Fractal summaries
- Id
- fractal-summaries
- Status
- Active
- Severity
- medium
- Detection
- judge
- Evidence grade
- community-observed
- Languages
- en
- Added
- 2026-08-15
- Updated
- 2026-08-15
Currently signals low-effort writing.
What it is
Every paragraph closes by summarising itself, every section closes by summarising its paragraphs, and the document closes by summarising the sections. tropes.fyi names the pattern; vale-ai-tells carries the sentence-level markers that usually come with it. No study has measured it, and the evidence grade says so.
Why it reads as machine-made
A recap is cheap to produce and reads as thoroughness. Stacked at three levels it tells the reader the same thing three times at three sizes while the piece never moves. The cost is attention: the reader spends it on repetition instead of on the one paragraph that carried the new fact.
Specimens
The pilot ran in two offices for six weeks. Helsinki logged fewer support tickets and Tampere logged none. Support tickets fell in both offices. The rollout will cover four more offices, six weeks each. The rollout follows the same shape as the pilot. Both the pilot and the rollout point the same way.
The pilot ran in two offices for six weeks. Helsinki logged 40 percent fewer support tickets. Tampere logged none at all, which turned out to be a broken tagging rule rather than a result. The rollout reaches four more offices from 1 September, and the Tampere queue is being audited first.
The recap sentences carried no noun that was not already in the paragraph above them. The repair spends that space on the number and on the thing that went wrong. Figures in this repair are invented for the specimen.
How it is detected
- Rubric
- Scan the passage at three levels: the last sentence of each paragraph, the last paragraph of each section, and the last section of the document. For each, decide whether it introduces a noun, figure, date, name or commitment that does not already appear in the unit it closes. Count how many of the three levels close on nothing new. Escape hatches: instructional and training material that states a learning objective, standards documents that repeat so a reader can enter anywhere, and any recap carrying a number, a date or a next action, all of which count as new. Return the count of empty levels out of three, and quote the closing sentence you judged at each level.
Who writes this way legitimately
Textbook and training-material authors write per-section recaps because the pedagogy asks for them, and a course reader without them would be judged incomplete. Standards documents and safety manuals repeat at every level so that a reader entering in the middle still gets the whole instruction. Technical documentation does the same for people who skim. The discriminator is content, not position: a recap that carries a figure, a date or a next action is doing work, and one that renames what was just said is filling space.
Model attribution
Undocumented by vendor. The habit tracks length targets more than model family: a draft asked for a word count and given a short idea will spend the difference on recaps.
Status history
| Date | Status | Rationale |
|---|---|---|
| 2026-08-15 | Active | Named in two independent community rule sets and unmeasured anywhere. Nothing in the vendor record suggests it has been trained out, and the sentence-level markers that accompany it are still shipped as checkable rules. |
Sources
- 01tropes.fyi pattern directorycommunityaccessed 2026-08-14
- 02vale-ai-tells, 111 machine-checkable rulescommunityaccessed 2026-08-14
CC BY 4.0 / The AI Tells Index, feedsquad.com/ai-tells