{"id":"W4289172108","doi":"10.26434/chemrxiv-2022-mvr06","title":"ARC-MOF: A Diverse Database of Metal-Organic Frameworks with DFT-Derived Partial Atomic Charges and Descriptors for Machine Learning","year":2022,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Mitacs; Natural Sciences and Engineering Research Council of Canada; Total; Compute Canada; University of Ottawa; U.S. Department of Energy","keywords":"Metal-organic framework; Arc (geometry); Key (lock); Database; Porosity; Materials science; Computer science; Ab initio; Nanotechnology; Chemistry; Mechanical engineering","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","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004018284,0.0005648977,0.0009141312,0.000103812,0.0003461383,0.0000809726,0.0006682442,0.0006564666,0.007818783],"category_scores_gemma":[0.0005095445,0.0005273225,0.0002627285,0.0001969852,0.0002586686,0.00008594163,0.001244764,0.002397768,0.000007157913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009977083,"about_ca_system_score_gemma":0.0001655168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007364989,"about_ca_topic_score_gemma":0.00001217852,"domain_scores_codex":[0.9974341,0.00005686577,0.000596165,0.001085293,0.0003633633,0.0004641811],"domain_scores_gemma":[0.9973257,0.0004252556,0.0007424005,0.001186204,0.0001053244,0.0002151728],"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":[0.000244511,0.000372027,0.004168876,0.001833682,0.0009151655,0.000008142022,0.0009050128,0.00009771102,0.9884411,0.001004165,0.0002858868,0.001723701],"study_design_scores_gemma":[0.001140958,0.00005867002,0.0001650138,0.0006442235,0.00127057,0.0000150778,0.001325513,0.004992095,0.9776582,0.0008840041,0.01081865,0.001027039],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.98708,0.002428127,0.008684613,0.0002937363,0.0001571943,0.0005614251,0.0003648221,0.0001694043,0.0002606317],"genre_scores_gemma":[0.9882914,0.0009152362,0.007941446,0.00006273408,0.0002394776,0.0007411743,0.001077262,0.0001568029,0.0005744334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01078294,"threshold_uncertainty_score":0.9999037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02549871955158492,"score_gpt":0.2498518255454263,"score_spread":0.2243531059938414,"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."}}