{"id":"W2155292833","doi":"10.48550/arxiv.1511.02793","title":"Generating Images from Captions with Attention","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Computer science; Artificial intelligence; Generative model; Baseline (sea); Image (mathematics); Natural language processing; Training set; Natural (archaeology); Natural language generation; Machine learning; Natural language; Geography","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":[0.0001619413,0.0002417709,0.0002095029,0.000154831,0.0002258811,0.0002035963,0.001254442,0.0001563818,0.00001934126],"category_scores_gemma":[0.00002702244,0.0002575861,0.00008694136,0.0003863338,0.00007491822,0.0003134948,0.001175722,0.0005996337,0.0001821446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001901865,"about_ca_system_score_gemma":0.0002017059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004533947,"about_ca_topic_score_gemma":0.0001712272,"domain_scores_codex":[0.9983744,0.0001438181,0.0001426572,0.001012618,0.0001035542,0.0002229545],"domain_scores_gemma":[0.9979794,0.00006961229,0.0002503272,0.001277966,0.0002613375,0.0001613752],"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":[0.000005532394,0.00006166842,0.01417032,0.00001042478,0.0000666783,0.00004726203,0.0001691571,0.9610744,0.0004565601,0.02295208,0.0002336206,0.0007523384],"study_design_scores_gemma":[0.0003127639,0.00002254956,0.0164797,0.00004638234,0.00005938028,0.000002646532,0.00003807092,0.9695531,0.00003093435,0.01301615,0.0001127341,0.0003256115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4405344,0.00002098646,0.5578642,0.0001761746,0.00009452077,0.0001468002,0.00002522364,0.0002696523,0.0008680313],"genre_scores_gemma":[0.9408504,0.00001154278,0.05816986,0.00004471229,0.0001087148,0.000003817993,0.0001099624,0.00001807437,0.0006829158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.500316,"threshold_uncertainty_score":0.9999877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06370869466700849,"score_gpt":0.2035532282945449,"score_spread":0.1398445336275364,"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."}}