mptyl/ThothII
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

docs: separate public manual from internal project documentation
Publish documentation / publish (push) Successful in 27s
Details

Browse Source
This commit is contained in:
Codex
2026-09-15 10:26:35 +02:00
parent 6a4634dcf1
commit 043ffdfad6
26 changed files with 859 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/operations/sensitivity-analysis.md
+6 -11
View File
@@ -118,12 +118,12 @@ other CPU workloads.
Run the first evaluation in shadow mode: read the source with its existing read-only role, do not
save proposed flags, and report only aggregate counts, rule IDs, coverage, and timings. Never copy
matched values into test output. Use a separately approved, labeled Italian corpus to calculate
precision and recall; raw PSD values must remain inside the authorized environment.
precision and recall; source values must remain inside the authorized environment.
Inside the configured core runtime, the non-mutating command is:
```bash
npm run sensitivity:shadow -- psd-clinical
npm run sensitivity:shadow -- <workspace-id>
```
It reads catalog metadata and source values but emits one aggregate JSON object with no database,
@@ -139,12 +139,7 @@ Enabling NER by default requires all of these gates:
If a gate fails, leave NER disabled. The deterministic policy remains available and produces the
binary draft from its scan coverage; no content is sent to an internal or external LLM.
The first aggregate PSD shadow comparison is recorded in
[`2026-09-02-psd-sensitivity-shadow.md`](../reports/2026-09-02-psd-sensitivity-shadow.md). On the
local CPU runner, NER found additional entities but reduced total coverage under the superseded
global deadline. The v2 benchmark removed that confounder: CPU NER added 18 sensitive proposals and
increased the warm analysis time from 50.1 to 61.3 seconds. It remains opt-in until a labeled Italian
evaluation establishes that the additional findings justify their false-positive rate and cost.
The deterministic progressive PSD run is recorded in
[`2026-09-03-psd-progressive-sensitivity-shadow.md`](../reports/2026-09-03-psd-progressive-sensitivity-shadow.md):
both deterministic and CPU-NER profiles assessed all 2,275 columns with zero `unknown` decisions.
Benchmarks from a particular installation are not a guarantee for another database or machine.
NER remains opt-in until an approved evaluation establishes that additional findings justify
their false-positive rate and operational cost. Keep benchmark and release records with the
installation's technical evidence, separate from this operator procedure.