{"id":"W3126624604","doi":"10.1371/journal.pone.0287736","title":"Using deep LSD to build operators in GANs latent space with meaning in real space","year":2023,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"TRIUMF","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"MNIST database; Autoencoder; Orthonormal basis; Latent variable; Space (punctuation); Eigenvalues and eigenvectors; Dimensionality reduction; Probabilistic latent semantic analysis; Artificial intelligence; Latent class model; Computer science; Pattern recognition (psychology); Representation (politics); Mathematics; Deep learning; Machine learning; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003041656,0.0001427785,0.0002394305,0.0002478405,0.00007360632,0.0001211365,0.0003259822,0.00004289194,0.000006856187],"category_scores_gemma":[0.00005611025,0.0001286351,0.00001994308,0.001631809,0.00001854426,0.0003166716,0.0002233094,0.0001414097,0.00003953371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001089405,"about_ca_system_score_gemma":0.00005296175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009328102,"about_ca_topic_score_gemma":0.002757019,"domain_scores_codex":[0.9986273,0.0000998183,0.0001665292,0.0004065473,0.0002978621,0.0004019493],"domain_scores_gemma":[0.9994338,0.00006051777,0.00003768421,0.0003079669,0.00005724551,0.0001027525],"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":[0.00006013667,0.0005967034,0.09240614,0.00004608828,0.0001154022,0.0003895775,0.01173296,0.7272967,0.1606638,0.004909316,0.0001500941,0.001633058],"study_design_scores_gemma":[0.0004408698,0.000130288,0.01326432,0.000398487,0.00001474996,0.000001560076,0.0002495499,0.9396889,0.04532544,0.0001298428,0.00003326329,0.0003227698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8898555,0.00002232542,0.106809,0.002094125,0.0000603956,0.000292608,9.681013e-7,0.0001016185,0.0007634535],"genre_scores_gemma":[0.8544208,0.00002829668,0.1452158,0.0001139827,0.00006870094,0.00001371079,8.372276e-7,0.00001653407,0.0001213163],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2123922,"threshold_uncertainty_score":0.5245587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06443923413368993,"score_gpt":0.2504712104728279,"score_spread":0.186031976339138,"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."}}