Revelation First
Revelation First meta-aggregator / AI and ancient texts

Revelation First ≠ Revelation Early. The pre-70 date is the old argument (Robinson, 1976; Gentry, 1989); Revelation First is the priority thesis: the rest of the New Testament unfolds from the Apocalypse.

Ithaca

AI and ancient textsa deep neural network for restoringactive
Ithaca: a deep neural network for restoring, placing and dating ancient Greek inscriptions. Operator: DeepMind with historians and collaborators; described in Nature (2022). Its unit: an inscription's restored text, attributed place and attributed date. Its texts: ancient Greek inscriptions.
Visit Ithaca ↗Its NonWiki articleThe thesis

What it records

IntersectionsAI and ancient texts: machine reading, restoration and dating
Kind of evidencemachine reading, restoration or dating
Unit of recordan inscription's restored text, attributed place and attributed date
Which textsancient Greek inscriptions
Methoddeep neural network trained on Greek inscriptions; evaluated alone and with historians
Coveragegeography: the ancient Greek world; period: as its training corpus (not stated in the abstract)
What it finds62% accuracy restoring damaged texts alone; historians' accuracy rose from 25% to 72% with it; 71% accuracy attributing location; dates within 30 years of ground-truth ranges, redating key texts of Classical Athens
Its stated limitsdesigned to assist and expand the historian's workflow

op the resource's own statement · 3p a third-party account · obs our observation · rd our reading. Hover a tag for its quote; each opens below with its source.

What this evidence can settle

Can answer

  • how accurately a model restores, places and dates Greek inscriptions, and how much it helps historians

Cannot answer

  • the dating of manuscripts or literary works
  • anything on the New Testament

In the worked questions

Where it meets Revelation First

rd Machine dating of Greek text: inscriptions, not manuscripts. A method the dating workstream can watch; it bears on the thesis only as machine dating moves toward literary and papyrus evidence.

Entity

Canonical nameIthaca
Also known asIthaca (DeepMind)
Addresshttps://ithaca.deepmind.com/
OperatorDeepMind with historians and collaborators; described in Nature (2022)
Founded2022
Kinda deep neural network for restoring, placing and dating ancient Greek inscriptions
Lifecycleactive — published 2022; interface online
Count78,608 inscriptions in I.PHI, the training dataset (as of 2026-10-31)
Data accessan interactive interface (the saved page is a JavaScript application); the paper is open in Nature
Licencecode Apache License 2.0; trained weights CC BY-SA 4.0 (the paper's statement)
Versions and datesread: 2026-10-30
Observation2026-10-30: read

Relations

Neighbours

Captures: the composition layer's account

NonWiki: the article, sourced

Evidenceevery field's quote, its source and the hash of the saved copy6
  • dataset op
    containing 78,608 inscriptions.
    https://www.nature.com/articles/s41586-022-04448-z · read 2026-10-31 · saved copy sha256 d2b4df37a93252c3…
  • licence op
    under Apache License 2.0, along with the trained weights, licensed under Creative Commons Attribution-ShareAlike 4.0 International.
    https://www.nature.com/articles/s41586-022-04448-z · read 2026-10-31 · saved copy sha256 d2b4df37a93252c3…
  • what op
    Here we present Ithaca, a deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions.
    https://www.nature.com/articles/s41586-022-04448-z · read 2026-10-31 · saved copy sha256 d2b4df37a93252c3…
  • assist op
    Ithaca is designed to assist and expand the historian’s workflow.
    https://www.nature.com/articles/s41586-022-04448-z · read 2026-10-31 · saved copy sha256 d2b4df37a93252c3…
  • restore op
    While Ithaca alone achieves 62% accuracy when restoring damaged texts, the use of Ithaca by historians improved their accuracy from 25% to 72%, confirming the synergistic effect of this research tool.
    https://www.nature.com/articles/s41586-022-04448-z · read 2026-10-31 · saved copy sha256 d2b4df37a93252c3…
  • date op
    Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history.
    https://www.nature.com/articles/s41586-022-04448-z · read 2026-10-31 · saved copy sha256 d2b4df37a93252c3…
Negative tagswhat it is not2
  • NOT a manuscript-dating model
  • NOT a New Testament resource
Sourcesevery source read, with its date and hash1
Not yet checkedwhat remains to read1
  • the interface (JavaScript)

Cite this record

Lee Sharks, ed. "Ithaca." Revelation First meta-aggregator, revelationfirst.com, compiled 2026-10-30. https://www.revelationfirst.com/aggregators/ithaca/

Record https://www.revelationfirst.com/aggregators/ithaca/ · entity https://www.revelationfirst.com/aggregators/ithaca/#entity · the census as data

@misc{rf-ithaca2026,
  editor = {Sharks, Lee},
  title = {Ithaca},
  howpublished = {Revelation First meta-aggregator, revelationfirst.com},
  year = {2026},
  note = {Compiled 2026-10-30; every field sourced and dated},
  url = {https://www.revelationfirst.com/aggregators/ithaca/}
}
Editor: Lee Sharks (ORCID 0009-0000-1599-0703). This page is the Revelation First meta-aggregator's record of the resource above: its reading and fields are ours, and each field carries its source, its basis and the hash of the copy read. The resource's own terms and findings are kept as its own. Compiled 2026-10-30. CC BY 4.0.