{"id":"W3023750926","doi":"","title":"Compact Neural Representation Using Attentive Network Pruning.","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":"York University","funders":"","keywords":"Computer science; Redundancy (engineering); Pruning; Artificial intelligence; Benchmark (surveying); Artificial neural network; Reduction (mathematics); Machine learning; Mathematics","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":[0.00009121491,0.0003482753,0.0003940011,0.0001072037,0.0003323252,0.0001528944,0.001769108,0.000171127,0.00001120438],"category_scores_gemma":[0.00002672663,0.0004346482,0.0002263439,0.001405355,0.0001197979,0.0006064186,0.002084077,0.0007338083,0.00004905297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002105206,"about_ca_system_score_gemma":0.0001214153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007756859,"about_ca_topic_score_gemma":0.00001549512,"domain_scores_codex":[0.9974729,0.0002160443,0.0002668382,0.001467628,0.0001220944,0.0004544549],"domain_scores_gemma":[0.9976273,0.0001907258,0.0004990743,0.001295414,0.0001502374,0.0002372647],"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":[0.00001721572,0.00002303584,0.002815681,0.00002196878,0.00004445558,0.0001236936,0.0001098721,0.9641731,0.00009844256,0.03187292,0.0004481041,0.0002515187],"study_design_scores_gemma":[0.0002184338,0.0000227681,0.002161773,0.0001123203,0.00005861701,0.000007557708,0.00002438887,0.9557457,0.00006551057,0.04110075,0.00009643779,0.0003857709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1085457,0.00006567628,0.8885927,0.0004770076,0.0005078582,0.0006674443,0.000008259524,0.0004696339,0.000665716],"genre_scores_gemma":[0.9880678,0.00005652369,0.01108104,0.0002513512,0.0003071116,0.000001258909,0.00003576811,0.00002812468,0.0001710192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8795221,"threshold_uncertainty_score":0.9998105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1805037949976826,"score_gpt":0.2504595302865041,"score_spread":0.06995573528882157,"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."}}