{"id":"W2952059673","doi":"10.48550/arxiv.1611.07810","title":"A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Automatic summarization; Benchmark (surveying); Artificial intelligence; Task (project management); Vocabulary; Question answering; Machine learning; Language model; Blank; Field (mathematics); Convolutional neural network; Natural language processing; Information retrieval","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":[0.001707275,0.002467309,0.0006708986,0.001964317,0.0009296308,0.001275918,0.003051789,0.002975971,0.005483332],"category_scores_gemma":[0.009077498,0.0003899993,0.001785968,0.002002412,0.0005914994,0.00244537,0.001320532,0.00273861,0.003905432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002105115,"about_ca_system_score_gemma":0.001321149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02879726,"about_ca_topic_score_gemma":0.06400169,"domain_scores_codex":[0.9984654,0.0004484032,0.0001491692,0.0005572211,0.0002688323,0.0001109701],"domain_scores_gemma":[0.9970053,0.001431976,0.0001931396,0.0007185402,0.0004576244,0.0001934558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001376608,0.002346615,0.01879917,0.003641717,0.0003919051,0.00137729,0.0008814296,0.04567886,0.01361207,0.006943416,0.6378316,0.2671194],"study_design_scores_gemma":[0.001028572,0.002096366,0.0478854,0.001095184,0.0002597861,0.002989604,0.002385427,0.5403664,0.02161585,0.02220563,0.357767,0.0003047936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2191412,0.007402875,0.08619177,0.005103816,0.0008769726,0.002926457,0.6360413,0.02451558,0.0178],"genre_scores_gemma":[0.1122002,0.000894796,0.1134704,0.0008106618,0.0001247507,0.001266313,0.7659593,0.0003436677,0.004929846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02879726,"threshold_uncertainty_score":0.05725932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3574155743804664,"score_gpt":0.2913819355829259,"score_spread":0.06603363879754054,"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."}}