skills.rest
arslan9024
arslan9024COMMUNITY
Explore all skills by this author →
GitHub

predictingthepast

Restore, attribute, date, and contextualize ancient Latin and Greek inscriptions using Aeneas and Ithaca models.

Updated Jan 8, 2026
Search Tags:#epigraphy#inscriptions#latin#ancient greek#aeneas#text restoration#ithaca
One-click install
npx skills add https://github.com/arslan9024/White-Caves --skill predictingthepast-arslan9024
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: predictingthepast
Source: https://github.com/arslan9024/White-Caves/tree/main/.agents/skills/predictingthepast
Command: npx skills add https://github.com/arslan9024/White-Caves --skill predictingthepast-arslan9024

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jax, predictingthepast, and includes scripts (resource) and references (resource) components.

What problem does it solve? Damaged ancient inscriptions are difficult to restore, date, and locate geographically without deep epigraphic expertise. This Skill runs Google DeepMind's Aeneas (Latin) and Ithaca (Ancient Greek) neural models locally to restore missing characters, predict geographical and chronological origins, retrieve parallel inscriptions, and generate text embeddings. ## Core Features & Use Cases - Text Restoration: Fill known-length gaps (?) and unknown-length gaps (#) in damaged inscriptions using beam search with configurable width, temperature, and max length. - Attribution & Dating: Predict the top geographical regions and most probable year (BCE/CE) for an inscription, with saliency analysis and multi-window averaging for texts over 750 characters. - Contextualization & Embedding: Retrieve top-K parallel inscriptions with full texts, Trismegistos IDs, and similarity scores, plus optional 384-dimension embedding vectors. - Use Case: A researcher has a fragmentary Latin inscription like donat in ??????????rtis. The Skill preprocesses the text, runs restoration and attribution, and produces an HTML dashboard showing the top restoration templum martis, a Britannia origin prediction, and a date around 295 CE. ## Quick Start Ask the assistant to restore and date your ancient inscription, providing the text with ? markers for each missing character, for example: restore and attribute the Latin text "donat in ??????????rtis".

Frequently Asked Questions about predictingthepast

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I restore missing characters in a Latin inscription?▼

Mark each missing character with `?` for known-length gaps or `#` for unknown-length gaps, then run inference with the --restore flag. The model returns beam-search candidates ranked by score, with the top prediction's restored characters highlighted.

What is the difference between Aeneas and Ithaca models?▼

Aeneas processes Latin inscriptions while Ithaca handles Ancient Greek; both perform restoration, attribution, contextualization, and embedding. Select the model with the --language flag set to latin or greek.

Can Ithaca or Aeneas handle texts longer than 750 characters?▼

Yes, texts over 750 characters are automatically split into overlapping windows with a default 33% overlap. Attribution scores are averaged across windows while restoration and contextualization run per window, though processing becomes significantly slower.

Why does ancient text restoration take so long?▼

Restoration time scales roughly linearly at about 10 seconds per `?` character on a high-end CPU, so 20 gaps take around 5 minutes. Reduce the number of markers, lower --restore_max_len, or restore section by section to speed it up.

What are the input requirements for inscription analysis?▼

Input must be at least 25 characters after preprocessing (pad with `-` if shorter), contain no consecutive `##` or adjacent `?#` markers, and use only the valid Latin or Greek alphabet. Preprocessing strips accents, brackets, punctuation, and converts numerals to 0.

Related Skills

Explore More Education & Research Skills→
google-deepmindgoogle-deepmind
2.8k

predictingthepast

Restore, attribute, date, and contextualize ancient Latin and Greek inscriptions using Aeneas and Ithaca models.

Official
Advanced
xlinh2301xlinh2301

predictingthepast

Restore, attribute, date, and contextualize ancient Latin and Greek inscriptions using Aeneas and Ithaca models.

Community
Advanced
k1064190k1064190
2

prediction-review

Review open predictions and analyze track record accuracy for calibration adjustments.

Community
Intermediate
hgxszhjhgxszhj

ubiquitous-language

Extract domain terms from conversations into a UBIQUITOUS_LANGUAGE.md glossary.

Community
Advanced