{"id":"W4413384220","doi":"10.1016/j.apmate.2025.100333","title":"Machine learning application in thermal CO2 hydrogenation: catalyst design, process optimization, and mechanism insights","year":2025,"lang":"en","type":"article","venue":"Advanced Powder Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; Western University","funders":"Office of Energy Research and Development; Natural Resources Canada; Western University; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Gaussian","keywords":"Mechanism (biology); Process (computing); Catalysis; Process engineering; Computer science; Biochemical engineering; Chemical engineering; Materials science; Chemistry; Engineering; Organic chemistry; Physics","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":[0.001054449,0.0002811598,0.0003958499,0.000200173,0.0003184646,0.0002562104,0.0003967863,0.0001187568,0.0004430575],"category_scores_gemma":[0.0002951925,0.0002578443,0.00001741467,0.0004761703,0.0001205126,0.0006603107,0.0001589796,0.0001143161,0.00005122802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006998866,"about_ca_system_score_gemma":0.0000835155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000108551,"about_ca_topic_score_gemma":0.00001737049,"domain_scores_codex":[0.9975861,0.00045911,0.0006102853,0.0006948043,0.000282772,0.000366924],"domain_scores_gemma":[0.9990152,0.0001377505,0.0003184976,0.0003253462,0.0001375654,0.00006562366],"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":[0.0000517621,0.00002493104,0.0001838704,0.00006918807,0.000002756288,0.000002403967,0.000296833,0.3131424,0.6844957,0.001613037,0.000001845119,0.0001152177],"study_design_scores_gemma":[0.0006798356,0.00004731575,0.0003056167,0.00008406831,0.00001398862,0.000007461518,0.00007438102,0.03164703,0.9622778,0.004414963,0.0001643103,0.0002832781],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8888991,0.000303642,0.1086516,0.0002793177,0.0004871071,0.0008284574,0.00001311258,0.0002310446,0.0003065983],"genre_scores_gemma":[0.9801658,0.00005506306,0.01890572,0.0002051772,0.00004236128,0.0002989517,0.00006770922,0.00003054524,0.0002286253],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2814954,"threshold_uncertainty_score":0.9999874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006361348529673476,"score_gpt":0.253398456529444,"score_spread":0.2470371079997705,"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."}}