{"id":"W2967817162","doi":"10.48550/arxiv.1908.05324","title":"Dual Adversarial Inference for Text-to-Image Synthesis","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Inference; Computer science; Image (mathematics); Adversarial system; Dual (grammatical number); Style (visual arts); Artificial intelligence; Composition (language); Image synthesis; Space (punctuation); Quality (philosophy); Process (computing); Natural language processing; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000447218,0.0005589577,0.0006833107,0.0003543898,0.0002598763,0.0003757703,0.002376668,0.0004099908,0.00008038538],"category_scores_gemma":[0.0005509715,0.0006252622,0.0004761377,0.0005813314,0.0001110168,0.0006991598,0.002930624,0.0004534617,0.0004325339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002372234,"about_ca_system_score_gemma":0.0004492195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000150885,"about_ca_topic_score_gemma":0.00004877411,"domain_scores_codex":[0.996735,0.0002240513,0.0003201234,0.00187368,0.0001576831,0.0006894372],"domain_scores_gemma":[0.9961835,0.001008342,0.0003075517,0.001769282,0.0004197434,0.000311596],"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":[0.0001689291,0.0001429947,0.0002751816,0.0001220201,0.0002797756,0.00009497115,0.0003297897,0.9426867,0.0005772207,0.04420666,0.005931368,0.005184404],"study_design_scores_gemma":[0.0006534213,0.0001433733,0.000509794,0.0001604263,0.00018316,0.000001897432,0.000067245,0.9772066,0.002377853,0.01072508,0.006923911,0.001047242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008212162,0.00002160845,0.9847324,0.0003515708,0.002204263,0.001095427,0.0001252521,0.0002201901,0.003037165],"genre_scores_gemma":[0.9583471,0.0000488404,0.03895615,0.0002308348,0.0004972626,0.00001348939,0.00001646611,0.0000383071,0.001851501],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.950135,"threshold_uncertainty_score":0.9996198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05694897520610009,"score_gpt":0.205429539313621,"score_spread":0.1484805641075209,"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."}}