{"id":"W7075997153","doi":"","title":"ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training","year":2025,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Sorbonne Université; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche","keywords":"Training (meteorology); Action (physics); Work (physics); Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004477897,0.0006931769,0.0005929944,0.001360237,0.004542302,0.006892004,0.002003384,0.003459318,0.54869],"category_scores_gemma":[0.02557051,0.0004487055,0.0006158847,0.0008660218,0.00102962,0.004006709,0.009731586,0.004217001,0.3365928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002357868,"about_ca_system_score_gemma":0.00997712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005105025,"about_ca_topic_score_gemma":0.01385913,"domain_scores_codex":[0.9952643,0.0009540936,0.0001345065,0.0004702447,0.001703429,0.001473461],"domain_scores_gemma":[0.9560093,0.003300746,0.001059053,0.002836426,0.01078556,0.02600894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001729957,0.0001725734,0.0004998617,0.00004700155,0.000002499319,0.00003854571,0.0003883223,0.0000690103,0.0002762184,0.001646051,0.9396372,0.05704953],"study_design_scores_gemma":[0.00007417986,0.0001563594,0.00297052,0.0002168572,0.000007172948,0.0001033151,0.001592999,0.0008853685,0.0004987306,0.003934492,0.9895174,0.00004251982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.01413509,0.0003683052,0.01124246,0.06701039,0.0363977,0.000846283,0.004507161,0.01159688,0.8538958],"genre_scores_gemma":[0.06904153,0.0002363916,0.007681148,0.01236143,0.005154604,0.0009288292,0.003354515,0.002808102,0.8984335],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.54869,"threshold_uncertainty_score":0.643739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05352045601776281,"score_gpt":0.2374584949708896,"score_spread":0.1839380389531268,"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."}}