Silent Reward and Environment Defects in EV Charging Simulation Benchmarks — Reproducibility Data (preliminary)

Abstract

Reproducibility data deposit for the manuscript "Silent Reward and Environment Defects in EV Charging Simulation Benchmarks: A Diagnostic Checklist", submitted to the Bulletin of Electrical Engineering and Informatics (BEEI), IAES. This dataset contains the raw campaign data, seed-level measurements, final published figures, and the three supplementary tables (S1-S3) referenced in the manuscript, supporting independent verification of the reported results. Contents:- data/ — raw campaign data and seed-level measurements (CSV/JSON), including D4 impact data, A1-A2 ablation per-seed data, the D5 frozen decision corpus, and the D1 (RNG-regime) validation-campaign data- figures/ — final published figures (PDF and PNG)- table_s1_comparative_positioning.pdf — full ten-work related-work comparison table- table_s2_full_ablation_family.pdf — complete 24-comparison A1-A2 ablation family- table_s3_full_repro_params.pdf — complete benchmark, reward, and training parameter table Every file's integrity can be verified against the included MANIFEST.sha256.