{"id":"W4233109831","doi":"10.26434/chemrxiv.12186681","title":"Inverse Design of Nanoporous Crystalline Reticular Materials with Deep Generative Models","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of Ottawa; University of Toronto","funders":"Basic Energy Sciences; Natural Sciences and Engineering Research Council of Canada; Quest High Performance Computing; Office of Science; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Compute Canada; École de technologie supérieure; Northwestern University; U.S. Department of Energy","keywords":"Reticular connective tissue; Nanoporous; Computer science; Autoencoder; Nanotechnology; Materials science; Artificial intelligence; Deep learning","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002014448,0.0004703563,0.0008603488,0.00003618336,0.00006620321,0.00006919364,0.0005817044,0.0006120411,0.002645817],"category_scores_gemma":[0.0001071685,0.0004044904,0.0001351387,0.0001290183,0.0001855496,0.00004932646,0.0003764116,0.0004649672,0.00002174773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007199057,"about_ca_system_score_gemma":0.0002025828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000234222,"about_ca_topic_score_gemma":0.000002048516,"domain_scores_codex":[0.9978911,0.00005819869,0.0006533345,0.0007954013,0.0003369057,0.0002650537],"domain_scores_gemma":[0.9977512,0.0001014982,0.0006422062,0.001141879,0.000202258,0.0001610003],"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":[0.00006301484,0.0001214558,0.000002912461,0.000653635,0.0003096672,0.00001659351,0.0004495006,0.0156408,0.9808165,0.001270967,0.0005559019,0.00009900424],"study_design_scores_gemma":[0.0002373613,0.00001593699,7.416047e-7,0.0003331808,0.0002726735,0.000005593508,0.0001261177,0.02655788,0.9604631,0.01129619,0.0002632702,0.00042795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2918641,0.0008389859,0.7023807,0.00111644,0.00008958326,0.0007879055,0.0001153515,0.0002331431,0.002573828],"genre_scores_gemma":[0.8926502,0.0003458823,0.1055672,0.0001192658,0.0002809297,0.0003289811,0.0002676896,0.0001153158,0.0003245303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.600786,"threshold_uncertainty_score":0.9998407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.040642738329056,"score_gpt":0.2364430074510832,"score_spread":0.1958002691220272,"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."}}