{"id":"W2986561443","doi":"10.1039/c9cy02070e","title":"Predicting aggregation energy for single atom bimetallic catalysts on clean and O* adsorbed surfaces through machine learning models","year":2019,"lang":"en","type":"article","venue":"Catalysis Science & Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Toronto Public Health","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Bimetallic strip; Adsorption; Catalysis; Atom (system on chip); Stability (learning theory); Energy (signal processing); Chemistry; Materials science; Chemical engineering; Computer science; Physical chemistry; Machine learning; Physics; Engineering; Organic chemistry; Embedded system","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":[0.00206778,0.0003584637,0.0005607465,0.0009279512,0.0009082249,0.0003804712,0.001439729,0.0002158233,0.00006969532],"category_scores_gemma":[0.0008025936,0.0003162008,0.00007981335,0.002534485,0.001638212,0.001473214,0.0006002564,0.0002525589,0.00009517592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001865681,"about_ca_system_score_gemma":0.0001336495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005371415,"about_ca_topic_score_gemma":0.00009816905,"domain_scores_codex":[0.9961283,0.0001071644,0.000555892,0.001561697,0.0007407498,0.0009061627],"domain_scores_gemma":[0.9979107,0.0002517487,0.0005555009,0.0008996152,0.0002595995,0.0001227757],"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":[0.00002963687,0.00005230815,0.004468672,0.0000294293,0.000007249392,0.000001928105,0.0003666589,0.03658509,0.944332,0.01151079,0.000004567786,0.002611644],"study_design_scores_gemma":[0.0003581358,0.0004219669,0.0001008468,0.00005816001,0.0000361483,0.00003944534,0.0003258796,0.2192999,0.7730275,0.005218969,0.0007629147,0.0003501097],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841757,0.0003039048,0.01279076,0.0004704498,0.0004497347,0.0003757323,0.00001901353,0.000628483,0.0007861755],"genre_scores_gemma":[0.9899963,0.00003539311,0.009367482,0.00009991921,0.00003875186,0.00006692865,0.00003613072,0.00003827439,0.0003207813],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1827148,"threshold_uncertainty_score":0.999929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01741536234932478,"score_gpt":0.2469497301445804,"score_spread":0.2295343677952556,"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."}}