SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.05856 · 2019

Detecting Photoshopped Faces by Scripting Photoshop

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 2 failures of our instrument; 3 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/1906.05856.json · badge: /api/ran/1906.05856.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
PeterWang512/FALdetector community (classifier label)
classifier basis not recorded on the link
7 ran · 3 no recorded run
FunctionStatusWhere it lives
center_crop Ran
ran on a synthesized input
PeterWang512/FALdetector/utils/tools.py
code served (permissive licence) · get_code("c4019770f99361ad")
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. 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.

from PIL import Image
import torch

torch.manual_seed(0)

# Create a small PIL Image for testing
# The function calls im.size, im.crop()
# We need an image with distinct width and height
im = Image.new('RGB', (100, 80))  # width=100, height=80

# length parameter should be less than both dimensions
length = 40

ARGS = {
    'im': im,
    'length': length
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
PeterWang512/FALdetector/networks/drn.py
code served (permissive licence) · get_code("0e722c9ff0920473")
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 Conv2d. 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

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "padding": 1,
    "dilation": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
drn_a_50 Ran
ran on a synthesized input
PeterWang512/FALdetector/networks/drn.py
code served (permissive licence) · get_code("19e291fafc7bb35b")
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 DRN_A. 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 math

torch.manual_seed(0)

ARGS = {
    'pretrained': False
}
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 DRN_A — a DRN_A output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DRN_A 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_heatmap_batch Ran
ran on a synthesized input
PeterWang512/FALdetector/utils/visualize.py
code served (permissive licence) · get_code("7b3fe2745271414b")
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 3, dtype family float, shape (3, 8, 14) 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
import numpy as np

torch.manual_seed(0)

# Create small test tensors
batch_size = 2
channels = 3
height = 4
width = 4

# img_batch: (batch_size, channels, height, width) - normalized image batch
img_batch = torch.randn(batch_size, channels, height, width)

# pred_batch: (batch_size, 2, height, width) - optical flow or similar 2-channel prediction
pred_batch = torch.randn(batch_size, 2, height, width)

ARGS = {
    "img_batch": img_batch,
    "pred_batch": pred_batch,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, 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 3, dtype family float, shape (3, 8, 14) — shape (3, 8, 14) 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
remove_boundary Ran
ran on a synthesized input
PeterWang512/FALdetector/utils/tools.py
code served (permissive licence) · get_code("31f27cfaf2e17176")
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.

from PIL import Image

# Create a small test image with PIL
# The function expects an image object with .size attribute and .crop() method
img = Image.new('RGB', (800, 500), color='red')

ARGS = {
    'img': img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — 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
resize_shorter_side Ran
ran on a synthesized input
PeterWang512/FALdetector/utils/tools.py
code served (permissive licence) · get_code("910e8701c0ed21ba")
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. 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.

from PIL import Image
import numpy as np

# Create a small test image
# Create a numpy array and convert to PIL Image
# Making a landscape image (wider than tall) to test aspect ratio preservation
img_array = np.random.randint(0, 256, (100, 150, 3), dtype=np.uint8)
test_img = Image.fromarray(img_array)

# min_length parameter - the target length for the shorter side
min_length = 50

ARGS = {
    "img": test_img,
    "min_length": min_length,
}
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 tuple — a tuple 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
unnormalize Ran
ran; our contract draft was wrong, not the code
PeterWang512/FALdetector/utils/visualize.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yzy-stack/effort-aigi-detection, is pointer only (licence: NONE) · get_code("7742460f647f9ca2")
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 yzy-stack/effort-aigi-detection, 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.

classify_fake Not yet run
unverified (harvested, no recorded run)
PeterWang512/FALdetector/global_classifier.py
code served (permissive licence) · get_code("a6a09be2fd8eb095")
How it ran

no invocation recorded.

drn_c_26 Not yet run
unverified (harvested, no recorded run)
PeterWang512/FALdetector/networks/drn.py
code served (permissive licence) · get_code("f2cb2c00d5b19823")
How it ran

no invocation recorded.

get_heatmap_cv Not yet run
unverified (harvested, no recorded run)
PeterWang512/FALdetector/utils/visualize.py
code served (permissive licence) · get_code("40e586b15242d87d")
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, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 6 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
conv3x3 6 other papers
1 dated earlier, 5 later
1808.07535 (2018-08)
Learning Hierarchical Semantic Image Manipulation through Structured Representations
1908.06702 (2019-08)
Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path
2003.05970 (2020-03)
LiDAR guided Small obstacle Segmentation
and 3 more not named here
unnormalize 2 other papers
2 later
2408.09647 (2024-08)
C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection
2411.15633 (2024-11)
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
drn_a_50 1 other paper
1 later
1908.06702 (2019-08)
Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path
drn_c_26 1 other paper
1 later
1908.06702 (2019-08)
Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path

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

Most malicious photo manipulations are created using standard image editing tools, such as Adobe Photoshop. We present a method for detecting one very popular Photoshop manipulation -- image warping applied to human faces -- using a model trained entirely using fake images that were automatically generated by scripting Photoshop itself. We show that our model outperforms humans at the task of recognizing manipulated images, can predict the specific location of edits, and in some cases can be used to "undo" a manipulation to reconstruct the original, unedited image. We demonstrate that the system can be successfully applied to real, artist-created image manipulations.

For agents

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

get_harvested_code_for_paper("1906.05856")
get_code_for_paper("1906.05856")
have("1906.05856")

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

curl https://syntology.ai/api/ran/1906.05856.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.05856.svg)](https://syntology.ai/paper/1906.05856)

Connect an agent — have() is free.