969612,0.0004247063,0.0006481088,0.0005150406,0.0002608452,0.0006029998,0.00009856508,0.0001686151,0.0003198859],"genre_scores_gemma":[0.9958201,0.0004644611,0.00272019,0.00003387533,0.0005643771,0.00005240592,0.00004310319,0.00006724177,0.000234256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2651536,"threshold_uncertainty_score":0.8660002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02362037421684576,"score_gpt":0.2959083274788911,"score_spread":0.2722879532620453,"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."}}