{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008123778,0.002024136,0.00216034,0.003119034,0.001155744,0.001183006,0.004379959,0.00158584,0.01232309],"category_scores_gemma":[0.002560007,0.0004820305,0.001603459,0.003902745,0.0003017373,0.001250866,0.00125058,0.001434213,0.003671764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001192723,"about_ca_system_score_gemma":0.001792196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006397692,"about_ca_topic_score_gemma":0.01264145,"domain_scores_codex":[0.9993744,0.00008593489,0.00004259278,0.00009333412,0.0003277778,0.00007588004],"domain_scores_gemma":[0.9994507,0.0002331824,0.00004525152,0.0001063307,0.0001266102,0.00003784139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001154391,0.0007123304,0.01412467,0.01273034,0.00158768,0.001228032,0.0003706565,0.2302202,0.0299341,0.0520216,0.3886873,0.2672287],"study_design_scores_gemma":[0.0007560508,0.0005576144,0.006330734,0.0008514016,0.0003430718,0.0008968762,0.0002604646,0.4052813,0.02567066,0.02654906,0.5321809,0.0003219307],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2674752,0.03041037,0.1081465,0.001051762,0.0003722731,0.0006593672,0.501371,0.05466511,0.03584837],"genre_scores_gemma":[0.251891,0.01008484,0.1344997,0.0004202759,0.0001114086,0.001572768,0.5925946,0.005109604,0.003715891],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01232309,"threshold_uncertainty_score":0.04122484,"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."}}