SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.09668 · 2024

EditBoard: Towards a Comprehensive Evaluation Benchmark for Text-Based Video Editing Models

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 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/2409.09668.json · badge: /api/ran/2409.09668.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
samchen2003/editboard canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
calculate_ff_alpha Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
samchen2003/editboard/editboard/ff_alpha.py
code served (permissive licence) · get_code("27893fdc6b9b40f4")
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 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 cv2
import numpy as np

# Create small test images with shape (m, n, 3) for BGR format
# Using 512x512 as the function references 512/512 in the calculation
m, n = 512, 512

# Create random BGR images (uint8)
original = np.random.randint(0, 256, (m, n, 3), dtype=np.uint8)
ori_warp = np.random.randint(0, 256, (m, n, 3), dtype=np.uint8)
edit = np.random.randint(0, 256, (m, n, 3), dtype=np.uint8)
edit_warp = np.random.randint(0, 256, (m, n, 3), dtype=np.uint8)

# Set threshold parameter
threshold = 5

ARGS = {
    'original': original,
    'ori_warp': ori_warp,
    'edit': edit,
    'edit_warp': edit_warp,
    'threshold': threshold
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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
crop_read_image_path Ran
ran, honoured the contract we drafted
samchen2003/editboard/editboard/clip_similarity.py
code served (permissive licence) · get_code("92f6ba552dffd628")
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 Image. 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
from PIL import Image
import numpy as np

# Create a temporary directory and image file
temp_dir = tempfile.mkdtemp()

# Create a test image with height > width (portrait orientation)
# Image size: width=100, height=150
img_array = np.random.randint(0, 256, (150, 100, 3), dtype=np.uint8)
test_image = Image.fromarray(img_array)
image_path = os.path.join(temp_dir, "test_image.png")
test_image.save(image_path)

ARGS = {
    "image_path": image_path
}
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 Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
dino_transform Ran
ran; our contract draft was wrong, not the code
samchen2003/editboard/editboard/utils.py
code served (permissive licence) · get_code("ab1a607c5868455f")
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 Compose. 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
from torchvision import transforms
from torchvision.transforms import Compose, Resize, CenterCrop, ToTensor, Normalize, ToPILImage

torch.manual_seed(0)

ARGS = {
    "n_px": 224
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
ff_beta_for_one Ran
ran, honoured the contract we drafted
samchen2003/editboard/editboard/ff_beta.py
code served (permissive licence) · get_code("e69da37dfb57b747")
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 float32, ndim 0, dtype family float, shape () 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

# Analyze the function:
# - Takes two parameters: a, b
# - Both are used with numpy operations expecting arrays
# - Operations: np.sum, multiplication, power
# - Accesses shape attributes: a.shape[0], a.shape[1]
# - Expected to be 2D arrays based on shape indexing and -1 axis operations

# Create small 2D numpy arrays
# Using distinct dimensions: batch_size=2, feature_dim=4
np.random.seed(0)

a = np.random.randn(2, 4).astype(np.float32)
b = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "a": a,
    "b": b,
}
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 float32, ndim 0, dtype family float, shape () — shape () 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
get_aesthetic_model Ran
ran; our contract draft was wrong, not the code
samchen2003/editboard/editboard/aesthetic_quality.py
code served (permissive licence) · get_code("643d7f2359bc5cd3")
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 Linear. 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 tempfile
import os

torch.manual_seed(0)

# Create a temporary directory for cache
cache_folder = tempfile.mkdtemp()

# Create a mock model file so the function doesn't try to download
path_to_model = os.path.join(cache_folder, 'sa_0_4_vit_l_14_linear.pth')
os.makedirs(cache_folder, exist_ok=True)

# Create a valid state dict for a Linear(768, 1) model
mock_model = nn.Linear(768, 1)
torch.save(mock_model.state_dict(), path_to_model)

ARGS = {
    'cache_folder': cache_folder
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
readimagefile Ran
ran; our contract draft was wrong, not the code
samchen2003/editboard/editboard/semantic_score.py
code served (permissive licence) · get_code("db1ae48be0b1fe2a")
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, 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 os
import tempfile
import shutil

