{"id":"W4410449345","doi":"10.1021/jacs.5c04914","title":"High Structural Error Rates in “Computation-Ready” MOF Databases Discovered by Checking Metal Oxidation States","year":2025,"lang":"en","type":"article","venue":"Journal of the American Chemical Society","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","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; University of Ottawa","keywords":"Chemistry; Computation; Database; Metal; Algorithm; Organic chemistry; Computer science","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007278468,0.001020585,0.001409592,0.002971783,0.001500345,0.001941947,0.0020736,0.001153143,0.001445743],"category_scores_gemma":[0.0302615,0.0006914812,0.001064998,0.003716604,0.0009427323,0.002172236,0.001226116,0.0009588594,0.0006637305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001300609,"about_ca_system_score_gemma":0.001683441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004795479,"about_ca_topic_score_gemma":0.0094442,"domain_scores_codex":[0.992547,0.001286537,0.0009197447,0.001458065,0.00343412,0.0003545973],"domain_scores_gemma":[0.9773164,0.01344186,0.002279885,0.003849017,0.002857526,0.0002552653],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005487429,0.0008737061,0.2735455,0.005350593,0.002198173,0.003709439,0.002080614,0.1321713,0.142464,0.02098732,0.05276307,0.3583689],"study_design_scores_gemma":[0.0005150755,0.00137121,0.08067269,0.0007903712,0.001256091,0.004657697,0.001663711,0.4986474,0.312649,0.0317843,0.06557444,0.0004180811],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9483014,0.003559625,0.02691279,0.0006592756,0.0001247531,0.00009798303,0.009381359,0.007549421,0.00341333],"genre_scores_gemma":[0.9045431,0.001144423,0.05564009,0.0004119825,0.00003568481,0.0001000738,0.03652112,0.0009458858,0.0006577023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9927216,"threshold_uncertainty_score":0.03849268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147413620457407,"score_gpt":0.2963211960643527,"score_spread":0.281579834018612,"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."}}