{"id":"W4416191083","doi":"10.48550/arxiv.2511.08396","title":"EMAformer: Enhancing Transformer through Embedding Armor for Time Series Forecasting","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; University of Cambridge; Fundamental Research Funds for the Central Universities; Institute for Catastrophic Loss Reduction","keywords":"Transformer; Embedding; Armour; Time series; Multivariate statistics; Series (stratigraphy)","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":[],"consensus_categories":[],"category_scores_codex":[0.001132838,0.0012177,0.0005992774,0.0005534366,0.000192527,0.0008465593,0.001350979,0.0008153932,0.006233578],"category_scores_gemma":[0.004084348,0.0004019534,0.0007757787,0.0005363122,0.0003583893,0.001704073,0.0009265548,0.001769053,0.002700334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003731121,"about_ca_system_score_gemma":0.000791101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003752664,"about_ca_topic_score_gemma":0.006175149,"domain_scores_codex":[0.9996753,0.00009788654,0.00002445626,0.0000822577,0.00008000459,0.00004025386],"domain_scores_gemma":[0.9993278,0.000357376,0.00005321357,0.0001326082,0.0001044663,0.00002454213],"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":[0.00031635,0.0001360381,0.001554876,0.0001790744,0.0001345274,0.0001290227,0.00007019659,0.579335,0.01246856,0.01058953,0.009782553,0.3853044],"study_design_scores_gemma":[0.000008639638,0.00002495534,0.00008425544,0.000006456322,0.000007376636,0.00001492773,0.000003658141,0.9929404,0.002770303,0.002832064,0.001300241,0.000006653592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01278931,0.0003485193,0.9730675,0.0002632714,0.00008891876,0.00004113207,0.0003491715,0.01090975,0.002142483],"genre_scores_gemma":[0.4919143,0.0006450755,0.4933294,0.0004225647,0.0001189574,0.0002183022,0.001872428,0.001664503,0.009814331],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006233578,"threshold_uncertainty_score":0.0208534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04649950636132352,"score_gpt":0.2820866765432398,"score_spread":0.2355871701819163,"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."}}