{"id":"W4407033826","doi":"10.1039/d4sc07438f","title":"MOSAEC-DB: a comprehensive database of experimental metal–organic frameworks with verified chemical accuracy suitable for molecular simulations","year":2025,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Total; Natural Sciences and Engineering Research Council of Canada; Mitacs; Alliance de recherche numérique du Canada; University of Ottawa","keywords":"Computer science; Metal-organic framework; Chemical database; Database; Metal; Materials science; Data mining; Chemistry; Physical chemistry; Organic chemistry; Metallurgy","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":[0.001184357,0.001479534,0.001826186,0.002357616,0.0008826845,0.001271248,0.005013283,0.001494045,0.00975289],"category_scores_gemma":[0.003189442,0.0006543694,0.00121594,0.003304163,0.0003909238,0.001466298,0.001448131,0.00119692,0.00296621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000990657,"about_ca_system_score_gemma":0.002684843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006445812,"about_ca_topic_score_gemma":0.01095973,"domain_scores_codex":[0.9994177,0.00009639154,0.00005924617,0.0001337071,0.0002230154,0.00007003223],"domain_scores_gemma":[0.9992719,0.0002341166,0.00008023679,0.0002010782,0.0001464645,0.00006604436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002393082,0.001281566,0.01829551,0.01164073,0.001472402,0.001398335,0.0004292763,0.3161956,0.04236067,0.04717826,0.3876471,0.1697074],"study_design_scores_gemma":[0.001474843,0.0007116962,0.009682762,0.0004570701,0.0004367691,0.0009819437,0.0002961645,0.4058645,0.04056525,0.0250204,0.5142094,0.0002992421],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1987824,0.005757915,0.06933228,0.000616562,0.0002213283,0.0007104779,0.6765149,0.03097381,0.01709036],"genre_scores_gemma":[0.1802866,0.002744279,0.1020965,0.0001869376,0.00004869403,0.001331716,0.710077,0.001705623,0.001522579],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.00975289,"threshold_uncertainty_score":0.03262669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01376168457755506,"score_gpt":0.3154719573024795,"score_spread":0.3017102727249244,"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."}}