Metraipolis › archive › dc_4f4e59dcdf8e

Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion — arXiv:2608.07249

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07249
License (as archived)
CC0-1.0
Archived
2026-10-19T09:46:57.317Z
SHA-256 of the archived text
bd2e384b14d149442ce7b905d0ff1123bc40120777636ed2f1860872e7b553f4
Stable URL of this page
https://metraipolis.com/documento/dc_4f4e59dcdf8e

How to cite

Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion — arXiv:2608.07249 — arXiv (en), https://arxiv.org/abs/2608.07249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f4e59dcdf8e (Metraipolis archive dc_4f4e59dcdf8e, sha256 bd2e384b14d149442ce7b905d0ff1123bc40120777636ed2f1860872e7b553f4)
BibTeX
@misc{dc4f4e59dcdf8e,
  title = {Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion — arXiv:2608.07249},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07249},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f4e59dcdf8e; sha256 bd2e384b14d149442ce7b905d0ff1123bc40120777636ed2f1860872e7b553f4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Stoicheia, a 405M-parameter character-level masked-diffusion encoder for Ancient Greek whose input factors into five aligned, independently maskable planes: letters, word and sentence boundaries, diacritics, capitalization, and punctuation. A single backbone can therefore restore lacunae, re-segment, accentuate, and punctuate unspaced text without task-specific retokenization. We pretrain it on an open, revision-pinned corpus of 380M words and release eleven checkpoints: ten rotated, decontaminated folds, guaranteeing that for any given literary passage at least one released model has never seen its text, and one with no exposure to documentary texts. Three experiments - reconstruction of damaged inscriptions and papyri, morphosyntactic tagging and dependency parsing, and macronization with metrical scansion - each carry a matched random-initialization control, isolating what character-level diffusion pretraining contributes: 5.6 CER points on inscription reconstruction, 12.9 LAS on parsing, and 6.0 points of balanced accuracy on macronization. On Ithaca's own test split, with identical frozen samples and strict scoring, Stoicheia reduces character error relative to both prior state-of-the-art systems, from 24.6 (Ithaca) and 23.5 (its 2025 Aeneas-framework successor) to 15.5, and raises top-1 accuracy from 63.0 and 64.0 to 74.5.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.07249 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:46:37.240Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).