The “it’s not X, it’s Y” reframe, quantified
We tagged 4,000 sentences. The reframe shows up once every 340 words of model output — and almost never in human drafts.
ciopinno··1 min read
The negative-parallelism reframe is the pattern people notice before they can name it. We measured it.
Method
- Corpus: 4,000 sentences, half model-written, half human.
- Tagger: regex + a classifier for the "not A, but B" shape.
Result
| Source | Reframes / 1000 words |
|---|---|
| GPT-5 | 3.1 |
| Claude | 2.4 |
| Human | 0.3 |
Models use it ~10x more than people. That ratio is why it reads as synthetic.