Experimental contract
What this family tests
descriptive panel and holdout studies
- Twenty-six-company trajectory panel
- Block-denoising holdout study
- KET trajectory comparison
- Animated brand and risk-profile rendering
Book-to-code crosswalk
The highlighted Experiment cards covered here
- Experiment: brand-aware temporal walk-forward audit.17.6.1 Middle-Year Reconstruction Benchmark · reported result or audit · direct chapter family
Implementation map
From entry point to source surface
Start here
These concrete files are selected from the complete registered source surface to orient the reader.
- runner · public-pinned —
brand-democritus:run_brand_financial_filings.py↗Open the pinned public source file. - runner · public-pinned —
brand-democritus:animate_company_structural_risk_radar.py↗Open the pinned public source file. - runner · public-pinned —
brand-democritus:temporal_infer.py↗Open the pinned public source file. - runner · public-pinned —
brand-democritus:temporal_train.py↗Open the pinned public source file.
Author-declared entry points
repository scripts and notebooks
Resolved code
Evidence record
Artifacts and frozen runs
Result artifacts
26-company outputs and movie artifacts
Run records
No run-level packet is registered. The family retains code-level provenance, but public run reproduction still requires curation.
Evidence boundary
The evidence supports a reproducible representation and diagnostics, not validated corporate-risk forecasts.
This registry links the experiments reported by the three books to their executable or archived code surfaces. A code link establishes traceability, not independent reproduction, correctness, or support for a claim beyond the experiment's stated boundary.