{"id":"W2524766041","doi":"10.5244/c.30.141","title":"Oracle Performance for Visual Captioning","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Closed captioning; Computer science; Oracle; Task (project management); Artificial intelligence; Natural language; Process (computing); Natural language processing; Image (mathematics); Simplicity; Imperfect; Upper and lower bounds; Machine learning; Programming language; Mathematics; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002693597,0.0001675504,0.0001605336,0.00009206334,0.0001924551,0.0001875868,0.001068587,0.00013226,0.00003104534],"category_scores_gemma":[0.00005284106,0.0001333448,0.00008526306,0.00007931531,0.00002477196,0.0001719931,0.001104284,0.000259463,0.0002378756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006755337,"about_ca_system_score_gemma":0.0001216633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009016036,"about_ca_topic_score_gemma":0.000002900906,"domain_scores_codex":[0.998778,0.00002555049,0.0002140351,0.0005769848,0.0001615831,0.0002438216],"domain_scores_gemma":[0.9987776,0.0001456683,0.0001520733,0.0007174419,0.000137377,0.00006986995],"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":[0.00001146223,0.0001392146,0.01015788,0.0003178207,0.00006488797,6.508747e-7,0.0005391709,0.009557547,0.001391917,0.2618126,0.001909588,0.7140972],"study_design_scores_gemma":[0.0001892489,0.00003602021,0.0165094,0.00006726209,0.000005228626,0.000002300369,0.000001872015,0.968852,0.0007899394,0.008906207,0.004368667,0.0002718884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04643993,0.00002186619,0.944419,0.002479094,0.0003264411,0.0004592504,0.000004932602,0.0005435519,0.005305984],"genre_scores_gemma":[0.7425095,0.000005443713,0.2555623,0.0001192481,0.0001703391,0.0003944834,0.00001055373,0.00001457628,0.001213467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9592944,"threshold_uncertainty_score":0.5437644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02151043613204327,"score_gpt":0.3232858661331357,"score_spread":0.3017754300010924,"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."}}