Dating models: when does a passage's English date from?
Classifiers that date English prose to a 1473-1830 bin (Amendments 17, 19, 29): models.joblib
holds the grammar model (61 grammatical features; decides H3) and the lexical model,
transformer.joblib the cross-check on the 297M time-locked model's hidden states. Load with
joblib.load and use with dating.classifier in the GitHub repository. Validation
(validation.json, transformer_validation.json): held-out mean error 23 years (grammar),
13 (lexical), 10.1 (transformer).
What they said about the Book of Mormon: the grammar model places most of the text before
1700 (median 1661); the lexical model's median is 1736 and the transformer's 1755. Writing in
imitation of the King James Bible pulls the grammar model about 53 years early, but the text
still dates earlier than the period's other imitation scripture (data/blind/unblinded.json,
data/dating/h3c.json in the GitHub repository).
The study and what it found
This is one of the models from a finished, open study of the English text of the Book of Mormon: who writes like it, what it borrows, and when its language dates from.
- The findings in plain words, with live charts: https://lifehug.com/book-of-mormon
- The paper, the code and every results file: https://github.com/lifehug/book-of-mormon-authorship
In short: the book copies almost nothing from earlier print. Among the eight people usually proposed as its author, the closest writing is Joseph Smith's revelations, and a search of 23,872 authors of the period puts those revelations first or second. No tool we found, ours included, can tell a person from the voice they are writing in, or reliably say "it is none of these people". The study takes no position on inspiration.
About
Part of an open, pre-registered study of the authorship, borrowing and dating of the
earliest Book of Mormon text (https://github.com/lifehug/book-of-mormon-authorship; pre-registration https://osf.io/6ugxc/). The project does not argue for or
against divine inspiration. Everything is published so it can be checked and redone; the corpus
texts we agreed to keep private are not, and the repository's docs/replication.md gives the
steps to obtain the same access.
Licence: CC BY-NC 4.0. Training data: English printed 1780-1830 (Internet Archive, Harvard
Institutional Books 1.0, HathiTrust public-domain volumes, Text Creation Partnership), with the
Book of Mormon and everything after 1830 removed; see the base model cards
(etherfuse/timelocked-1830-125m). Contains derivatives of Harvard Institutional Books 1.0,
Institutional Data Initiative, Harvard Law School Library; used for noncommercial research.
Checksums: every file's SHA-256 is in the GitHub repository, data/manifests/hf_<repo>.jsonl.