{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002441288,0.001589942,0.001207091,0.0009527525,0.001094711,0.001070264,0.002859556,0.001712351,0.00424647],"category_scores_gemma":[0.005808987,0.0003725459,0.001020948,0.001122112,0.0007327843,0.001461298,0.001551893,0.00153623,0.0007517572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001355336,"about_ca_system_score_gemma":0.001940387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01381784,"about_ca_topic_score_gemma":0.01425998,"domain_scores_codex":[0.9991629,0.0003493139,0.00004725764,0.00009233521,0.0002330001,0.0001151548],"domain_scores_gemma":[0.9983556,0.001005572,0.00007323137,0.0001946617,0.0002235275,0.0001474534],"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":[0.0005329798,0.0004765815,0.005928408,0.001132834,0.0003945983,0.0002352585,0.0001060797,0.9080375,0.004230909,0.01915456,0.01732729,0.042443],"study_design_scores_gemma":[0.000118692,0.00023908,0.0006445569,0.00006161715,0.00002601283,0.00003850721,0.00004287171,0.9848123,0.004281773,0.005041668,0.004663621,0.0000293794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8041025,0.01050736,0.09876329,0.00315536,0.0008594958,0.0005911125,0.01505912,0.02573566,0.04122618],"genre_scores_gemma":[0.8885907,0.00171367,0.08741529,0.0008959653,0.000127326,0.0005335567,0.01523567,0.002412098,0.003075711],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01381784,"threshold_uncertainty_score":0.02747482,"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."}}