{"id":"W4403305310","doi":"10.26434/chemrxiv-2024-ftsv3","title":"Alarming structural error rates in MOF databases used in data driven workflows identified via a novel metal oxidation state-based method","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Database; Computer science; Oxidation state; State (computer science); Data mining; Metal; Materials science; Algorithm; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01264954,0.001318924,0.001100646,0.004358805,0.001499504,0.003537681,0.003639801,0.002379924,0.001077138],"category_scores_gemma":[0.05433969,0.0007352217,0.00121571,0.003172654,0.001020924,0.002645704,0.001914559,0.001534165,0.0009922624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001453037,"about_ca_system_score_gemma":0.003514932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006264738,"about_ca_topic_score_gemma":0.007543349,"domain_scores_codex":[0.9883003,0.001990872,0.001907124,0.003318907,0.003925432,0.0005573184],"domain_scores_gemma":[0.966773,0.01562077,0.003294682,0.007648502,0.005925636,0.0007373762],"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":[0.004378197,0.001577557,0.2898985,0.003258504,0.00159813,0.003100262,0.002134602,0.1423497,0.09212091,0.01633664,0.05006268,0.3931844],"study_design_scores_gemma":[0.0002238119,0.0004431392,0.02098322,0.0002218735,0.0001934208,0.00107141,0.0005717255,0.8502587,0.09990025,0.009478217,0.01648191,0.0001722977],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.727595,0.002486435,0.1889502,0.00143445,0.0003316544,0.0005905347,0.02039594,0.05537392,0.002841924],"genre_scores_gemma":[0.6181433,0.0004821115,0.3322813,0.0004070398,0.00004224997,0.0004977364,0.04592646,0.001473868,0.0007459964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9873505,"threshold_uncertainty_score":0.06689793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08879264022500052,"score_gpt":0.3877871288231015,"score_spread":0.298994488598101,"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."}}