{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007479189,0.0007133881,0.001083406,0.0002387396,0.0007713577,0.0004707961,0.001670681,0.0004011738,0.0001025118],"category_scores_gemma":[0.0002391258,0.0006807852,0.000870264,0.0006036714,0.00009502706,0.001349791,0.0009958419,0.0007041983,0.0000620857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001636826,"about_ca_system_score_gemma":0.0003444971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001054126,"about_ca_topic_score_gemma":0.00007583308,"domain_scores_codex":[0.9959432,0.0000612951,0.001159847,0.001405156,0.0003839852,0.001046459],"domain_scores_gemma":[0.9974976,0.0003188834,0.0006014383,0.001111026,0.0003391033,0.0001320116],"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":[0.001056471,0.001346261,0.0447026,0.02267575,0.01153968,0.000374121,0.09617217,0.09546559,0.04523572,0.09067907,0.01453221,0.5762203],"study_design_scores_gemma":[0.001539759,0.0005527656,0.001229457,0.004370967,0.000969126,0.00009884185,0.001115796,0.8515161,0.07344635,0.01736562,0.04391813,0.003877106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08244611,0.0006927969,0.9031679,0.0008977673,0.001258252,0.0009431615,0.0000883477,0.0005027195,0.01000292],"genre_scores_gemma":[0.5407232,0.0002568191,0.4350467,0.0008740262,0.00140418,0.0006426445,0.0002752429,0.0001418341,0.02063536],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7560505,"threshold_uncertainty_score":0.9995643,"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."}}