$ styleprofile show '<tmp>/newer-minor.json'
[exit 0]
--- stdout
STYLE PROFILE   7 chunks, 4,496 words

                                                     typical   usual range

Sentences
  Average sentence length                         14.2 words   12.9 - 15.4 words
  Short sentences (8 words or fewer)                     41%   34% - 47%
  Long sentences (30+ words)                             12%   6.2% - 17%
  Sentence length variation (0 = uniform)               0.75   0.67 - 0.83
  Words per paragraph                             86.9 words   80.0 - 93.8 words
  One-sentence paragraphs                               0.0%   0.0% - 0.0%

Vocabulary
  Long words (7+ letters)                                11%   9.9% - 11%
  Vocabulary variety (MATTR, 0-1)                       0.72   0.70 - 0.75

Punctuation
  Commas                                            54.0 /1k   46.1 - 61.8 /1k
  Em dashes                                          0.0 /1k   0.0 - 0.0 /1k
  Parentheses                                        1.3 /1k   0.0 - 2.7 /1k
  Colons                                             1.6 /1k   0.7 - 2.5 /1k

Voice
  Contractions                                      34.6 /1k   26.6 - 42.5 /1k
  I / me / my                                       49.2 /1k   38.8 - 59.7 /1k
  You / your                                        18.5 /1k   13.2 - 23.8 /1k
  Hedges (maybe, I think)                            3.6 /1k   0.7 - 6.4 /1k
  Sentences starting However / Moreover                 0.0%   0.0% - 0.0%
  LLM marker words (delve, crucial)                  0.0 /1k   0.0 - 0.0 /1k

As a reference   held-out Delta 0.68 typically, 95% under 0.89 (7 documents)
  Shorter texts: calibrated at 75 words (124 pieces), 150 words (56 pieces); not at 300 words (28 pieces from 7
  documents, worth 18 independent ones), as a length needs 20 independent pieces from 3 or more documents. Under 75
  words, no verdict.

Contrast: LLM drafts   5 chunks from 5 documents; separates them from the reference with AUC 1.00 (perfect separation on
7 reference and 5 contrast documents)
  LLM-likeness on held-out text: reference 0.20 typically (95% under 0.82), LLM drafts 14.23
  Length alone: AUC 0.73 (reference 640 words per chunk, LLM drafts 624): some length difference
  Compared with the reference, LLM drafts have: Long words (7+ letters) ▲, List items ▲, Bold phrases ▲, Headings ▲

Pass --all to see every metric.
--- stderr
note: Newer minor report version; some fields may be ignored. Upgrade styleprofile.
