Em dashes and curly marks in two corpora
Published ; updated
Em dashes and curly quotation marks are often presented as evidence of machine writing. We counted both in collected Claude output and in five nineteenth-century novels. In this comparison, the novels used both far more often.
Counts
We compared 457,045 characters from four Claude model assignments with 3,059,329 characters from Austen, Carroll, Melville, Twain and Shelley. The novels came from raw Project Gutenberg files. The Claude files were written straight to disk, without a chat interface changing their punctuation.
Scroll horizontally to see all columns
| Corpus | Characters | Curly quote and apostrophe characters | Em dashes |
|---|---|---|---|
| Collected Claude output | 457,045 | 0 | 37 |
| Five nineteenth-century novels | 3,059,329 | 20,224 | 3,055 |
Across 120 Claude files, we found no curly quotation marks or apostrophes. The files used straight marks instead. Em dashes appeared at about 0.08 per thousand characters. The novels contained about 6.6 curly marks and one em dash per thousand characters, so their em-dash rate was roughly twelve times higher.
These figures describe the files we examined. They do not establish a general punctuation rate for people or models.
Dialogue
The novels contain much more dialogue than the full prompt set, which also includes code, JSON, lists and technical prose. A second, rough comparison put the three dialogue prompts against all five novels and counted curly marks and em dashes together. The gap narrowed, but each model rate was still about 5.5 to 23.4 times lower. The genres are closer, not matched, so treat this as a check on the first count rather than a separate result.
The em dashes are concentrated. Thirty-six of the 37 occur in dialogue prompts and mark interrupted speech. One occurs in an informal post. None appears in the factual prose, lists, code or JSON. The punctuation followed the writing task.
Editing
The Project Gutenberg files are modern edited transcriptions of older books. They contain typographic quotation marks, but do not reveal which marks came from the original edition and which came from later editorial work.
Modern text can change after drafting too. A word processor can curl quotation marks. A person, model, editor or style rule can add an em dash. Our Claude files did not pass through a word processor or publishing system before the scan. Later changes to the punctuation would tell us about that edit, not who drafted the words.
Authorship
An em dash or curly quote tells you only that a writer, editor or piece of software used it. It does not reconstruct how the text was made.
Anthropic says that even finding its own supported watermark is not conclusive. Its technical post describes a keyed SynthID-Text system based on word choices, not a style checklist. Punctuation has no published key, calibrated cut-off or stated error rate. A decision about a person should not rest on the tidiness of their typography.
Characters
To find out which characters are present, inspect their Unicode code points. The result will show whether an apostrophe is straight or curly, whether text contains a zero-width character and where it occurs.
A character inventory cannot tell you who wrote the words, what they checked or what changed between drafts. You need to record those facts while you work.
Read the full byte-level scan, or try the four watermark steps.