{"id":"W4413289814","doi":"10.26434/chemrxiv-2025-dl4sb","title":"Capturing Electron Correlation with Machine Learning through a Data-Driven CASPT2 Framework","year":2025,"lang":"en","type":"article","venue":"ChemRxiv","topic":"Electron and X-Ray Spectroscopy Techniques","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Division of Chemistry; National Science Foundation","keywords":"Computer science; Correlation; Electron; Artificial intelligence; Machine learning; Pattern recognition (psychology); Physics; Mathematics; Geometry; Nuclear physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002231416,0.0007294946,0.0008735158,0.0007787722,0.0006370911,0.001036159,0.002548425,0.001085786,0.001277345],"category_scores_gemma":[0.004549021,0.000307062,0.0006350763,0.0007766237,0.000890799,0.001898517,0.001172533,0.001830266,0.0002653418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006902178,"about_ca_system_score_gemma":0.001512044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001337372,"about_ca_topic_score_gemma":0.001511578,"domain_scores_codex":[0.9992424,0.0003365868,0.00002558269,0.00007909121,0.0002761018,0.00004024207],"domain_scores_gemma":[0.9978138,0.001177257,0.0001571758,0.0004612319,0.0003052183,0.0000853376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008456687,0.0001830498,0.001369146,0.0001427383,0.0001070648,0.0001219899,0.00007304449,0.8483313,0.005629894,0.0898792,0.00222836,0.05184961],"study_design_scores_gemma":[0.000004989422,0.00001056623,0.00004969038,0.000001761492,0.000001866414,0.000006265673,0.00000334037,0.9881992,0.0007568985,0.01074719,0.0002139642,0.000004223376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04013618,0.0001239391,0.9556072,0.0002906118,0.00003622661,0.00008499427,0.0002308908,0.001015756,0.002474124],"genre_scores_gemma":[0.5431668,0.0001590911,0.4542452,0.0002079428,0.00005876707,0.0003400845,0.0005741162,0.0002050173,0.001042972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002548425,"threshold_uncertainty_score":0.011801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01531066456444434,"score_gpt":0.2931409582012542,"score_spread":0.2778302936368098,"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."}}