SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.10474 · 2022

ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 failures of our instrument; 0 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/2212.10474.json · badge: /api/ran/2212.10474.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
potamides/uniformers canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
find_rhymes Ran
ran; our contract draft was wrong, not the code
potamides/uniformers/uniformers/utils/poetry.py
code served (permissive licence) · get_code("e5a56129e93f36d9")
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) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch
import numpy as np

# Analyze the function to understand what it needs:
# - stanza: a sequence that can be indexed (list or similar)
# - rhyme: a sequence that can be indexed, has len(), and supports string operations
#   The function iterates through rhyme as letters and uses escape() and finditer() on it
#   So rhyme should be a string

# Create a simple stanza - a list of strings (verses)
stanza = ["verse_one", "verse_two", "verse_three", "verse_four"]

# Create a rhyme pattern - a string where each character represents a rhyme scheme
# For example: "ABAB" means verses 0 and 2 rhyme, verses 1 and 3 rhyme
rhyme = "ABAB"

# Verify they have the same length as required by the assertion
assert len(stanza) == len(rhyme)

ARGS = {
    "stanza": stanza,
    "rhyme": rhyme
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
meter_to_label Ran
ran; our contract draft was wrong, not the code
potamides/uniformers/uniformers/utils/poetry.py
code served (permissive licence) · get_code("51bf8f8321735435")
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) 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 torch
import numpy as np

METERS = ('alexandrine', 'amphibrach', 'anapaest', 'dactyl', 'iambus', 'other', 'trochee')

RARE_METERS = ('asklepiade', 'diphilius', 'glykoneus', 'hexameter', 'pherekrateus', 'prosodiakos', 'spondee', 'zehnsilber')

ALL_METERS = METERS + RARE_METERS

def meter_to_label(meter, group_rare=True):
    match meter:
        case 'anapestic':
            meter = 'anapaest'
        case 'dactylic':
            meter = 'dactyl'
        case 'trochaic':
            meter = 'trochee'
        case 'spondeus':
            meter = 'spondee'
        case 'iamb' | 'iambic':
            meter = 'iambus'
    if group_rare and meter in RARE_METERS:
        meter = 'other'
    if meter in METERS if group_rare else ALL_METERS:
        return meter
    else:
        raise ValueError(f"Meter called '{meter}' can't be processed or doesn't exist.")

ARGS = {
    'meter': 'dactyl',
    'group_rare': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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
scheme_to_label Ran
ran; our contract draft was wrong, not the code
potamides/uniformers/uniformers/utils/poetry.py
code served (permissive licence) · get_code("850afafadaf2712c")
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) 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 torch

torch.manual_seed(0)

# The function scheme_to_label takes 4 string parameters (a, b, c, d)
# and converts a scheme in CCAD form to AABC form by relabeling characters
# based on their first appearance order.

ARGS = {
    'a': 'C',
    'b': 'C',
    'c': 'A',
    'd': 'D'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

State-of-the-art poetry generation systems are often complex. They either consist of task-specific model pipelines, incorporate prior knowledge in the form of manually created constraints, or both. In contrast, end-to-end models would not suffer from the overhead of having to model prior knowledge and could learn the nuances of poetry from data alone, reducing the degree of human supervision required. In this work, we investigate end-to-end poetry generation conditioned on styles such as rhyme, meter, and alliteration. We identify and address lack of training data and mismatching tokenization algorithms as possible limitations of past attempts. In particular, we successfully pre-train ByGPT5, a new token-free decoder-only language model, and fine-tune it on a large custom corpus of English and German quatrains annotated with our styles. We show that ByGPT5 outperforms other models such as mT5, ByT5, GPT-2 and ChatGPT, while also being more parameter efficient and performing favorably compared to humans. In addition, we analyze its runtime performance and demonstrate that it is not prone to memorization. We make our code, models, and datasets publicly available.

For agents

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

get_harvested_code_for_paper("2212.10474")
get_code_for_paper("2212.10474")
have("2212.10474")

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

curl https://syntology.ai/api/ran/2212.10474.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.10474.svg)](https://syntology.ai/paper/2212.10474)

Connect an agent — have() is free.