{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005119232,0.0006812591,0.001010444,0.0006776149,0.000109677,0.0008725239,0.00288571,0.0002398513,0.0008067884],"category_scores_gemma":[0.001231417,0.0006431008,0.0001049835,0.0007815689,0.0002284666,0.0007576338,0.005298835,0.001117701,0.0001618833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002775494,"about_ca_system_score_gemma":0.0005379717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003103405,"about_ca_topic_score_gemma":0.002543842,"domain_scores_codex":[0.9938378,0.000694904,0.001306594,0.00250225,0.0008647227,0.0007937804],"domain_scores_gemma":[0.996076,0.0005764397,0.0006543854,0.00245247,0.00009837625,0.0001422994],"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":[0.00006300261,0.00005935253,0.002155065,0.000635037,0.00001418001,0.0000596127,0.0004224883,0.1062551,0.8900656,0.00003172059,0.00004923124,0.0001895776],"study_design_scores_gemma":[0.0005470304,0.000008193679,0.003742555,0.0006929368,0.00005518496,0.000007112381,0.00005068419,0.5568584,0.4362878,0.001120901,0.00004431041,0.0005849939],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9505883,0.0001588725,0.04473337,0.0003567272,0.002612976,0.0008929496,0.0003957037,0.000238675,0.00002240647],"genre_scores_gemma":[0.8155771,0.000004235565,0.1820733,0.00006342649,0.0001470574,0.0001295819,0.001826737,0.00008204698,0.00009652345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4537778,"threshold_uncertainty_score":0.999602,"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."}}