{"id":"W4416342822","doi":"10.1109/socc66126.2025.11235365","title":"Sparse Attention: A Co-Design Approach for Efficient Transformer Execution on Tensor Cores","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint John Regional Hospital; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exploit; Software; Inference; Pruning; Set (abstract data type); Component (thermodynamics); Minification; Tensor (intrinsic definition)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004884066,0.0004799715,0.0004350641,0.000298512,0.00090404,0.0002404404,0.0009959775,0.0002029241,0.00003764567],"category_scores_gemma":[0.00003669079,0.000435574,0.0003365182,0.001488708,0.0002585963,0.0002365799,0.00005953169,0.0002916885,0.00009566197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002043864,"about_ca_system_score_gemma":0.0001776366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003846295,"about_ca_topic_score_gemma":9.329549e-7,"domain_scores_codex":[0.996393,0.0001429876,0.0007538952,0.001454068,0.0004489386,0.0008070638],"domain_scores_gemma":[0.997716,0.0005473393,0.0001943052,0.001086174,0.0002766939,0.0001794955],"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":[0.0004338385,0.001469589,0.00002201065,0.0001371236,0.00008470522,0.000001557966,0.0001872442,0.4301697,0.003823481,0.460507,0.02064141,0.0825223],"study_design_scores_gemma":[0.001508669,0.0004758033,0.0004189144,0.00009392775,0.00008554336,0.000007274243,0.00007929378,0.9750398,0.009277743,0.003320117,0.009239014,0.0004538313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005618193,0.0002095058,0.9741037,0.003344722,0.0004715254,0.005393981,0.00002585918,0.0002769303,0.01561194],"genre_scores_gemma":[0.6033545,0.0001291024,0.3771537,0.002019105,0.0002021371,0.002199964,0.00005494109,0.0000390384,0.0148476],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6027926,"threshold_uncertainty_score":0.9998096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05240302543642369,"score_gpt":0.3107068447083154,"score_spread":0.2583038192718918,"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."}}