{"id":"W3025465415","doi":"10.1364/osac.413394","title":"Successive training of a generative adversarial network for the design of an optical cloak","year":2020,"lang":"en","type":"preprint","venue":"OSA Continuum","topic":"Metamaterials and Metasurfaces Applications","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; European Research Council","keywords":"Cloak; Cloaking; Shell (structure); Generative grammar; Generative adversarial network; Convolution (computer science); Computer science; Algorithm; Artificial intelligence; Metamaterial; Deep learning; Engineering; Optics; Mechanical engineering; Physics; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001765144,0.000251711,0.000858144,0.00002165444,0.0001401595,0.00009476432,0.0007694617,0.0002037354,0.0001921831],"category_scores_gemma":[0.0004614516,0.0001783036,0.0001835263,0.0000903476,0.0002420974,0.00006863169,0.0003151277,0.0001595287,0.000005598613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001436895,"about_ca_system_score_gemma":0.0003389486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009102913,"about_ca_topic_score_gemma":0.00004706825,"domain_scores_codex":[0.9978101,0.0003614399,0.0007507219,0.0005161275,0.0002586253,0.0003029597],"domain_scores_gemma":[0.9971612,0.0009588647,0.0009034157,0.0005804803,0.0002972608,0.00009876036],"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":[0.0003067852,0.00003731361,0.000001819882,0.00008550035,0.000084795,7.865318e-7,0.001425059,0.006509525,0.9829162,0.006985326,0.0008667033,0.0007801887],"study_design_scores_gemma":[0.0006647371,0.000200369,0.00008964429,0.00008656194,0.0004638668,0.000001024073,0.0003363051,0.004877324,0.9836239,0.007524948,0.001884667,0.0002466917],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3766858,0.0003288657,0.6167154,0.0006650655,0.002128453,0.002455751,0.0008280384,0.00003943374,0.0001532295],"genre_scores_gemma":[0.7314942,0.00003490629,0.2663502,0.00007781111,0.001277592,0.0005745742,0.000104222,0.00003287071,0.00005363828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3548084,"threshold_uncertainty_score":0.7271011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.104190141214418,"score_gpt":0.3161933082928063,"score_spread":0.2120031670783882,"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."}}