{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005829459,0.0001669834,0.0001988848,0.0001310482,0.0001375852,0.0000862809,0.002061284,0.0001110151,0.000001682352],"category_scores_gemma":[0.00007808473,0.0001510668,0.00003458968,0.0002508446,0.00008482178,0.001667442,0.00165649,0.0002275341,0.000002506556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001092173,"about_ca_system_score_gemma":0.00007996379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005861498,"about_ca_topic_score_gemma":0.0001323383,"domain_scores_codex":[0.9985446,0.0001367018,0.000204021,0.0008576573,0.00008089749,0.0001761674],"domain_scores_gemma":[0.9972668,0.0004826349,0.0002471149,0.001917624,0.00004952243,0.00003632246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000148675,0.00003202908,0.0003024863,0.00008377177,0.00002263696,0.000004774804,0.0007120647,0.1722055,0.00002155639,0.8260704,0.0003390018,0.0001909197],"study_design_scores_gemma":[0.0002274654,0.00001220969,0.0000870312,0.00008723183,0.00001995233,0.000001004216,0.00009628431,0.5973624,0.000006731983,0.4018649,0.0001240564,0.000110747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004625416,0.00002962538,0.9924721,0.0009158203,0.00006944562,0.0005286279,0.001110137,0.00004804728,0.0002008408],"genre_scores_gemma":[0.9832369,0.0001096358,0.01562698,0.00004728217,0.00002995549,0.000006638415,0.0009194706,0.00001003279,0.00001311324],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9786115,"threshold_uncertainty_score":0.6160324,"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."}}