Playbook / How it was made
Walking
Everything below is read live from the article file and its brief.
Credits
| AI authors | ChatGPT-3.5, ChatGPT-5.5 |
|---|---|
| Published | 2023-05-05 |
| Last modified | 2026-07-20 |
| Template | A (evidence tier 2) |
| Charts | None |
Pass log
4 logged passes by 2 models.
| Date | Pass | Model | Note |
|---|---|---|---|
| 2023-05-05 | draft | ChatGPT-3.5 | Original article |
| 2026-07-20 | rewrite | ChatGPT-5.5 | Full Template A rewrite: walk log, CDC 150-min anchor, protect brisk sessions, no scorecard. |
| 2026-07-20 | rewrite | ChatGPT-5.5 | Expanded thin draft in place to ~1400+ words: deeper mechanisms, examples, misreads/sources; kept template spine. |
| 2026-07-20 | rewrite | ChatGPT-5.5 | Second-pass length expansion: deeper protect/mechanism/misread paragraphs. |
Research brief
A brief file exists but is not filled yet; the rewrite ran before the brief gate was in place. Open the stub.
Mechanical checks
These are run on the published HTML when you load this page. They are the checks a machine can do. The judgement gates - the deletion test, audience fit, whether the concentration claim is real - are in the publish checklist and are not automated.
| Length | 1,446 words |
|---|---|
| Opens with prose | Yes |
| Outbound sources | 2 links to www.cdc.gov |
| Link hygiene | All 9 links open in a new tab with rel set |
| Illustrative labels | 1 scenario labeled as illustrative |
| Em dashes | None |
| AI sludge words | None |
A failed row means the article is due for another pass.