{"id":"W7106829309","doi":"10.48448/pv6x-t052","title":"ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Scalability; Throughput; Training (meteorology); Inference; FLOPS; Computational complexity theory; Adaptation (eye)","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":[0.0009803422,0.001030957,0.0007224731,0.0004768794,0.0006495697,0.001720489,0.004099199,0.001273617,0.01145638],"category_scores_gemma":[0.007059977,0.0008427926,0.0006180173,0.0005715564,0.0008424857,0.004945604,0.002696684,0.002205345,0.005339757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009141328,"about_ca_system_score_gemma":0.001676013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005850698,"about_ca_topic_score_gemma":0.0112896,"domain_scores_codex":[0.9993234,0.000161485,0.00005791189,0.0002009329,0.0001554378,0.0001008838],"domain_scores_gemma":[0.9979101,0.0006566225,0.0001127762,0.0008219429,0.0003780315,0.000120532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001825074,0.0004607267,0.005343867,0.0004498463,0.0002778362,0.0005436687,0.0004613018,0.2074634,0.05354551,0.02308019,0.0725261,0.6340225],"study_design_scores_gemma":[0.00005427648,0.000122205,0.0002776999,0.00002752992,0.00002553673,0.0000915999,0.00003914032,0.9540367,0.02334332,0.009797212,0.01214335,0.00004148196],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.04025408,0.001281172,0.8693676,0.0005854332,0.0003800393,0.0001122798,0.0007046992,0.08057038,0.006744283],"genre_scores_gemma":[0.5492113,0.000401085,0.4289584,0.000975135,0.000139391,0.0003209724,0.003359086,0.004279015,0.01235565],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01145638,"threshold_uncertainty_score":0.03832537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05021796711804338,"score_gpt":0.3219710691510244,"score_spread":0.271753102032981,"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."}}