A familiar author.
A better question.
Would this passage fit Jane Austen’s writing history?
Watch a simple style index try, and see exactly where it fails. Real public-domain excerpts from three authors, not pretend data.
A small, honest experiment. The text is real; the comparison is illustrative. No trained model, AI verdict, or academic credential is produced. The surprising result is the lesson: scroll to the scoreboard.
PUBLIC COLLECTIONS · V2Try the question for yourself.
Start with a known voice
The reference baseline
Three different books. One published author. Choose which excerpts contribute.
Bundled with this app. No student records or live source connection.
Choose a passage to compare
Known sources. Different scenarios.
Emma1815
Jane Austen·599 words·Original English
Emma Woodhouse, handsome, clever, and rich, with a comfortable home and happy disposition, seemed to unite some of the best blessings of existence; and had lived nearly twenty-one years in the world with very little to distress or vex her.
She was the youngest of the two daughters of a most affectionate, indulgent father; and had, in consequence of her sister’s marriage, been mistress of his house from a very early period. Her mother had died too long ago for her to have more than an indistinct remembrance of her caresses; and her place had been supplied by an excellent woman as governess, who had fallen little short of a mother in affection.
Sixteen years had Miss Taylor been in Mr. Woodhouse’s family, less as a governess than a friend, very fond of both daughters, but particularly of Emma. Between _them_ it was more the intimacy of sisters. Even before Miss Taylor had ceased to hold the nominal office of governess, the mildness of her temper had hardly allowed her to impose any restraint; and the shadow of authority being now long passed away, they had been living together as friend and friend very mutually attached, and Emma doing just what she liked; highly esteeming Miss Taylor’s judgment, but directed chiefly by her own.
The real evils, indeed, of Emma’s situation were the power of having rather too much her own way, and a disposition to think a little too well of herself; these were the disadvantages which threatened alloy to her many enjoyments. The danger, however, was at present so unperceived, that they did not by any means rank as misfortunes with her.
Sorrow came—a gentle sorrow—but not at all in the shape of any disagreeable consciousness.—Miss Taylor married. It was Miss Taylor’s loss which first brought grief. It was on the wedding-day of this beloved friend that Emma first sat in mournful thought of any continuance. The wedding over, and the bride-people gone, her father and herself were left to dine together, with no prospect of a third to cheer a long evening. Her father composed himself to sleep after dinner, as usual, and she had then only to sit and think of what she had lost.
The event had every promise of happiness for her friend. Mr. Weston was a man of unexceptionable character, easy fortune, suitable age, and pleasant manners; and there was some satisfaction in considering with what self-denying, generous friendship she had always wished and promoted the match; but it was a black morning’s work for her. The want of Miss Taylor would be felt every hour of every day. She recalled her past kindness—the kindness, the affection of sixteen years—how she had taught and how she had played with her from five years old—how she had devoted all her powers to attach and amuse her in health—and how nursed her through the various illnesses of childhood. A large debt of gratitude was owing here; but the intercourse of the last seven years, the equal footing and perfect unreserve which had soon followed Isabella’s marriage, on their being left to each other, was yet a dearer, tenderer recollection. She had been a friend and companion such as few possessed: intelligent, well-informed, useful, gentle, knowing all the ways of the family, interested in all its concerns, and peculiarly interested in herself, in every pleasure, every scheme of hers—one to whom she could speak every thought as it arose, and who had such an affection for her as could never find fault.
Look at the evidence. Keep the context.
Ready to inspect · Emma against 3 reference excerpts
Observable style index
A distance display. Not a probability.
A comparison, not a conclusion.
A closer style index means these six observable features sit nearer this small reference set. It is not the probability that Jane Austen wrote the passage, and it does not determine whether AI was involved.
Published attribution: Jane Austen. This is documented source metadata, not a finding from the score.
Now look at all four together.
Every passage scored against the same 3 Jane Austen reference excerpts. This is the part worth remembering.
Mary Shelley scores at least as close to Jane Austen as Jane Austen’s own held-out Emma. Six surface features cannot tell two authors of the same era apart. This is exactly why no production decision in the AuthWords design rests on a style score alone: style is context, and supervised, attributable writing is the evidence.
The AI fixture looks further away mostly because it is modern English. Its largest normalized difference is word length (3.56), a signal about vocabulary and era, not about who or what wrote it. A model prompted to imitate Jane Austen would close that gap.
Across all three collections, the real author beats the control in 1 of 3 (John Stuart Mill by 8). Switch collections above and watch the same six features succeed and fail for no principled reason. Different is not dishonest, and similar is not proof. Read how the design answers this in Why not detection? and Flip the assignment.
Context, without assumptions.
Usable metadata. Honest gaps.
- Birthplace Documented
- Steventon, Hampshire, England Biographical context, not a demographic prior.
- Historical period Documented
- 1775–1817 Publication dates are not a learning trajectory.
- ESL history Unknown
- Not documented Never inferred from a name or birthplace.
- Language proficiency Unknown
- Not assessed No CEFR level or growth curve is fabricated.
- Student cohort Not available
- Not a student dataset No demographic fairness claim can be made.
Small on purpose. Open to inspection.
What you’re evaluating—and what you aren’t.
This demo replaces anonymous placeholder prose with three tiny, reproducible reference collections: a novelist, a philosopher, and a naturalist, each paired with a real other-author control. It demonstrates the product’s question—not the accuracy of a production model.
How is the number calculated?
Compare equal leading windows of up to 250 words across the chosen excerpts. Measure six signals, take their reference means and variances, and average normalized absolute differences.
index = round(100 / (1 + mean distance))Fixed scale floors reduce instability. The formula and floors are included in result exports. They are engineering choices, not statistically fitted thresholds. No semantics model, Bayesian calibration, or demographic classifier runs here.
What can this collection not tell us?
- Six historical English-language authors in three pairs; not a representative demographic sample.
- Three baseline passages from three books cannot estimate a calibrated posterior or prove authorship.
- Each other-human control changes genre or register as well as author; this is a confound, not a clean accuracy benchmark.
- Historical publication years are not a measured student learning trajectory.
- A language model may have encountered these public books during training; this is not a contamination-free AI benchmark.
- One synthetic output per collection cannot establish AI-detection accuracy. Similarity can be high for another author or low for the same author.
No index triggers a credential or misconduct decision.
Why these authors?
Austen, Mill, Darwin, Shelley, James, and Wallace all wrote in English and their selected works have clear U.S. public-domain source records, so the excerpts are original text rather than translations. A novelist, a philosopher, and a naturalist also give the index three different registers to fail in different ways.
We do not assume a modern author’s works are public domain, and a translated philosopher such as Frege would need separate rights and language checks for the specific edition. The snippets exclude introductions, footnotes, illustrations, and license boilerplate. Check local copyright law outside the United States.
Different is not dishonest. A student’s language, learning, genre, and permitted tools belong in the context—not in an accusation.
Why we flipped the question