{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001518047,0.003517498,0.001627779,0.01939146,0.0007462957,0.002265237,0.003040412,0.002073881,0.01715677],"category_scores_gemma":[0.007579317,0.0008820225,0.001981542,0.01048283,0.0005362437,0.003097554,0.001910122,0.001377514,0.01005397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001426138,"about_ca_system_score_gemma":0.002707029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003746775,"about_ca_topic_score_gemma":0.006200378,"domain_scores_codex":[0.9987196,0.0001187697,0.0002769721,0.0004248378,0.0003638224,0.00009611636],"domain_scores_gemma":[0.9967632,0.001601478,0.0006239157,0.0004074279,0.0004067338,0.0001971853],"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":[0.001634533,0.0005426988,0.01412488,0.03140127,0.001033581,0.00460027,0.0009505324,0.0153385,0.05103148,0.01373886,0.5170857,0.3485177],"study_design_scores_gemma":[0.0007237437,0.0003941153,0.01881481,0.001466903,0.0005592637,0.002219673,0.0003889584,0.02695616,0.04494693,0.01201423,0.8912238,0.0002914289],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01172213,0.003096918,0.01515766,0.0002145873,0.00006632003,0.0003587119,0.9387457,0.02639398,0.004244105],"genre_scores_gemma":[0.01654769,0.001901645,0.04494838,0.0001428258,0.00003724754,0.0006481626,0.9334343,0.001365636,0.0009741274],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01939146,"threshold_uncertainty_score":0.05739516,"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."}}