# Create a temporary directory with test image files
temp_dir = tempfile.mkdtemp()

# Create some test image files
test_files = ['image1.png', 'image2.jpg', 'photo.jpeg', 'readme.txt', 'image3.png']
for filename in test_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write('dummy content')

# Define arguments for readimagefile
ARGS = {
    'filepath': temp_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 list, ndim 1, dtype family float — a list 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
semantic_score Ran
ran, honoured the contract we drafted
samchen2003/editboard/editboard/semantic_score.py
code served (permissive licence) · get_code("a1846d558cae212d")
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 float64, ndim 0, 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 cv2
import os
import numpy as np
import tempfile
import shutil

# Create temporary directories with test images
temp_dir = tempfile.mkdtemp()
original_dir = os.path.join(temp_dir, 'original')
edit_dir = os.path.join(temp_dir, 'edit')
mask_dir = os.path.join(temp_dir, 'mask')

os.makedirs(original_dir)
os.makedirs(edit_dir)
os.makedirs(mask_dir)

res = 512

# Create test images
for i in range(2):
    # Original image
    original_img = np.ones((res, res, 3), dtype=np.uint8) * 100
    cv2.imwrite(os.path.join(original_dir, f'image_{i}.png'), original_img)
    
    # Edit image (slightly different)
    edit_img = np.ones((res, res, 3), dtype=np.uint8) * 105
    cv2.imwrite(os.path.join(edit_dir, f'image_{i}.png'), edit_img)
    
    # Mask image (binary mask with some zeros for unmasked regions)
    mask_img = np.ones((res, res, 3), dtype=np.uint8) * 255
    mask_img[100:200, 100:200] = 0  # Create a masked region
    cv2.imwrite(os.path.join(mask_dir, f'image_{i}.png'), mask_img)

ARGS = {
    'original_file': original_dir,
    'edit_file': edit_dir,
    'mask_file': mask_dir,
    'res': res
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
transform Ran
ran; our contract draft was wrong, not the code
samchen2003/editboard/editboard/imaging_quality.py
code served (permissive licence) · get_code("80ed837661340660")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 512, 597) 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 torch
from torchvision import transforms

torch.manual_seed(0)

# Create a small batch of images with shape (batch, channels, height, width)
# Using distinct dimensions: batch=2, channels=3, height=600, width=700
images = torch.randint(0, 256, (2, 3, 600, 700), dtype=torch.uint8).float()

ARGS = {
    'images': images,
    'preprocess_mode': 'shorter'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 512, 597) — shape (2, 3, 512, 597) 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
clip_transform Not yet run
unverified (harvested, no recorded run)
samchen2003/editboard/editboard/utils.py
code served (permissive licence) · get_code("e0b29c7c05ba011e")
How it ran

no invocation recorded.

clip_transform_Image Not yet run
unverified (harvested, no recorded run)
samchen2003/editboard/editboard/utils.py
code served (permissive licence) · get_code("1afdce04b74e52dd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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
crop_read_image_path 1 other paper
1 dated earlier
2303.09535 (2023-03)
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

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

The rapid development of diffusion models has significantly advanced AI-generated content (AIGC), particularly in Text-to-Image (T2I) and Text-to-Video (T2V) generation. Text-based video editing, leveraging these generative capabilities, has emerged as a promising field, enabling precise modifications to videos based on text prompts. Despite the proliferation of innovative video editing models, there is a conspicuous lack of comprehensive evaluation benchmarks that holistically assess these models' performance across various dimensions. Existing evaluations are limited and inconsistent, typically summarizing overall performance with a single score, which obscures models' effectiveness on individual editing tasks. To address this gap, we propose EditBoard, the first comprehensive evaluation benchmark for text-based video editing models. EditBoard encompasses nine automatic metrics across four dimensions, evaluating models on four task categories and introducing three new metrics to assess fidelity. This task-oriented benchmark facilitates objective evaluation by detailing model performance and providing insights into each model's strengths and weaknesses. By open-sourcing EditBoard, we aim to standardize evaluation and advance the development of robust video editing models.

For agents

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

get_harvested_code_for_paper("2409.09668")
get_code_for_paper("2409.09668")
have("2409.09668")

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

curl https://syntology.ai/api/ran/2409.09668.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.09668.svg)](https://syntology.ai/paper/2409.09668)

Connect an agent — have() is free.