{"id":"W4412025314","doi":"10.1016/j.apcata.2025.120434","title":"Machine learning for catalyst optimization: Outlier detection and material innovation","year":2025,"lang":"en","type":"article","venue":"Applied Catalysis A General","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Chemistry; Catalysis; Heterogeneous catalysis; Biochemical engineering; Chemical engineering; Process engineering; Organic chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0009959926,0.0002186598,0.000310457,0.0003297963,0.0005451204,0.0003691405,0.0002456089,0.0001072705,0.0002471748],"category_scores_gemma":[0.000166605,0.0002078825,0.00003911743,0.0008094761,0.0001188726,0.0001838304,0.000175445,0.00009887409,0.00002149988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007074017,"about_ca_system_score_gemma":0.00004718864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002166031,"about_ca_topic_score_gemma":0.00003392981,"domain_scores_codex":[0.998302,0.00006827863,0.0004851529,0.0006121248,0.0002158082,0.0003166173],"domain_scores_gemma":[0.9992245,0.00005564287,0.000242805,0.0002956743,0.0001395931,0.00004180038],"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":[0.00009797428,0.00001839391,0.0001422234,0.00004572627,0.00001401548,2.949901e-7,0.0001023463,0.1232842,0.8698864,0.003091812,0.00005013514,0.003266496],"study_design_scores_gemma":[0.00075333,0.00005210735,0.0004590606,0.00000992582,0.0001042772,0.000005494454,0.00003437744,0.2036427,0.7899931,0.0009289472,0.003690284,0.0003264358],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6566067,0.00003411194,0.3408485,0.0001817693,0.0006766111,0.0004401316,0.00002735844,0.0001916808,0.000993151],"genre_scores_gemma":[0.9717079,0.000007541244,0.02590207,0.0002218813,0.0002232947,0.0002814214,0.0004467842,0.00002434364,0.001184706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3151013,"threshold_uncertainty_score":0.8477201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007380233559850604,"score_gpt":0.243052673652795,"score_spread":0.2356724400929444,"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."}}