Published result

Shaping readiness on a fixed request set

A plain-language summary comes first, followed by the full text of the result's reproduction pack.

Result summary and pack text · reproduce/lab-shaping-climb-round0-20261107/README.md

In plain terms

A shape-only baseline reached readiness without questions on 9 of 21 requests. No change was evaluated.

Verdict key: Yes, The result supports the change or claim that was tested. No, The result does not support it, so nothing changes. Unresolved, The evidence is not strong enough either way. Superseded, A later test replaced this result.

Full text of the reproduction pack

The text below is the pack's README as published in the repository (a system folder name may show without its leading slash, so that the site's privacy scan passes).

A shape-only baseline reached a ready Intent without a question on 9 of 21 requests: 9 of 15 small requests and 0 of 6 complex requests. This is a baseline, not evidence of an improvement. Eight results ended as not ready, two as invalid output, and two with questions. The complex request text is private; the data preserves outcomes without it.

The run used Sol at low effort with no answerer and the release built from Kogen source. Each request was run once. A result is ready only when it reached readiness with no questions or refusals. No Build or hidden evaluation was run. Small Go and Node workspaces were reconstructed from the earlier study description; byte identity with the original workspaces is unverified. Account-wide credit readings did not move visibly, but do not establish attributable spend. The cell data records elapsed time, including failed attempts.

Rerun

Run python3 report.py to recompute the published counts from the included results. To repeat the model study, use the linked release, the registered request set and equivalent workspaces, run one shape per request with the same model and effort and no answerer, and record readiness, questions and refusals. Private requests require authorized access.