{"id":"W2933890497","doi":"10.1109/iccv.2019.01040","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal; University of Guelph; Vector Institute","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Extension (predicate logic); Image (mathematics); Code (set theory); Simple (philosophy); Code generation; Artificial intelligence; Natural language processing; Computer vision; Programming language; Key (lock)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003467604,0.0002613832,0.0002695216,0.0001766536,0.0002253199,0.0006124465,0.0003688998,0.000168002,0.000005916333],"category_scores_gemma":[0.0003712,0.0002497883,0.00004060061,0.00008987547,0.00006209143,0.00007972748,0.0008218282,0.0006775601,0.00001077879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004094178,"about_ca_system_score_gemma":0.00008156297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008430769,"about_ca_topic_score_gemma":0.000007111334,"domain_scores_codex":[0.9982178,0.0001084364,0.0002917752,0.0009653581,0.0002192333,0.0001973625],"domain_scores_gemma":[0.9984412,0.0002835066,0.0002265285,0.0008464478,0.0001147821,0.00008756053],"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":[0.00002794261,0.0001416076,0.05957102,0.0008547044,0.00007172439,0.00001771016,0.002354012,0.5390972,0.006684575,0.02912883,0.0002370266,0.3618136],"study_design_scores_gemma":[0.0003372854,0.00003736374,0.01849156,0.0001014664,0.00001102474,0.000008771739,0.000008027871,0.9794162,0.000474584,0.0007256849,0.0001218124,0.0002662463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3424641,0.00008428683,0.6518039,0.0004939009,0.0003494089,0.000407386,0.000006265688,0.0003131854,0.004077523],"genre_scores_gemma":[0.7354438,0.000009071653,0.2640319,0.0001906648,0.0001456167,0.00003290814,0.00001305937,0.00001550462,0.0001174468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4403189,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01344478684576166,"score_gpt":0.2737859628238873,"score_spread":0.2603411759781257,"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."}}