SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.14867 · 2023

VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 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/2312.14867.json · badge: /api/ran/2312.14867.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
TIGER-AI-Lab/VIEScore canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
encode_image Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/mllm_tools/openai.py
pointer only (licence: MIT); the stored copy get_code serves, from jongwoopark7978/LVNet, is pointer only (licence: NONE) · get_code("f41cb1a19b154297")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jongwoopark7978/LVNet, and GitHub detected no licence in that repository when it was checked. 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.

fix_json Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/utils.py
code served (permissive licence) · get_code("5ea35c6f48bf72a0")
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 regex as re

def fix_json(input_str):
    fixed_str = re.sub('(\\w+):', '"\\1":', input_str)

    def format_value(match):
        key, value, comma = match.groups()
        value = value.strip()
        if re.match('^-?\\d+(\\.\\d+)?$', value):
            value = f'[{value}]'
        elif re.match('^(true|false|null)$', value, re.IGNORECASE):
            pass
        else:
            value = f'"{value}"'
        return f'{key}: {value}{comma}'
    fixed_str = re.sub('(".*?"):(.*?)(,|})', format_value, fixed_str)
    return fixed_str


ARGS = {
    'input_str': '{name: John, age: 30, active: true, score: 95.5, city: NYC}'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
regex — 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
get_api_key Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/mllm_tools/openai.py
code served (permissive licence) · get_code("e71f0a1840318cb9")
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 tempfile
import os

# Create a temporary file with an API key
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write('test_api_key_12345\n')
temp_file.write('extra_line_that_should_not_be_read\n')
temp_file.close()

ARGS = {
    'file_path': temp_file.name
}
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
get_file_path Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/paper_implementation/clean_result.py
code served (permissive licence) · get_code("ae1444e80f1dbb62")
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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
test_dir = tempfile.mkdtemp()

# Create a nested directory structure with test files
os.makedirs(os.path.join(test_dir, "subdir1", "subdir2"), exist_ok=True)
os.makedirs(os.path.join(test_dir, "subdir3"), exist_ok=True)

# Create some test files
test_filename = "test_file.txt"
with open(os.path.join(test_dir, "subdir1", "subdir2", test_filename), 'w') as f:
    f.write("test content")

# Setup arguments for get_file_path
ARGS = {
    "filename": test_filename,
    "search_from": test_dir
}
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
load_image Ran
ran, honoured the contract we drafted
TIGER-AI-Lab/VIEScore/viescore/mllm_tools/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from raptormai/compbench, is pointer only (licence: NOASSERTION) · get_code("0ec33995a5dc05d1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from raptormai/compbench, 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.

load_images Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/mllm_tools/utils.py
code served (permissive licence) · get_code("3c0709cacb35e6aa")
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 list. 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 tempfile
from PIL import Image
import os

# Create a temporary directory for test images
temp_dir = tempfile.mkdtemp()

# Create a small test image file
test_image_path = os.path.join(temp_dir, "test_image.jpg")
test_image = Image.new('RGB', (10, 10), color=(255, 0, 0))
test_image.save(test_image_path)

# Create another test image file
test_image_path_2 = os.path.join(temp_dir, "test_image_2.jpg")
test_image_2 = Image.new('RGB', (20, 20), color=(0, 255, 0))
test_image_2.save(test_image_path_2)

# Define ARGS with a list of image file paths
ARGS = {
    'image_files': [test_image_path, test_image_path_2]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, requests — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is 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
pick_next_item Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/mllm_tools/openai.py
code served (permissive licence) · get_code("c302d46717895f2b")
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

# Set random seed for reproducibility
torch.manual_seed(0)

# Define arguments for pick_next_item function
current_item = "apple"
item_list = ["apple", "banana", "cherry", "date"]

ARGS = {
    "current_item": current_item,
    "item_list": item_list,
}
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
pil_image_to_base64 Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/mllm_tools/utils.py
code served (permissive licence) · get_code("ad84f742a5662dd6")
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 base64
from io import BytesIO
from PIL import Image
import numpy as np

# Create a small PIL Image
img_array = np.random.randint(0, 256, (10, 10, 3), dtype=np.uint8)
pil_image = Image.fromarray(img_array, mode='RGB')

ARGS = {
    'pil_image': pil_image,
    'format': 'PNG'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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
read_file_to_string Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/utils.py
code served (permissive licence) · get_code("22ae1ae2b156c6ff")
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 tempfile
import os

# Create a temporary text file with some content
temp_dir = tempfile.mkdtemp()
temp_file_path = os.path.join(temp_dir, "test_file.txt")
with open(temp_file_path, 'w', encoding='utf-8') as f:
    f.write("This is a test file content.\nIt has multiple lines.\n")

ARGS = {
    "file_path": temp_file_path
}
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
read_files_to_string Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/VIEScore/viescore/utils.py
code served (permissive licence) · get_code("ff84253d325511bc")
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 tempfile
import os

# Create temporary text files with sample content
temp_dir = tempfile.mkdtemp()

file1_path = os.path.join(temp_dir, "file1.txt")
file2_path = os.path.join(temp_dir, "file2.txt")
file3_path = os.path.join(temp_dir, "file3.txt")

with open(file1_path, 'w', encoding='utf-8') as f:
    f.write("This is the content of file 1.")

with open(file2_path, 'w', encoding='utf-8') as f:
    f.write("This is the content of file 2.")

with open(file3_path, 'w', encoding='utf-8') as f:
    f.write("This is the content of file 3.")

ARGS = {
    'file_paths': [file1_path, file2_path, file3_path]
}
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
save_image_from_url Not yet run
unverified (harvested, no recorded run)
TIGER-AI-Lab/VIEScore/viescore/mllm_tools/gemini.py
code served (permissive licence) · get_code("65ffcd17f0ae0bab")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 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
encode_image 76 other papers
2 dated earlier, 74 later
2309.05950 (2023-09)
Language Models as Black-Box Optimizers for Vision-Language Models
2311.15732 (2023-11)
GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?
Cao_MAPLM_A_Real-World_Large-Scale_Vision-Language_Benchmark_for_Map_and_Traffic_CVPR_2024_paper (2024 (year only))
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding
and 73 more not named here
load_images 20 other papers
20 later
2024.findings-emnlp.268 (2024 (year only))
Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
2403.13805 (2024-03)
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
2404.10618 (2024-04)
Private Attribute Inference from Images with Vision-Language Models
and 17 more not named here
load_image 1 other paper
1 later
2407.16837 (2024-07)
MLLM-COMPBENCH: A Comparative Reasoning Benchmark for Multimodal LLMs

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

In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIEScore, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIEScore leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIEScore on seven prominent tasks in conditional image tasks and found: (1) VIEScore (GPT4-o) achieves a high Spearman correlation of 0.4 with human evaluations, while the human-to-human correlation is 0.45. (2) VIEScore (with open-source MLLM) is significantly weaker than GPT-4o and GPT-4v in evaluating synthetic images. (3) VIEScore achieves a correlation on par with human ratings in the generation tasks but struggles in editing tasks. With these results, we believe VIEScore shows its great potential to replace human judges in evaluating image synthesis tasks.

For agents

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

get_harvested_code_for_paper("2312.14867")
get_code_for_paper("2312.14867")
have("2312.14867")

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

curl https://syntology.ai/api/ran/2312.14867.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.14867.svg)](https://syntology.ai/paper/2312.14867)

Connect an agent — have() is free.