{"id":"W4377022920","doi":"10.1021/acs.chemmater.3c00788","title":"DigiMOF: A Database of Metal–Organic Framework Synthesis Information Generated via Text Mining","year":2023,"lang":"en","type":"article","venue":"Chemistry of Materials","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council; Cambridge Crystallographic Data Centre; Lembaga Pengelola Dana Pendidikan; Royal Academy of Engineering","keywords":"Chemical space; Computer science; Limiting; Very large database; Database; Metal-organic framework; Chemical database; Data mining; Chemistry; Drug discovery; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004319867,0.0002562967,0.0005923381,0.00005541091,0.00008111497,0.00005507472,0.0004811326,0.0003451516,0.01724651],"category_scores_gemma":[0.001648745,0.0002523031,0.00010843,0.0004699062,0.0001188538,0.0002200958,0.0001885132,0.0001183919,0.0001813952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003086618,"about_ca_system_score_gemma":0.00006961966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001495712,"about_ca_topic_score_gemma":1.80229e-7,"domain_scores_codex":[0.9980943,0.00002433995,0.0009901852,0.000274405,0.0003275181,0.0002892744],"domain_scores_gemma":[0.9976606,0.0004796785,0.000706256,0.0009159652,0.0001411231,0.00009631182],"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":[0.00002339529,0.00005823071,0.00002360095,0.00133955,0.0001128007,0.000001065626,0.0001285048,0.000009095966,0.9962851,0.00006460214,0.0007165382,0.001237498],"study_design_scores_gemma":[0.0001176132,0.000002818349,0.00004077529,0.0004647824,0.0001227868,0.000006162135,0.0003117184,0.000083733,0.9971958,0.0002031431,0.001222602,0.0002280229],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958969,0.00008121365,0.0009215942,0.0001090352,0.00008380961,0.00008854687,0.0008031373,0.0001603058,0.001855455],"genre_scores_gemma":[0.9956796,0.000140569,0.002945501,0.00001957321,0.0001624515,0.0001051162,0.0005994293,0.0000411833,0.0003066205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01706512,"threshold_uncertainty_score":0.9999929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01807835215305226,"score_gpt":0.2422001877428258,"score_spread":0.2241218355897735,"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."}}