{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001626072,0.001358937,0.001579678,0.001072614,0.0001628705,0.001207021,0.002125298,0.001318915,0.001955643],"category_scores_gemma":[0.003041206,0.0005437386,0.0008153846,0.001231731,0.0008034889,0.002572008,0.0009562643,0.00331347,0.001728993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006751016,"about_ca_system_score_gemma":0.001026395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001023335,"about_ca_topic_score_gemma":0.001471083,"domain_scores_codex":[0.9996922,0.00007887185,0.00002671642,0.00007446075,0.0001048614,0.00002295862],"domain_scores_gemma":[0.998558,0.001084815,0.00006397441,0.0000776671,0.0001877043,0.00002792264],"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":[0.00003089808,0.00006500428,0.000196293,0.008934004,0.0002468429,0.00006826255,0.0000223636,0.009123784,0.002009819,0.02560791,0.01971065,0.9339842],"study_design_scores_gemma":[0.00007873224,0.0001730111,0.000873498,0.005658532,0.0004701512,0.0006851191,0.00003863404,0.04458086,0.009001612,0.1260019,0.8123265,0.0001114815],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0007419109,0.9415777,0.05239178,0.00149247,0.000642815,0.00004574624,0.0001489614,0.0002721566,0.002686461],"genre_scores_gemma":[0.008113589,0.9476494,0.04066903,0.0008099294,0.0009117604,0.0000995189,0.0003657088,0.00007015209,0.001311046],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.002125298,"threshold_uncertainty_score":0.008599579,"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."}}