{"id":"W4404071195","doi":"10.26434/chemrxiv-2024-zmq13","title":"MOSAEC-DB: A comprehensive database of experimental metal-organic frameworks with verified chemical accuracy suitable for molecular simulations","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Metal; Database; Materials science; Data mining; 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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004038397,0.0005519619,0.0008388228,0.0001308762,0.000120532,0.0003106847,0.001137806,0.0005463195,0.001441092],"category_scores_gemma":[0.0007007811,0.000485905,0.0001868657,0.0002990735,0.0004290302,0.0001741136,0.002126493,0.001010229,0.00007702798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001266922,"about_ca_system_score_gemma":0.0003800298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007535778,"about_ca_topic_score_gemma":0.000001854938,"domain_scores_codex":[0.9967486,0.0001127534,0.000666248,0.001296493,0.0006080123,0.0005678894],"domain_scores_gemma":[0.9970982,0.0005775999,0.0004832547,0.001358816,0.0003117356,0.0001703604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001288773,0.0001460845,0.000008940375,0.0008617233,0.00005853138,0.00001584719,0.0004298526,0.01106723,0.9861581,0.0009072936,0.0002071628,0.00001041359],"study_design_scores_gemma":[0.0004502317,0.0000772962,0.000009049479,0.0005205706,0.000169951,0.00001127395,0.0001129266,0.0220953,0.9740312,0.001802853,0.0002022574,0.0005170795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815936,0.001093264,0.01432572,0.0001778167,0.000951603,0.001183156,0.0003136302,0.0002347951,0.0001264079],"genre_scores_gemma":[0.9276524,0.000005899964,0.07126741,0.0001294521,0.0001509016,0.000242304,0.000376975,0.0001050074,0.00006966716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05694169,"threshold_uncertainty_score":0.9997593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02337411544364729,"score_gpt":0.3152555743704559,"score_spread":0.2918814589268086,"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."}}