{"id":"W7117709618","doi":"10.18280/isi.301112","title":"Efficient Transformer Architectures via Learnable Sparse Attention and Optimization","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Digital Filter Design and Implementation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Transformer; Minification; Optimization problem; Constrained optimization; Optimization algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004710185,0.0008033082,0.0008485949,0.0004215301,0.0002845969,0.0008696645,0.001234683,0.001301897,0.005412611],"category_scores_gemma":[0.00226054,0.0005018992,0.000484022,0.0005403978,0.0005482906,0.001836149,0.00127562,0.001585157,0.00149125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006038953,"about_ca_system_score_gemma":0.0009116057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0026336,"about_ca_topic_score_gemma":0.007227784,"domain_scores_codex":[0.9997005,0.00007377771,0.00001594204,0.00006916768,0.00008395231,0.00005664949],"domain_scores_gemma":[0.9994152,0.0003325318,0.00003857088,0.00007705716,0.0001041269,0.00003256554],"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":[0.0003211161,0.0001502184,0.0004035888,0.0001549082,0.00006914035,0.0001249903,0.0001112993,0.4095225,0.02021974,0.06717099,0.009711122,0.4920403],"study_design_scores_gemma":[0.00001189271,0.00002024638,0.00002251597,0.000003292189,0.000007338182,0.00001787016,0.000006684882,0.9847676,0.001733324,0.01297073,0.0004351925,0.000003336668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0104374,0.0001635164,0.9860706,0.0001961295,0.00003858691,0.00002021544,0.00005271851,0.0009012532,0.002119623],"genre_scores_gemma":[0.6111914,0.0003754407,0.3767493,0.0003917991,0.0001101053,0.0001603194,0.0003759604,0.0003491087,0.01029668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005412611,"threshold_uncertainty_score":0.018107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01315322231391874,"score_gpt":0.2374645899890035,"score_spread":0.2243113676750847,"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."}}