{"id":"W2910175903","doi":"10.1021/acs.jpcc.8b10644","title":"Robust Machine Learning Models for Predicting High CO<sub>2</sub> Working Capacity and CO<sub>2</sub>/H<sub>2</sub> Selectivity of Gas Adsorption in Metal Organic Frameworks for Precombustion Carbon Capture","year":2019,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry C","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":158,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Quantitative structure–activity relationship; Metal-organic framework; Molecular descriptor; Test set; Computer science; Network topology; Machine learning; Normalization (sociology); Adsorption; Artificial intelligence; Data mining; Chemistry; Organic chemistry","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"],"consensus_categories":[],"category_scores_codex":[0.001312936,0.0005335247,0.001062889,0.00007281176,0.0002144906,0.00007524882,0.0004525087,0.0007672543,0.00001624789],"category_scores_gemma":[0.0006853958,0.0004316235,0.000396043,0.0003884975,0.0001694828,0.0002814724,0.0001008779,0.002910554,0.000001299226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003051911,"about_ca_system_score_gemma":0.0001389538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001793893,"about_ca_topic_score_gemma":0.00001463106,"domain_scores_codex":[0.9971277,0.0001537124,0.0009758672,0.0005476141,0.0005962803,0.0005988909],"domain_scores_gemma":[0.9956368,0.001769832,0.00154999,0.0004832645,0.0003535174,0.0002065685],"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":[0.0003407472,0.0004028348,0.0005925262,0.0006341307,0.0002420644,6.767651e-7,0.0005601583,0.03242343,0.961929,0.00004147153,0.00001743224,0.002815478],"study_design_scores_gemma":[0.001001221,0.00008374195,0.0001192652,0.0006414796,0.0004371135,0.00003704313,0.0002355644,0.1946243,0.8004109,0.002064532,0.000005684143,0.0003391487],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854351,0.0002429162,0.01336918,0.0001799289,0.00006489733,0.0004936367,0.0000773619,0.00005533616,0.00008168293],"genre_scores_gemma":[0.9984159,0.0001723454,0.0003782361,0.00001747865,0.000761436,0.00005980862,0.00006965603,0.0001142304,0.0000109155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1622008,"threshold_uncertainty_score":0.9998136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01745244417982451,"score_gpt":0.2195081446109794,"score_spread":0.2020557004311549,"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."}}