IST02-IST03 JSE-Eskom Infrastructure-Coupled Financial Network Dataset IST02-IST03 JSE-Eskom Infrastructure-Coupled Financial Network Dataset (v2.0.0)

Hypergraph edge-weight time series linking 87 JSE-listed securities to 34 Eskom transmission grid nodes (January 2015 to December 2025, T=2870 trading days, 340 hyperedges). Supports IST-02 CASCADEnt/VORTEX and IST-03 PHYSAN research series by Prof. N.D. Moroke, North-West University, South Africa. This dataset supports the paper "Infrastructure-Induced Geometric Compression in an Emerging Financial Market" (Moroke, 2026, Emerging Markets Review, under review). Contents:- eskom_stages_2015_2026.csv: Daily peak load-shedding stage   (integer 0–6) for South Africa, 1 January 2015 to 30 April 2026.   Sources: Eskom published schedules, CSIR energy reports,   EskomSePush archive.- eskom_stages_trading_days.csv: Business-day version of the above,   forward-filled for weekends and public holidays.- jse_panel.csv: Daily adjusted closing prices for 15 JSE Top40   securities, January 2015 to April 2026 (Yahoo Finance).- shredi_combined.csv: Final merged analysis dataset — 7 asset   return series plus Eskom stage and regime classification,   N=2,838 trading days.- shredi_7asset_pipeline.py: Complete reproducible Python pipeline   producing all results in the paper.- shredi_all_results.json: All numerical results from pipeline.- build_eskom_zenodo.py: Script to rebuild the Eskom stage series   from documented public record. This dataset also supports the paper: Moroke, N.D. (2026). TENSORnet: A Physics-Informed Entropy Protocol for Infrastructure-Induced Metabolic Arrest Detection in Cross-Asset Financial Networks. Computation (MDPI), under review. Moroke,  N. D. TENSORnet: A Physics-Informed Entropy Protocol for Infrastructure-Induced Metabolic Arrest Detection in Cross-Asset Financial Networks. Preprints 2026, 2026051670. doi.org The TENSORnet paper uses the JSE panel data (jse_panel.csv), Eskom load-shedding stages (eskom_stages_trading_days.csv), and the hypergraph edge-weight time series to construct the Topological Entropy Network Stress Operator and validate metabolic arrest detection across 87 JSE securities coupled to 34 Eskom transmission nodes over T=2,870 trading days (January 2015 – December 2025). This dataset also supports: Moroke, N.D. (2026). Interpretable Machine Learning Reveals Jamming Physics in Infrastructure-Constrained Markets: The MERI Framework. Modelling (MDPI), under review. Uses jse_7asset_returns_2015_2026.csv for EGARCH-GED calibration and eskom_stages_trading_days.csv as the infrastructure stress target (seed=42 simulation). DOI: 10.5281/zenodo.20008530 This dataset also supports: Moroke, N.D. (2026). Interpretable Machine Learning Reveals Jamming Physics in Infrastructure-Constrained Markets: The MERI Framework. Modelling (MDPI), under review. Uses: - jse_7asset_returns_2015_2026.csv — EGARCH-GED calibration parameters   estimated from these real returns (seed=42 simulation) - eskom_stages_trading_days.csv — infrastructure stress target (Stage 4+) --- SARDINE: Fuzzy-Gated Stochastic Diffusion for Financial Regime Detection in Fractal Long-Memory Emerging Markets SARDINE (Stochastic Adaptive Regime Detection via Integrated Neuro-Fuzzy Estimation) is the fourth paper in the IST-02 series on JSE financial network analysis. The IST-02 series applies physics-informed neural architectures to the Johannesburg Stock Exchange (JSE) and Eskom infrastructure-coupled dataset. The series includes:- CASCADEnt (entropy-network topology)- TENSORnet (tensor decomposition)- S-NODE-ANFRRC (deterministic neural ODE baseline)- SARDINE (fuzzy-gated stochastic diffusion — this paper) DATASET CONTENTSThis repository contains the IST-02/IST-03 JSE-Eskom Infrastructure-Coupled Financial Network Dataset: 1. jse_7asset_returns_2015_2026.csv (310 kB)   Daily closing prices for 17 JSE Top40 securities across 7 sectors (financial services, mining, energy, telecommunications, consumer commodities, diversified financials, insurance), 27 March 2015 to 30 March 2026. 2. eskom_stages_2015_2026.csv (54 kB)   Daily Eskom load-shedding stage (Stage 0–8), 2015–2026. Source: beyarkay/eskom-calendar (GitHub). 