{"id":"W4386037082","doi":"10.1039/d3mh00788j","title":"Machine learning-assisted optimization of multi-metal hydroxide electrocatalysts for overall water splitting","year":2023,"lang":"en","type":"article","venue":"Materials Horizons","topic":"Electrocatalysts for Energy Conversion","field":"Energy","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Agency for Science, Technology and Research","keywords":"Workflow; Water splitting; Hydroxide; Materials science; Metal; Metal hydroxide; Nanotechnology; Computer science; Chemical engineering; Chemistry; Catalysis; Engineering; Metallurgy; Photocatalysis","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":[0.000761622,0.0002987432,0.0005104452,0.0003363557,0.0002276694,0.0000517365,0.0002744647,0.0001858366,0.0002414055],"category_scores_gemma":[0.0002417426,0.0002530497,0.0001743813,0.0003376128,0.00004515753,0.0002111418,0.0001462018,0.0001061387,0.0001339377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001276448,"about_ca_system_score_gemma":0.00003929077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001072618,"about_ca_topic_score_gemma":0.0001326471,"domain_scores_codex":[0.9977446,0.0001545843,0.0006385943,0.0004628931,0.0003041041,0.0006951836],"domain_scores_gemma":[0.9990507,0.0001016701,0.0002387455,0.0003502882,0.0001743801,0.00008414993],"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":[0.0001670221,0.00005989988,0.00003014205,0.0001030445,0.0001405841,0.000005593277,0.0001144747,0.03871405,0.9589782,0.001112154,0.00006658831,0.0005082585],"study_design_scores_gemma":[0.001051923,0.0003235458,0.00005705579,0.00002985975,0.0001076297,0.000009708071,0.00001840554,0.03116123,0.9636486,0.0001382351,0.003162037,0.0002918162],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926152,0.00004206071,0.005331629,0.000143803,0.0005062293,0.0003591791,0.00002924925,0.0006389316,0.0003336937],"genre_scores_gemma":[0.9905095,0.00004365989,0.002556634,0.0000209612,0.0001583065,0.0001049074,0.003838093,0.0001208452,0.002647122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007552818,"threshold_uncertainty_score":0.9999922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01443315736233897,"score_gpt":0.2387203535305613,"score_spread":0.2242871961682223,"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."}}