REFERENCES
References and data sources
The academic works cited in the CP2 report draft, every data source with its terms, permission and attribution, and the software the terminal uses.
- ACADEMIC REFERENCES
- DATA SOURCES WITH PERMISSIONS
- SOFTWARE LICENCES
Academic references
As written in the citation ledgers of the CP2 report draft, read from the repository at build time, with each entry's recorded verification status.
Vitor Cerqueira; Luis Torgo; Igor Mozetič (2020). Evaluating time series forecasting models: an empirical study on performance estimation methods. Machine Learning, 109, 1997–2028. DOI 10.1007/s10994-020-05910-7.
Christoph Bergmeir; Rob J. Hyndman; Bonsoo Koo (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120, 70–83. DOI 10.1016/j.csda.2017.11.003.
Shihao Gu; Bryan Kelly; Dacheng Xiu (2020). Empirical Asset Pricing via Machine Learning. The Review of Financial Studies, 33(5), 2223–2273. DOI 10.1093/rfs/hhaa009.
Andrew Ang; Geert Bekaert (2002). International Asset Allocation with Regime Shifts. The Review of Financial Studies, 15(4), 1137–1187. DOI 10.1093/rfs/15.4.1137.
Robert Almgren; Neil Chriss (2001). Optimal execution of portfolio transactions. The Journal of Risk, 3(2), 5–39. DOI 10.21314/JOR.2001.041.
Abhimanyu Das; Weihao Kong; Rajat Sen; Yichen Zhou (2024). A decoder-only foundation model for time-series forecasting. ICML; Proceedings of Machine Learning Research, 235, 10148–10167.
Tilmann Gneiting; Adrian E. Raftery (2007). Strictly Proper Scoring Rules, Prediction, and Estimation. Journal of the American Statistical Association, 102(477), 359–378. DOI 10.1198/016214506000001437.
Google Research (Accessed 2026-10-14). google/timesfm-2.5-200m-pytorch model card. Official model documentation.
Hastie, Trevor; Tibshirani, Robert; Friedman, Jerome (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, second edition. Springer.
Jeffrey Heer; Ben Shneiderman (2012). Interactive Dynamics for Visual Analysis. Communications of the ACM, 55(4), 45–54. DOI 10.1145/2133806.2133821.
Meelis Kull; Miquel Perello Nieto; Markus Kängsepp; Telmo Silva Filho; Hao Song; Peter Flach (2019). Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration. Advances in Neural Information Processing Systems, 32.
Takaya Saito; Marc Rehmsmeier (2015). The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLOS ONE, 10(3), e0118432. DOI 10.1371/journal.pone.0118432.
Sokolova, Marina; Lapalme, Guy (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management45(4),427–437. DOI10.1016/j.ipm.2009.03.002.
Matthew Wang; Yi-Hong Lin; Ilya Mikhelson (2020). Regime-Switching Factor Investing with Hidden Markov Models. Journal of Risk and Financial Management, 13(12), 311. DOI 10.3390/jrfm13120311.
Chuan Guo; Geoff Pleiss; Yu Sun; Kilian Q. Weinberger (2017). On Calibration of Modern Neural Networks. ICML; Proceedings of Machine Learning Research, 70, 1321–1330. Primary record. Status: PRIMARY PEER-REVIEWED SOURCE VERIFIED.
Google Research (Accessed 2026-10-14). google/timesfm-2.5-200m-pytorch model card. Official model documentation. Primary record. Status: OFFICIAL TECHNICAL DOCUMENTATION VERIFIED.
Scott M. Lundberg; Su-In Lee (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30. Primary record. Status: PRIMARY PEER-REVIEWED SOURCE VERIFIED.
Dominik Janzing; Lenon Minorics; Patrick Blöbaum (2020). Feature relevance quantification in explainable AI: A causal problem. AISTATS; Proceedings of Machine Learning Research, 108, 2907–2916. Primary record. Status: PRIMARY PEER-REVIEWED SOURCE VERIFIED.
