{"id":"W3016732970","doi":"10.48550/arxiv.2004.08708","title":"Adaptive Attention Span in Computer Vision","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"FLOPS; Computer science; Kernel (algebra); Convolution (computer science); Artificial intelligence; Code (set theory); Transformer; Algorithm; Computer engineering; Computer vision; Parallel computing; Theoretical computer science; Machine learning; Mathematics; Programming language; Voltage; Artificial neural network; Engineering","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":[0.0009246449,0.0005505924,0.0006591942,0.001051651,0.0003137465,0.0009455231,0.001146781,0.0009453826,0.002774812],"category_scores_gemma":[0.003936499,0.0002847071,0.000424498,0.001354719,0.001013993,0.00217335,0.00137152,0.001533778,0.0007803109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001322341,"about_ca_system_score_gemma":0.000527676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004180916,"about_ca_topic_score_gemma":0.001908439,"domain_scores_codex":[0.9994253,0.0001317938,0.00002347341,0.0002233568,0.0001382333,0.0000579588],"domain_scores_gemma":[0.9990895,0.0005092894,0.00006575487,0.000134519,0.0001522012,0.00004879543],"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":[0.000218876,0.00009750808,0.001617322,0.000297784,0.0001033381,0.0001227634,0.000194084,0.2126666,0.01584332,0.189031,0.009606822,0.5702006],"study_design_scores_gemma":[0.00001599491,0.00007087456,0.0009507473,0.0000235465,0.00001841368,0.00009438363,0.0000200717,0.7897745,0.005489167,0.1980716,0.005452703,0.00001796805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0398634,0.007499461,0.9429772,0.0009390906,0.0002281614,0.00004016908,0.0001061376,0.001746407,0.006600061],"genre_scores_gemma":[0.8203462,0.003748626,0.168011,0.0005525699,0.0005123966,0.0001111014,0.0002598186,0.0002741595,0.006184153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004180916,"threshold_uncertainty_score":0.009594321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0817765409891001,"score_gpt":0.2090942608997732,"score_spread":0.1273177199106731,"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."}}