SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.11513 · 2023

GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 1 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/2310.11513.json · badge: /api/ran/2310.11513.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
djghosh13/geneval canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
make_plural Ran
ran; our contract draft was wrong, not the code
djghosh13/geneval/prompts/create_prompts.py
code served (permissive licence) · get_code("556a917293596716")
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 torch

def make_plural(name: str):
    if name[-1] in 's':
        return f'{name}es'
    return f'{name}s'

ARGS = {
    'name': 'cat'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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
timed Ran
ran; our contract draft was wrong, not the code
djghosh13/geneval/evaluation/evaluate_images.py
code served (permissive licence) · get_code("844a4aecea80d106")
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 function. 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 torch.nn as nn
import time
import sys

def timed(fn):
    def wrapper(*args, **kwargs):
        startt = time.time()
        result = fn(*args, **kwargs)
        endt = time.time()
        print(f'Function {fn.__name__!r} executed in {endt - startt:.3f}s', file=sys.stderr)
        return result
    return wrapper

# Create a simple test function to decorate
def sample_function(x, y):
    return x + y

# The timed decorator takes a function as its only argument
ARGS = {
    'fn': sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
with_article Ran
ran; our contract draft was wrong, not the code
djghosh13/geneval/prompts/create_prompts.py
code served (permissive licence) · get_code("e56c199fc836a44e")
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 torch

def with_article(name: str):
    if name[0] in 'aeiou':
        return f'an {name}'
    return f'a {name}'

ARGS = {
    'name': 'apple'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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
generate_single_object_sample Not yet run
unverified (harvested, no recorded run)
djghosh13/geneval/prompts/create_prompts.py
code served (permissive licence) · get_code("601de58a282ecb25")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 0 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
timed 4 other papers
4 later
2412.04431 (2024-12)
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
2505.14683 (2025-05)
Emerging Properties in Unified Multimodal Pretraining
2505.23380 (2025-05)
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
and 1 more not named here
generate_single_object_sample 1 other paper
1 later
2505.24875 (2025-05)
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
make_plural 1 other paper
1 later
2505.24875 (2025-05)
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
with_article 1 other paper
1 later
2505.24875 (2025-05)
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL

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

Recent breakthroughs in diffusion models, multimodal pretraining, and efficient finetuning have led to an explosion of text-to-image generative models. Given human evaluation is expensive and difficult to scale, automated methods are critical for evaluating the increasingly large number of new models. However, most current automated evaluation metrics like FID or CLIPScore only offer a holistic measure of image quality or image-text alignment, and are unsuited for fine-grained or instance-level analysis. In this paper, we introduce GenEval, an object-focused framework to evaluate compositional image properties such as object co-occurrence, position, count, and color. We show that current object detection models can be leveraged to evaluate text-to-image models on a variety of generation tasks with strong human agreement, and that other discriminative vision models can be linked to this pipeline to further verify properties like object color. We then evaluate several open-source text-to-image models and analyze their relative generative capabilities on our benchmark. We find that recent models demonstrate significant improvement on these tasks, though they are still lacking in complex capabilities such as spatial relations and attribute binding. Finally, we demonstrate how GenEval might be used to help discover existing failure modes, in order to inform development of the next generation of text-to-image models. Our code to run the GenEval framework is publicly available at https://github.com/djghosh13/geneval.

For agents

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

get_harvested_code_for_paper("2310.11513")
get_code_for_paper("2310.11513")
have("2310.11513")

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

curl https://syntology.ai/api/ran/2310.11513.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.11513.svg)](https://syntology.ai/paper/2310.11513)

Connect an agent — have() is free.