Replication package for Low-Dimensional Asset-Pricing Networks: Identification, Stability, and Economic Use
收藏资源简介：
Code, frozen scientific configurations, synthetic selection frequencies, aggregate numerical results, figure and table inputs, and manuscript sources for Low-Dimensional Asset-Pricing Networks: Identification, Stability, and Economic Use, by Jinpeng Wang and Yan Jiang. The package follows the manuscript section order: framework, data design, dimension identification, temporal updating, representation geometry, and audit. Public exhibit replay verifies archived numerical outputs and regenerates the paper without WRDS access. Full retraining requires lawfully acquired CRSP, Compustat, CCM and benchmark inputs. Licensed stock records, security-level panels and predictions, checkpoints, credentials and institutional connection details are excluded. Original and sanitized-release SHA-256 values are recorded. Interpretation limits are documented: legacy Core-92 development overlaps January 2020; Core-86 bridges benchmark and self-built characteristics; the temporal exercise uses a retrospectively selected sample; and the theoretical result concerns finite known loading spans. Failed tests and historical protocol labels are retained with these qualifications. No claim of journal acceptance, completely untouched research-wide holdout, or cross-platform bitwise retraining is made. Version 1.0.1. The main ZIP is stored as 13 checksum-verified parts after a single-file upload encountered a gateway timeout. Download all parts, archive_parts.json and join_archive.py to one folder and run python3 join_archive.py; see README_ZENODO.txt. The reconstructed ZIP is byte-identical to the complete ZIP on the GitHub v1.0.1 release. The separate geometry-calibration-supplement-1.0.1.zip contains synthetic calibration materials and its own README. Original aggregate data and documentation: CC BY 4.0. Source code: MIT, as specified by LICENSE-CODE. Third-party inputs and dependencies retain their own terms. GitHub: https://github.com/extradimen/asset-pricing-dimension-replication. Correspondence: jiangyan@gcu.edu.cn.
