{"id":"W7095002216","doi":"10.6084/m9.figshare.c.8109755.v1","title":"VNFlow: integration of variational autoencoders and normalizing flows for novel molecular design","year":2025,"lang":"","type":"other","venue":"Figshare","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"","keywords":"Generative grammar; Inverse; Key (lock); Range (aeronautics); Sampling (signal processing); Generative model; Training set; Inverse problem","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":[0.00144682,0.0008219104,0.0006593073,0.0005551378,0.0003134897,0.0007070667,0.0009527399,0.001059047,0.002825422],"category_scores_gemma":[0.002119564,0.000462358,0.0007004244,0.0003670226,0.0007722485,0.0007270777,0.001026999,0.001269657,0.0005384815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009497897,"about_ca_system_score_gemma":0.001120767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004312706,"about_ca_topic_score_gemma":0.005789489,"domain_scores_codex":[0.9997868,0.00007223272,0.000009649011,0.00004145437,0.00006884912,0.00002100028],"domain_scores_gemma":[0.9994389,0.0003535882,0.00004275409,0.00005468821,0.00007994686,0.00003003734],"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":[0.00002350349,0.00002978185,0.000265013,0.00003787944,0.00002806881,0.00002936838,0.0000183495,0.9432829,0.002778137,0.0141497,0.0008069949,0.03855034],"study_design_scores_gemma":[0.000001783404,0.0000059051,0.00001021162,0.000002293893,0.000001621039,0.000003092457,7.553282e-7,0.9972094,0.0005176932,0.001908243,0.0003374664,0.000001553009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01145162,0.0002346227,0.984543,0.0001714352,0.00006188812,0.0000465913,0.00007337254,0.001046583,0.002370795],"genre_scores_gemma":[0.3979928,0.0003163524,0.5951053,0.0003191789,0.00007035323,0.0002773209,0.0003621137,0.0005405485,0.005016093],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004312706,"threshold_uncertainty_score":0.009451926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0395505370752871,"score_gpt":0.291092438192949,"score_spread":0.2515419011176619,"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."}}