SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.06262 · 2019

Restoring ancient text using deep learning: a case study on Greek epigraphy

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1910.06262.json · badge: /api/ran/1910.06262.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
sommerschield/ancient-text-restoration canonical (classifier label)
classifier basis: census
4 ran · 5 no recorded run
FunctionStatusWhere it lives
idx_to_text Ran
ran on a synthesized input
sommerschield/ancient-text-restoration/pythia/util/vocab.py
code served (permissive licence) · get_code("92f3c297fa4bc0c9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

class Alphabet:
    def __init__(self):
        self.eos_idx = 5
        self.sos_idx = 0
        self.idx2char = {
            1: 'a',
            2: 'b',
            3: 'c',
            4: 'd',
            5: '<eos>',
            0: '<sos>'
        }

idxs = np.array([1, 2, 3, 4, 5])
alphabet = Alphabet()

ARGS = {
    'idxs': idxs,
    'alphabet': alphabet
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
strip_accents Ran
ran; our contract draft was wrong, not the code
sommerschield/ancient-text-restoration/pythia/util/text_clean.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from emeryberger/CSrankings, is pointer only (licence: NOASSERTION) · get_code("b34f5dfa407987e8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from emeryberger/CSrankings, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

text_clean_phi Ran
ran on a synthesized input
sommerschield/ancient-text-restoration/pythia/util/text_clean.py
code served (permissive licence) · get_code("c202065a5f0872be")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

class Alphabet:
    def __init__(self):
        self.alphabet = list('abcdefghijklmnopqrstuvwxyz')
        self.numerals = list('0123456789')
        self.punctuation = ['.', ',', '!', '?', ';', ':']
        self.space = ' '
        self.missing = '—'
        self.sog = '<'
        self.eog = '>'
    
    def filter(self, text):
        """Filter text to keep only valid characters"""
        valid_chars = set(self.alphabet + self.numerals + self.punctuation + [self.space, self.missing, self.sog, self.eog])
        return ''.join(c if c in valid_chars else ' ' for c in text)

alphabet = Alphabet()

sample_text = """
This is a test [Greek numerals ∶ΠT].
Some text with dashes-
and line breaks.
v1.2 some versioned text v2.0
(annotation text here)
<tagged content>
[MMMCMXCIX] end of roman numeral
"""

ARGS = {
    'text_cleaned': sample_text,
    'alphabet': alphabet
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
text_to_idx Ran
ran on a synthesized input
sommerschield/ancient-text-restoration/pythia/util/vocab.py
code served (permissive licence) · get_code("bbfa59c68f3512e4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family int, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

class Alphabet:
    def __init__(self):
        self.char2idx = {
            'a': 0,
            'b': 1,
            'c': 2,
            'd': 3,
            'e': 4,
            'f': 5,
            'g': 6,
            'h': 7,
            'i': 8,
            'j': 9,
            'k': 10,
            'l': 11,
            'm': 12,
            'n': 13,
            'o': 14,
            'p': 15,
            ' ': 16,
        }

alphabet = Alphabet()
text = "hello"

ARGS = {
    't': text,
    'alphabet': alphabet,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (5,) — shape (5,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_graph Not yet run
unverified (harvested, no recorded run)
sommerschield/ancient-text-restoration/pythia/model/graph.py
code served (permissive licence) · get_code("dcd412c5340b7001")
How it ran

no invocation recorded.

error Not yet run
unverified (harvested, no recorded run)
sommerschield/ancient-text-restoration/pythia/model/loss.py
code served (permissive licence) · get_code("1da3e2dd45219cde")
How it ran

no invocation recorded.

loss_seq2seq Not yet run
unverified (harvested, no recorded run)
sommerschield/ancient-text-restoration/pythia/model/loss.py
code served (permissive licence) · get_code("abe06350e77d2d47")
How it ran

no invocation recorded.

text_to_sentences Not yet run
unverified (harvested, no recorded run)
sommerschield/ancient-text-restoration/pythia/util/text_clean.py
code served (permissive licence) · get_code("0593a6b4d210c86b")
How it ran

no invocation recorded.

text_to_word_idx Not yet run
unverified (harvested, no recorded run)
sommerschield/ancient-text-restoration/pythia/util/vocab.py
code served (permissive licence) · get_code("177808f8fa0313ab")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
strip_accents 2 other papers
2 later
2304.01196 (2023-04)
Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data
2601.02578 (2026-01)
DataParasite Enables Scalable and Repurposable Online Data Curation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Ancient history relies on disciplines such as epigraphy, the study of ancient inscribed texts, for evidence of the recorded past. However, these texts, "inscriptions", are often damaged over the centuries, and illegible parts of the text must be restored by specialists, known as epigraphists. This work presents Pythia, the first ancient text restoration model that recovers missing characters from a damaged text input using deep neural networks. Its architecture is carefully designed to handle long-term context information, and deal efficiently with missing or corrupted character and word representations. To train it, we wrote a non-trivial pipeline to convert PHI, the largest digital corpus of ancient Greek inscriptions, to machine actionable text, which we call PHI-ML. On PHI-ML, Pythia's predictions achieve a 30.1% character error rate, compared to the 57.3% of human epigraphists. Moreover, in 73.5% of cases the ground-truth sequence was among the Top-20 hypotheses of Pythia, which effectively demonstrates the impact of this assistive method on the field of digital epigraphy, and sets the state-of-the-art in ancient text restoration.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1910.06262")
get_code_for_paper("1910.06262")
have("1910.06262")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1910.06262.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1910.06262.svg)](https://syntology.ai/paper/1910.06262)

Connect an agent — have() is free.