{"id":"W3118480672","doi":"10.48550/arxiv.2101.01447","title":"End-to-End Video Question-Answer Generation with Generator-Pretester Network","year":2021,"lang":"en","type":"preprint","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":"Ministry of Science and Technology, Taiwan; Nvidia","keywords":"Computer science; Task (project management); Generator (circuit theory); Question answering; Annotation; Artificial intelligence; Ground truth; Information retrieval; Multimedia; Power (physics)","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":[0.0003482871,0.0004165504,0.0003540692,0.0001988007,0.0003440001,0.000500794,0.001501712,0.0002843088,0.00010427],"category_scores_gemma":[0.00004250274,0.0004570997,0.0001391245,0.001038881,0.00007300176,0.000429433,0.001536388,0.000788411,0.0001351825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002607524,"about_ca_system_score_gemma":0.0003815384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008323955,"about_ca_topic_score_gemma":0.0004199119,"domain_scores_codex":[0.9969883,0.0003753409,0.0002525146,0.001744603,0.0001907342,0.0004485382],"domain_scores_gemma":[0.9968777,0.0001141173,0.0002518667,0.002060568,0.0003943696,0.00030138],"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":[0.00000794317,0.00004366409,0.01428022,0.00001660791,0.00007593969,0.0001034338,0.0001954635,0.9196961,0.0002991445,0.06402448,0.0004164639,0.0008405447],"study_design_scores_gemma":[0.0003033727,0.00006408365,0.01565003,0.0001070228,0.00008464983,0.00001551545,0.0000126486,0.9801172,0.0003164208,0.001569912,0.001074959,0.0006841848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3318717,0.00004506709,0.6657917,0.000444413,0.0003906786,0.000344968,0.000006529459,0.0002702125,0.0008347461],"genre_scores_gemma":[0.9262731,0.00002468247,0.0716856,0.0006024066,0.0005413374,0.00001443023,0.0001158474,0.00003706911,0.0007055076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5944015,"threshold_uncertainty_score":0.999788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04454339780986381,"score_gpt":0.2032893094926347,"score_spread":0.1587459116827709,"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."}}