> For the complete documentation index, see [llms.txt](https://docs.thecolliery.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.thecolliery.org/benchmarks/coalledger/readme/results.md).

# Results

**Measured:**—*(corpus ready—awaiting first dated run)* · CoalLedger version:—· engines: —

> **TL;DR:** the org-level benchmark is not yet run—CoalLedger launched **unbenchmarked** rather than with an invented number. The corpus and scorer shipped first; this digest fills from the first dated record, never before.

| Suite                 | Fixtures | Decoys | Recall (mean ± range) | FP (mean) | Runs |
| --------------------- | -------- | ------ | --------------------- | --------- | ---- |
| doc-rot (27 planted)  | 5        | 2      | —                     | —         | —    |
| doc-leak (33 planted) | 4        | 2      | —                     | —         | —    |

**Current evidence (in-repo, not the org benchmark):** the mechanical AST layer is fixture-gated in the CoalLedger repo—**13/13 planted defects found, 0 findings on clean decoys** (anti-cry-wolf), Thai fixtures included—*fixture gate re-counted 2026-07-25 at v0.3.0-beta.1 (11 in `defects-structure.md` + 2 in `defects-thai.md`); re-derive with `node scripts/lib/md-checks.mjs` over `scripts/fixtures/`*. That gate proves the deterministic detector; the org benchmark below will measure per-canary RECALL on an independent foreign corpus (the canaries whose severity is context-judged, not mechanical, need the corpus, not a fixture).

**Honest scope:** a docs-health recall figure is corpus- and version-bound (each future record names both). Detection is deterministic (AST, not regex); severity is context-judged and never benchmarked as a fixed number.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.thecolliery.org/benchmarks/coalledger/readme/results.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.