{"id":"W4416570873","doi":"10.1038/s41524-025-01786-0","title":"From biomass waste to CO2 capture: a multi-fidelity machine learning workflow for high-throughput screening of activated carbons","year":2025,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Biomass (ecology); Convolutional neural network; Probabilistic logic; Artificial neural network; Scarcity; Throughput","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001635786,0.0003859682,0.0007961809,0.0002746091,0.000371621,0.0003220326,0.0007033264,0.0001695287,0.0006675474],"category_scores_gemma":[0.001348801,0.0003693609,0.00009048059,0.0005417475,0.0001778278,0.0002561681,0.0004249284,0.0001323319,0.00004966987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001141533,"about_ca_system_score_gemma":0.000198115,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007107691,"about_ca_topic_score_gemma":0.00005426692,"domain_scores_codex":[0.9963286,0.0006041155,0.001080327,0.0008964575,0.0005578266,0.0005326699],"domain_scores_gemma":[0.9974169,0.001027093,0.0005733763,0.0003914825,0.0004570952,0.0001341278],"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":[0.0003517113,0.00006835886,0.0003295273,0.0001068234,0.00003357989,0.000002230237,0.0002887195,0.1766767,0.8210781,0.0006681907,0.0002051496,0.0001909146],"study_design_scores_gemma":[0.001533357,0.0001108265,0.006717975,0.0003238859,0.00005660566,0.000002227208,0.00009343052,0.03360101,0.9503836,0.006449536,0.0003151468,0.0004123804],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6854937,0.00004025674,0.3104845,0.0006909622,0.001488968,0.0006357254,0.0009712611,0.0001718049,0.00002286526],"genre_scores_gemma":[0.6980588,8.254374e-7,0.3009043,0.0002248421,0.0001594757,0.0000967715,0.000377208,0.00003064967,0.0001470954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1430757,"threshold_uncertainty_score":0.9998758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01981743661095644,"score_gpt":0.2984894838998237,"score_spread":0.2786720472888672,"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."}}