Experimental contract
What this family tests
four registered simulation families
- E1 calibration and power
- E2 opposite-stratum localization
- E3 relational preference game
- E4 incomplete-support and abstention
Book-to-code crosswalk
The highlighted Experiment cards covered here
- Experiment: LINCS-RLHF controlled preference suite16.7 What the experiments establish · 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 —
lincs-rlhf:scripts/run_smoke.sh↗Open the pinned public source file. - runner · public-pinned —
lincs-rlhf:scripts/run_full.sh↗Open the pinned public source file. - runner · public-pinned —
lincs-rlhf:scripts/build_manifest.py↗Open the pinned public source file.
Author-declared entry points
scripts/run_smoke.shscripts/run_full.sh
Resolved code
Evidence record
Artifacts and frozen runs
Result artifacts
E1–E4 registered result grids
Run records
No run-level packet is registered. The family retains code-level provenance, but public run reproduction still requires curation.
Evidence boundary
Oracle population quantities are evaluation-only and do not characterize deployed preference learning.
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.