Joelle Pineau; Philippe Vincent-Lamarre; Koustuv Sinha; Vincent Lariviere; Alina Beygelzimer; Florence d'Alche-Buc; Emily Fox; Hugo Larochelle (2021). Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program). Journal of Machine Learning Research, 22(164), 1–20. Primary record. Status: PRIMARY PEER-REVIEWED SOURCE VERIFIED.
Data sources
Each source is shown only where its terms allow, with the attribution text it requires. Broker prices from the research (MT5) are never published.
| Source | Used for | Terms | Permission | Attribution shown | On this site |
|---|---|---|---|---|---|
| London Strategic Edge | XAU/USD and QQQM derived prices, bid/ask, 5-minute candles and the economic calendar (live panels from the live proxy only) | Non-commercial academic showcase; cached server-side; no download, export or API; attribution and a link to the provider's website on every page with its data | Written permission by email, 3 Nov 2026 (owner record) | Data: London Strategic Edge (derived prices, not exchange data) | Live panels only, after the live proxy is published |
| U.S. Bureau of Labor Statistics | Official release values and news releases (live proxy panels) | US government open data, used with attribution | Not required (open data) | Source: U.S. Bureau of Labor Statistics | Live panels only, after the live proxy is published |
| U.S. Bureau of Economic Analysis | Official release values and news releases (live proxy panels) | US government open data, used with attribution | Not required (open data) | Source: U.S. Bureau of Economic Analysis | Live panels only, after the live proxy is published |
| Board of Governors of the Federal Reserve System | Monetary-policy press releases (live proxy panels) | Board website information is in the public domain; cite the Board as the source; no seals, logos or framing | Not required (public domain) | Source: Board of Governors of the Federal Reserve System | Live panels only, after the live proxy is published |
| U.S. Securities and Exchange Commission | Press-release headlines in the planned News and releases panel | US government press releases; reuse statement verified by the live proxy task before the source is switched on | Not required (public domain), pending that verification | Source: U.S. Securities and Exchange Commission | Not yet: planned live proxy panel |
| FRED, Federal Reserve Bank of St. Louis | Macro series for the heat map (public-domain series only) | FRED terms of use; only series marked public domain are shown | Not required for public-domain series | Source: FRED, Federal Reserve Bank of St. Louis | Live panels only, after the live proxy is published |
| World Bank | Country indicators for the heat map | Mostly CC BY 4.0; licence checked per dataset | Not required (open licence with attribution) | Source: World Bank (CC BY 4.0) | Live panels only, after the live proxy is published |
| International Monetary Fund | Country indicators for the heat map | IMF terms: attribution and dataset notes | Not required (attribution) | Source: International Monetary Fund | Live panels only, after the live proxy is published |
| The GDELT Project | Headlines (headline, outlet, time and link only) in the planned News and releases panel | Unlimited and unrestricted use for academic, commercial or governmental use; any use or redistribution must cite the GDELT Project | Not required (citation) | Source: The GDELT Project | Not yet: planned live proxy panel |
| Alpaca (News API, Benzinga content) | Headlines in the private terminal only | Alpaca Support, 4 Nov 2026: News API content may not be publicly displayed or redistributed under a standard account, including a non-commercial academic showcase | Public display refused, 4 Nov 2026 (owner record) | Not displayed on this site (provider terms) | Never on this site |
| MT5 broker prices (research data) | The research data behind the frozen models, on the owner's computer | Not cleared for public display | None for public display | Not displayed on this site | Never on this site |
| Twelve Data | Private terminal context only | Non-display plan | None for public display | Not displayed on this site | Never on this site |
Software and fonts
| Component | Licence |
|---|---|
| Node.js (built-in modules only) for this site's build | MIT |
| Lightweight Charts™ by TradingView (private terminal and demo charts) | Apache License 2.0, attribution to TradingView |
| XGBoost | Apache License 2.0 |
| hmmlearn | BSD 3-Clause |
| scikit-learn | BSD 3-Clause |
| React (private terminal and demo) | MIT |
| FastAPI (private terminal) | MIT |
| Fonts: none downloaded; the site uses IBM Plex if installed on your device, otherwise your system fonts | IBM Plex: SIL Open Font License 1.1 |