{"id":"W4417213662","doi":"10.1038/s41524-025-01872-3","title":"MOFSimBench: evaluating universal machine learning interatomic potentials in metal-organic framework molecular modeling","year":2025,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Canada First Research Excellence Fund; University of Toronto","keywords":"Nanoporous; Benchmarking; Benchmark (surveying); Scalability; Modular design; Multiscale modeling; Key (lock); Molecular dynamics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00265714,0.0003753291,0.0006245621,0.000494822,0.0003404263,0.0005758095,0.0007353717,0.0001830957,0.00355806],"category_scores_gemma":[0.00131426,0.000386559,0.00007028283,0.0006411362,0.0000999188,0.0004189671,0.0005113442,0.0003324102,0.00025763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002329949,"about_ca_system_score_gemma":0.0002476022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004177802,"about_ca_topic_score_gemma":0.00001584925,"domain_scores_codex":[0.9955059,0.001303218,0.001051823,0.0008524665,0.0007148195,0.000571811],"domain_scores_gemma":[0.9985514,0.0004393417,0.0003534177,0.0003295444,0.000240754,0.00008549482],"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":[0.00004218793,0.00003494795,0.00008661964,0.00004237374,0.000008784019,0.00001248584,0.0002083669,0.4859878,0.5078614,0.005651243,0.000003020668,0.00006083238],"study_design_scores_gemma":[0.0007651363,0.00009641956,0.0003578379,0.0004109702,0.00003555141,0.00001205614,0.0001440267,0.7773839,0.1720421,0.04836053,0.00001285784,0.0003786149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7817683,0.00009374187,0.2160279,0.0002507801,0.001110045,0.0003267465,0.00002079635,0.0001926598,0.000208984],"genre_scores_gemma":[0.9472499,0.000003795896,0.05211303,0.0003207526,0.00006878575,0.00003291888,0.00007367629,0.0000400018,0.00009706633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3358192,"threshold_uncertainty_score":0.9998586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01444469657454001,"score_gpt":0.3039852451862552,"score_spread":0.2895405486117152,"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."}}