{"id":"W4412520561","doi":"10.1038/s41570-025-00740-4","title":"Developing machine learning for heterogeneous catalysis with experimental and computational data","year":2025,"lang":"en","type":"review","venue":"Nature Reviews Chemistry","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"","keywords":"Throughput; Field (mathematics); Computer science; Machine learning; Experimental data; Heterogeneous catalysis; Computational model; Artificial intelligence; Catalysis; Biochemical engineering; Chemistry; Engineering; Mathematics","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":[0.001319207,0.0006357078,0.00207015,0.00006467904,0.0003322945,0.0002772186,0.001473412,0.0004726531,0.0001911307],"category_scores_gemma":[0.0008688661,0.0004477138,0.0001659861,0.0003242828,0.0001498038,0.0001493775,0.0009142532,0.0007655335,0.00001886891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552629,"about_ca_system_score_gemma":0.0004780226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006416971,"about_ca_topic_score_gemma":0.000001544818,"domain_scores_codex":[0.9967951,0.0002397118,0.0008168782,0.001411545,0.0003562176,0.0003805564],"domain_scores_gemma":[0.9975934,0.0004878772,0.0008455886,0.0008906602,0.00008002537,0.0001024593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004364351,0.000111481,0.00001131276,0.3546778,0.0002064563,0.0000425882,0.00007815281,0.0005949086,0.004849467,0.00008764544,0.0009661192,0.6383305],"study_design_scores_gemma":[0.0001465396,0.00001694617,1.154491e-7,0.01553614,0.000395082,0.0002446116,0.000002802566,0.0008138577,0.001045084,0.00001054669,0.9812616,0.0005266585],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002567127,0.9946579,0.003701309,0.00003027098,0.0001704798,0.0009743999,0.0002620421,0.00008602023,0.00009190637],"genre_scores_gemma":[0.00001869276,0.9326986,0.06265968,0.00007520727,0.0001759901,0.0002634474,0.003670139,0.00004798413,0.0003902348],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9802955,"threshold_uncertainty_score":0.9997975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04318400353052269,"score_gpt":0.3782970460458757,"score_spread":0.335113042515353,"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."}}