{"id":"W7115579649","doi":"10.26434/chemrxiv-2025-tpfct","title":"Practical Data-Driven Interrogation of Reactivity in Acid-Catalyzed Carbonyl–Olefin Metathesis with Machine Learning and Large Language Models","year":2025,"lang":"","type":"article","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Research Corporation for Science Advancement","keywords":"Blueprint; Catalysis; Scheduling (production processes); Interpretability; Metathesis; Substrate (aquarium); Bayesian inference; Inference","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":[0.004366602,0.0004254045,0.0009104116,0.0003513786,0.0001805806,0.0002488391,0.0008274768,0.0002032023,0.0002627998],"category_scores_gemma":[0.0022817,0.0003735731,0.00004876121,0.000809906,0.0005230192,0.001471489,0.001365106,0.0006519535,0.00001330085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001458036,"about_ca_system_score_gemma":0.0004568322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001722683,"about_ca_topic_score_gemma":0.001095023,"domain_scores_codex":[0.995792,0.0009366195,0.0007896498,0.001309659,0.0005415935,0.000630477],"domain_scores_gemma":[0.9971417,0.0006080233,0.0008841507,0.001120013,0.0001168709,0.0001292167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005185574,0.0003846292,0.007865661,0.0005563587,0.00005098191,0.00004958039,0.003600628,0.001395622,0.9835314,0.001260622,0.000009252106,0.0007767108],"study_design_scores_gemma":[0.00135808,0.0001029049,0.001902248,0.0005208428,0.0001976133,0.00002202889,0.00146275,0.5878411,0.4059007,0.0001945762,0.000128941,0.0003682647],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9689909,0.0005127291,0.02795461,0.0007799414,0.0002071649,0.0004280951,0.00005589758,0.00006915599,0.001001573],"genre_scores_gemma":[0.9777116,0.0001061348,0.02176227,0.00004333678,0.0000265848,0.00002505762,0.00008150138,0.0000324773,0.0002110684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5864455,"threshold_uncertainty_score":0.9998716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02863788593630032,"score_gpt":0.3246500443258162,"score_spread":0.2960121583895159,"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."}}