{"id":"W2931367569","doi":"10.1038/s41598-019-56773-5","title":"Molecular Geometry Prediction using a Deep Generative Graph Neural Network","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":128,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Samsung; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation; Tencent; Canadian Institute for Advanced Research; Nvidia","keywords":"Force field (fiction); Artificial neural network; Set (abstract data type); Function (biology); Graph; Generative grammar; Field (mathematics); Energy minimization","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003750507,0.0002329841,0.0002902603,0.0002203423,0.000584949,0.001014018,0.0003674787,0.00009296822,0.001772107],"category_scores_gemma":[0.0002196962,0.0002064238,0.0001063835,0.00116913,0.0003625379,0.0005880517,0.0002588893,0.000156896,0.0002309928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007989938,"about_ca_system_score_gemma":0.0001206787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005984397,"about_ca_topic_score_gemma":0.000004678538,"domain_scores_codex":[0.9960173,0.0002700305,0.0006455578,0.001322866,0.001045467,0.0006987171],"domain_scores_gemma":[0.9979013,0.00003701611,0.0005337039,0.001154968,0.0002070843,0.0001659934],"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":[0.000004474869,0.00001288582,0.009855899,0.00001174563,0.00000242834,0.00008836965,0.00008938097,0.3718517,0.6175933,0.0001276583,0.0003142155,0.0000479326],"study_design_scores_gemma":[0.0002743849,0.0001393612,0.006637109,0.00008179689,0.00004986485,0.001156995,0.00009652608,0.4543255,0.5131921,0.02043645,0.00286583,0.0007441068],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9556957,0.0001459548,0.0121429,0.00003918961,0.03068609,0.0004346732,0.000003199609,0.0002012269,0.0006510926],"genre_scores_gemma":[0.9804277,5.831916e-7,0.01869117,0.00009601114,0.0002363637,0.0000139931,0.00002412256,0.00002622055,0.0004838186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1044013,"threshold_uncertainty_score":0.9991404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00993590855811866,"score_gpt":0.2478214441956838,"score_spread":0.2378855356375651,"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."}}