{"id":"W3213111926","doi":"10.48550/arxiv.2012.02339","title":"Understanding Guided Image Captioning Performance across Domains","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Closed captioning; Computer science; Readability; Transformer; Artificial intelligence; Natural language processing; Image (mathematics); Domain (mathematical analysis); Key (lock); Information retrieval; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00401172,0.001827779,0.000652472,0.00135856,0.0004934589,0.00230515,0.001809865,0.002717609,0.004014676],"category_scores_gemma":[0.02065178,0.0005104488,0.001086521,0.0008436,0.0008529149,0.004292742,0.001601895,0.002485325,0.002921435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001629479,"about_ca_system_score_gemma":0.0006916358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008254639,"about_ca_topic_score_gemma":0.006679851,"domain_scores_codex":[0.9984918,0.0006512144,0.00007173213,0.0004984898,0.0001696008,0.0001171597],"domain_scores_gemma":[0.9905046,0.00620044,0.0003126616,0.001594488,0.001096267,0.0002915547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001272655,0.0006022577,0.006596196,0.001293116,0.000394502,0.0005810717,0.00158887,0.2942722,0.04486995,0.00482038,0.03808941,0.6056194],"study_design_scores_gemma":[0.00006355971,0.0003383823,0.002636669,0.0001263537,0.00006572263,0.000265007,0.0003734337,0.9491901,0.03176307,0.008712155,0.006397443,0.00006814171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4950174,0.007687208,0.4161422,0.00189704,0.0007545331,0.00120557,0.00609647,0.04478002,0.02641945],"genre_scores_gemma":[0.7995638,0.001250678,0.1814939,0.0006504825,0.0001157879,0.000303658,0.01021143,0.001204817,0.005205456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008254639,"threshold_uncertainty_score":0.02121627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2005041772895836,"score_gpt":0.2319281612384972,"score_spread":0.0314239839489136,"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."}}