{"id":"W3024781884","doi":"10.1016/j.matt.2020.04.016","title":"Crystal Site Feature Embedding Enables Exploration of Large Chemical Spaces","year":2020,"lang":"en","type":"article","venue":"Matter","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University; National Research Council Canada; Vector Institute; University of Ottawa; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Toronto; Samsung Advanced Institute of Technology; Samsung; Government of Ontario; Canada Foundation for Innovation; Compute Canada; Ontario Research Foundation; Ontario Centres of Excellence","keywords":"Crystal (programming language); Embedding; Atom (system on chip); Autoencoder; Materials science; Crystal structure; Band gap; Doping; Density functional theory; Representation (politics); Feature (linguistics); Computer science; Physics; Chemistry; Artificial neural network; Artificial intelligence; Computational chemistry; Crystallography; Optoelectronics","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":[0.0002097605,0.0004438053,0.0005579702,0.0005198588,0.0003073276,0.0008542406,0.0006327927,0.0007743568,0.003273983],"category_scores_gemma":[0.001196933,0.0002303775,0.0004178932,0.000703854,0.0005062674,0.00154378,0.001175627,0.0009954002,0.0005189088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002489604,"about_ca_system_score_gemma":0.0003239676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001171357,"about_ca_topic_score_gemma":0.002471092,"domain_scores_codex":[0.9999077,0.00002550899,0.000003153791,0.00002381121,0.00002917051,0.00001063624],"domain_scores_gemma":[0.9995284,0.0002687543,0.00003608473,0.0000953832,0.00004047404,0.00003083875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000558656,0.0005027748,0.003758088,0.0005433648,0.0001262303,0.0004407081,0.0001898,0.5395585,0.05637956,0.1119002,0.01917856,0.2668635],"study_design_scores_gemma":[0.00001041024,0.00001866896,0.0001453739,0.000003992433,0.000003987745,0.00002227775,0.00001052011,0.9794235,0.002154145,0.01723921,0.0009627864,0.000005059544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3911541,0.0007550286,0.5881496,0.0008168868,0.000126199,0.00005437642,0.001365429,0.003745172,0.0138331],"genre_scores_gemma":[0.9231081,0.0002232987,0.07324859,0.00009986613,0.00003556828,0.00004441988,0.0007501777,0.0002310581,0.00225899],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003273983,"threshold_uncertainty_score":0.01095259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01519668677294133,"score_gpt":0.2696332585937563,"score_spread":0.254436571820815,"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."}}