{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008040969,0.0002516538,0.0002662522,0.000185909,0.00008880881,0.00006596661,0.001444214,0.0001774514,0.000006209298],"category_scores_gemma":[0.000005004905,0.0003101161,0.0001361817,0.0009019854,0.00006512801,0.0004168289,0.002640794,0.0006327065,0.0001719131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002131911,"about_ca_system_score_gemma":0.00006126964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003574065,"about_ca_topic_score_gemma":0.00003759319,"domain_scores_codex":[0.9980582,0.000116403,0.0001966265,0.001274681,0.00008224142,0.0002718408],"domain_scores_gemma":[0.9985939,0.00008250997,0.0002108092,0.0008974079,0.00007498451,0.0001404417],"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":[0.00002721862,0.00008355378,0.0007480844,0.00001933933,0.00001902715,0.000266401,0.00008006872,0.8274091,0.00006926447,0.1647402,0.0003495029,0.006188217],"study_design_scores_gemma":[0.0002615188,0.00006752729,0.00803214,0.0000684856,0.00001060127,0.000002422878,0.000007204199,0.9048195,0.00001548516,0.08622383,0.0002141838,0.000277109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05497481,0.00001721104,0.9430481,0.0005570083,0.0002848092,0.0003940694,0.000005539215,0.0002626298,0.0004558797],"genre_scores_gemma":[0.9737499,0.00006632937,0.02572579,0.0001876912,0.0001088218,0.000002082814,0.00001902101,0.00001471707,0.000125588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9187751,"threshold_uncertainty_score":0.9999351,"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."}}