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

• URL: http://arxiv.org/abs/2608.07249v1
• Date: Fri, 07 Aug 2026 14:07:43 GMT
• Title: Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion
• Abstract summary: Stoicheia is a character-level masked-diffusion encoder for Ancient Greek.<n>We pretrain it on an open, revision-pinned corpus of 380M words and release eleven checkpoints.<n>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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation [25.91174070621304]
  Glyph-level obfuscation can leave harmful Chinese content readable to humans while degrading automated moderation.<n>We introduce SinoGlyphBench, a diagnostic benchmark that identifies label-critical semantic anchors and creates matched original and glyph-obfuscated inputs.
  arXiv  Detail & Related papers  (2026-09-05T03:15:49Z)
• Contextual Tamil Spelling and Grammar Correction Using Progressively Fine-Tuned Sequence-to-Sequence Transformers [0.14658400971135652]
  Tamil is an agglutinative low-resource language with rich verbal morphology, complex sandhi rules at word boundaries, and 247 distinct letters.<n>We propose an end-to-end sequence-to-sequence formulation and fine-tune mT5-small and mBART-50 on a synthetic corpus of up to 657,720 noisy-clean Tamil sentence pairs.<n>Our best model, mBART-50 v5, reaches 69.3% top-1 exact-match accuracy, with 87.5% on sandhi and 43.5% on subject-verb agreement.
  arXiv  Detail & Related papers  (2026-09-03T02:02:39Z)
• VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement [57.86962208273888]
  We present an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations.<n>Each action returns a provenance-carrying evidence record whose payload, when usable, is either a typed measurement or an explicitly tagged learned state.<n>We anchor evaluation in a 1,500-clip corpus of human-annotated flaw records that localize real generation failures in prompt reference, space, and time.
  arXiv  Detail & Related papers  (2026-09-02T20:36:45Z)
• Unadapted Multilingual ASR on a Garrusi Kurdish Evaluation Set: A Common-Reference Staged Normalization Analysis [0.0]
  I evaluate speech recognition for a Kurdish variety written in a Latin field orthography.<n>The raw Arabic-script hypothesis scores 111.70% WER and 100.92% CER, with zero exact word matches.<n>Latin transliteration gives 102.36% WER and 57.89% CER; folding it into the reference's reduced orthography gives 97.85% and 51.20%.
  arXiv  Detail & Related papers  (2026-08-17T10:31:30Z)
• IndicQE-APE: A Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages [77.88427845181154]
  We consolidate the WMT 2020--2024 shared-task lineage with an extended English--Malayalam resource into indicqe: $126,754$ instances over nine directional pairs.<n>We benchmark six prompted LLMs and three COMET metrics on segment-level QE, and three systems on APE.
  arXiv  Detail & Related papers  (2026-08-17T09:50:52Z)
• Morphology Aware Reversible Semantic Tokenization and Hierarchical Word Composition for Tamil Language Models [0.0]
  We present a Tamil morphology system extending the open-source ThamizhiMorph analyzer and generator.<n>We compare a flat morphology tokenizer, a signal-preserving word composer, and tokenizers based on Sarvam-1, AI4Bharat IndicBERTv2, and BrahmicTokenizer-131K.<n> explicit Tamil morphology improves translation under a fixed small-model budget, while hierarchical composition substantially reduces sequence length and estimated inference cost.
  arXiv  Detail & Related papers  (2026-08-02T11:07:53Z)
• Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories [3.694051864521789]
  We recast fine-grained intertextuality extraction as an agentic task in which a large language model reads two text units in full.<n>We validate the approach on an exhaustive comparison of the Analects with the Book of Han, where three domain experts adjudicate a pooled multi-model candidate set into a benchmark of 2,533 intertextual pairs.
  arXiv  Detail & Related papers  (2026-07-30T02:34:23Z)
• AI_LectureNote: A Retrospective Pilot Study of a Post-ASR Workflow for English-Script Rendering and Semantic Drift in Korean-English Medical Lectures [1.7028841264419619]
  AI_LectureNote is a readability-oriented post-ASR workflow for Korean-English medical lectures.<n>It rewrites speech-to-text output into study transcripts while restoring Latin-script medical terms.
  arXiv  Detail & Related papers  (2026-07-19T13:02:07Z)
• Context-Aware Distillation and Ablation for Text2DSL [78.29352305480285]
  We replace prompt-only synthetic generation with context-aware distillation.<n>A teacher large language model operates under an explicitly defined structured context.<n>This scales the verified PolkitBench corpus from 4,204 to 10,073 pairs.
  arXiv  Detail & Related papers  (2026-06-21T16:27:24Z)
• Output Vector Editing for Memorization Mitigation in Large Language Models [68.30351930772788]
  Large language models memorize and reproduce sequences from their training data, creating privacy, copyright, and security risks.<n>Existing neuron-level mitigation methods equate editing with zeroing out neuron activations, but the activation only controls whether a neuron engages.<n>We propose output vector editing, a constrained-optimization edit that locates a small set of neurons responsible for a memorized continuation.
  arXiv  Detail & Related papers  (2026-06-17T07:29:18Z)
• Benchmarking Speech-to-Speech Translation Models [55.00303727199927]
  Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol.<n>We introduce a benchmarking framework integrating 46 metrics across eight dimensions.<n>We deploy it on 1,248 model-language configurations from FLEURS and CVSS.
  arXiv  Detail & Related papers  (2026-06-02T07:01:33Z)
• The Digital Afterlife of Empires: Four Language Models Converge on the Same Imperial Cartography of Writing [0.0]
  Large language models process the world's writing systems with radical inequality.<n>Only 29 scripts (9.7%) are fully supported by contemporary digital infrastructure; among 158 living scripts, 60 (38.0%) lack complete support.<n> Tokenizer efficiency varies by a factor of 31.7 across 45 scripts measured with parallel text.
  arXiv  Detail & Related papers  (2026-04-30T07:02:45Z)
• The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions [0.0]
  We present the Patrologia Graeca Corpus, the first large-scale open OCR and linguistic resource for nineteenthcentury editions of Ancient Greek.<n>The collection covers the remaining undigitized volumes of the Patrologia Graeca (PG), printed in complex bilingual (Greek-Latin) layouts and characterized by highly degraded polytonic Greek typography.<n>We achieve a character error rate (CER) of 1.05% and a word error rate (WER) of 4.69%, largely outperforming existing OCR systems for polytonic Greek.<n>The resulting corpus contains around six million lemmatized and part-of-speech tagged tokens, aligned with full
  arXiv  Detail & Related papers  (2026-03-10T10:21:54Z)
• Look-back Decoding for Open-Ended Text Generation [62.53302138266465]
  We propose Look-back, an improved decoding algorithm that tracks the distribution distance between current and historical decoding steps. Look-back can automatically predict potential repetitive phrase and topic drift, and remove tokens that may cause the failure modes. We perform decoding experiments on document continuation and story generation, and demonstrate that Look-back is able to generate more fluent and coherent text.
  arXiv  Detail & Related papers  (2023-05-22T20:42:37Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.