3. eskom_stages_trading_days.csv (38 kB)   Trading-day aligned version of the Eskom load-shedding series, matched to JSE trading calendar. 4. build_eskom_zenodo.py (10 kB)   Provenance and build script documenting data sourcing, alignment, and quality checks. EXOGENOUS COVARIATECBOE Volatility Index (VIX) daily closing levels sourced from Yahoo Finance (ticker: ^VIX). Not included in this archive; publicly available. TEMPORAL SPLIT USED IN SARDINETraining: 2015–2021 (70%), Validation: 2022 (10%), Test: 2023–2026 (537 days, 20%). RELATED PUBLICATIONS (IST-02/IST-03 Series)- Moroke, N.D. S-NODE-ANFRRC. Preprints 2026, 2026051066. doi.org Moroke, N.D. Metabolic Saliency (IST-03). Entropy 2026, 28, 559. doi.org Moroke, N.D. SARDINE (this paper). Fractal and Fractional, submitted 2026. CORRESPONDING AUTHORProf. Ntebogang Dinah Moroke | ORCID: 0000-0001-8545-1860Faculty of Economic and Management Sciences, North-West University, Mafikeng Campus, South Africantebo.moroke@nwu.ac.za Hypergraph edge-weight time series and real JSE-Eskom financial market data linking 87 JSE-listed securities to 34 Eskom transmission grid nodes (January 2015 to December 2025, T=2,870 trading days, 340 hyperedges). Supports the IST-02 and IST-03 research series by Prof. N.D. Moroke, North-West University, South Africa. FILES------ jse_7asset_returns_2015_2026.csv: Real daily adjusted closing   prices for 17 JSE-listed securities across nine FTSE/JSE sector   classifications, sourced from Yahoo Finance (2015-2026, 310 kB)- eskom_stages_2015_2026.csv: Daily peak Eskom load-shedding stage   (integer 0-8), 1 January 2015 to 30 April 2026. Sources: Eskom   published schedules, CSIR energy reports, EskomSePush archive- eskom_stages_trading_days.csv: Trading-day aligned version of   the Eskom load-shedding series, forward-filled for weekends and   public holidays- build_eskom_zenodo.py: Provenance and build script documenting   data sourcing, alignment, and quality checks- README.md: Full dataset documentation SUPPORTED PAPERS----------------1. SHREDI Framework   Moroke, N.D. (2026). Statistical Hybrid Riemannian-Ensemble    Dimensional Integration: Documenting Jamming Transitions in JSE    Financial Networks under Eskom Load-Shedding.   Symmetry (MDPI), under review.   Preprint DOI: 10.20944/preprints202605.0757.v1   Uses: jse_7asset_returns_2015_2026.csv,          eskom_stages_trading_days.csv 2. MERI Framework   Moroke, N.D. (2026). Cognitive Big Data Architecture for    Real-Time Jamming Transition Detection in Infrastructure-   Constrained Financial Markets: The MERI Framework.   Big Data and Cognitive Computing (MDPI), submitted May 2026.   DOI: 10.5281/zenodo.20008530   Uses: jse_7asset_returns_2015_2026.csv (real JSE daily returns,    EGARCH-GED parameters estimated via MLE),    eskom_stages_trading_days.csv (infrastructure stress target,    Stage 4+ = Fragile regime label)   Key empirical results: 97.3% accuracy, AUC=0.9973,    48-hour Granger lead (F=62.003, p<0.001), 7.78x hysteresis 3. TENSORnet   Moroke, N.D. (2026). TENSORnet: A Physics-Informed Entropy    Protocol for Infrastructure-Induced Metabolic Arrest Detection    in Cross-Asset Financial Networks.   Computation (MDPI), under review.   Preprint DOI: 10.20944/preprints202605.1670.v1   Uses: jse_panel.csv, eskom_stages_trading_days.csv 4. CASCADEnt / S-NODE-ANFRRC / SARDINE (IST-02 series)   Uses: jse_7asset_returns_2015_2026.csv,          eskom_stages_2015_2026.csv METHODOLOGICAL NOTE-------------------All JSE return data are real market observations sourced directly from Yahoo Finance. EGARCH-GED tail shape parameters are estimated from these real returns via maximum likelihood:  Resilient regime: nu_hat = 1.87 +/- 0.14  Fragile regime:   nu_hat = 1.34 +/- 0.21 Regime labels: Resilient = Stage 0-3 (N=2,173 days, 83.3%); Fragile = Stage 4+ (N=436 days, 16.7%). Stage 6+ episodes absent before 2022, comprising 146 trading days (5.6%) of full sample. CORRESPONDING AUTHOR--------------------Prof. Ntebogang Dinah MorokeDepartment of Statistics and Operations ResearchNorth-West University, Mafikeng Campus, South AfricaORCID: 0000-0001-8545-1860