{"id":"W4413357328","doi":"10.26434/chemrxiv-2025-c6rxp-v3","title":"Distilling System Complexity to Enable Unbiased and Predictive Computational Reaction Investigations","year":2025,"lang":"en","type":"article","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Université de Sherbrooke; Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Hydro-Québec; Centre in Green Chemistry and Catalysis","keywords":"Computer science; Computational complexity theory; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0007549239,0.0001065332,0.0001540469,0.00009024244,0.0003461985,0.0001566758,0.0001690404,0.00003962526,0.00005218405],"category_scores_gemma":[0.0005305167,0.0001028555,0.00001600898,0.0003033967,0.0002320568,0.0001628305,0.0001071428,0.00007264858,0.00007398132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001184872,"about_ca_system_score_gemma":0.00007459932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001340519,"about_ca_topic_score_gemma":0.000007137731,"domain_scores_codex":[0.9989107,0.0001160797,0.0002296317,0.0003661581,0.0001888961,0.0001885581],"domain_scores_gemma":[0.9993157,0.0001983519,0.0000871778,0.0001806322,0.0001109484,0.0001071405],"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":[0.00002908992,0.0000242146,0.002386089,0.0001817591,0.000005189625,0.000001685583,0.0003667005,0.05147103,0.9149479,0.02978144,0.0007265318,0.00007842112],"study_design_scores_gemma":[0.0006097872,0.00008094578,0.0670146,0.0005936602,0.00005065374,0.00001777158,0.0005627528,0.5644795,0.3413947,0.02156571,0.003199077,0.000430879],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8785737,0.00001432071,0.1168496,0.0006862012,0.0004672198,0.0002339748,0.00001573187,0.0001974064,0.002961909],"genre_scores_gemma":[0.9679627,4.194313e-7,0.03152021,0.0002122762,0.00005278441,0.00003727993,0.00002712288,0.000006188108,0.0001809969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5735531,"threshold_uncertainty_score":0.4194325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02452473904853978,"score_gpt":0.2743451841579776,"score_spread":0.2498204451094378,"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."}}