{"id":"W4405394547","doi":"10.1016/j.jcat.2024.115906","title":"Leveraging Machine learning and active motifs-based catalyst design for discovery of oxygen reduction electrocatalysts for hydrogen peroxide production","year":2024,"lang":"en","type":"article","venue":"Journal of Catalysis","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Institute for Information and Communications Technology Promotion; Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea; Korea Institute of Science and Technology Information; Ministry of Trade, Industry and Energy","keywords":"Chemistry; Hydrogen peroxide; Catalysis; Oxygen reduction; Combinatorial chemistry; Oxygen; Oxygen reduction reaction; Electrochemistry; Organic chemistry; Electrode","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":[],"consensus_categories":[],"category_scores_codex":[0.004029475,0.0002155871,0.0005481389,0.000480211,0.0002331853,0.0002611973,0.0002461339,0.00006600618,0.00001856297],"category_scores_gemma":[0.001335309,0.0001733984,0.0002571458,0.0004165351,0.0001294982,0.001116847,0.00004372459,0.0001883917,0.00000244195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001733322,"about_ca_system_score_gemma":0.0002554611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006062814,"about_ca_topic_score_gemma":0.000004479615,"domain_scores_codex":[0.9977056,0.0002326143,0.0008228255,0.0004679257,0.000475093,0.0002959836],"domain_scores_gemma":[0.998094,0.0003753537,0.0008775776,0.0002099225,0.0003675848,0.0000755361],"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":[0.0004131867,0.0000390405,0.00006109646,0.0003081145,0.00009161028,0.000003030671,0.0007056019,0.05857652,0.9384757,0.00001287535,0.00006435313,0.001248892],"study_design_scores_gemma":[0.0003041277,0.0003926057,0.00008683236,0.0001494108,0.0004001225,0.0001958121,0.0001998061,0.04877245,0.9487557,0.0003518046,0.0002262203,0.0001650759],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.751177,0.0006816091,0.246787,0.000499821,0.0004698869,0.0003322656,0.00002157565,0.00002778264,0.000002972307],"genre_scores_gemma":[0.976927,0.00003078842,0.0223218,0.000007551237,0.0003580622,0.00003493519,0.00004851524,0.00003666798,0.0002346643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.22575,"threshold_uncertainty_score":0.7070982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588216165559079,"score_gpt":0.273187923306187,"score_spread":0.2573057616505962,"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."}}