SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.13370 · CVPR · 2025

Unraveling Normal Anatomy via Fluid-Driven Anomaly Randomization

Peirong Liu, Juan Iglesias, Ana Aguila

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 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/2501.13370.json · badge: /api/ran/2501.13370.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
peirong26/UNA community
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
Upwind Ran
ran on a synthesized input · constructed an object; no result was computed
peirong26/UNA/FluidAnomaly/DiffEqs/pde.py
code served (permissive licence) · get_code("3dbe725093f9872e")
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 an instance of its own class, Upwind: the run constructed the object and did not call it, so no result was computed. 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)

# Create a small tensor for U
# For batched=True, shape should be (n_batch, ...)
# For dim=2 (based on the code), shape should be (n_batch, height, width)
U = torch.randn(2, 4, 3, dtype=torch.float)

# Define data_spacing for 2D case
data_spacing = [1.0, 1.0, 1.0]

# Set batched to True
batched = True

ARGS = {
    "U": U,
    "data_spacing": data_spacing,
    "batched": batched,
}
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 Upwind — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Upwind 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
gradient_b Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
peirong26/UNA/FluidAnomaly/DiffEqs/pde.py
code served (permissive licence) · get_code("b58901280a43cbc0")
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 (4, 3, 2) 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

torch.manual_seed(0)

# Test case 1: 1D non-batched tensor
X_1d = torch.randn(5, dtype=torch.float)

# Test case 2: 2D non-batched tensor
X_2d = torch.randn(4, 3, dtype=torch.float)

# Test case 3: 3D non-batched tensor
X_3d = torch.randn(4, 3, 2, dtype=torch.float)

# Test case 4: 1D batched tensor
X_1d_batched = torch.randn(2, 5, dtype=torch.float)

# Test case 5: 2D batched tensor
X_2d_batched = torch.randn(2, 4, 3, dtype=torch.float)

# Test case 6: 3D batched tensor
X_3d_batched = torch.randn(2, 4, 3, 2, dtype=torch.float)

# Use 2D non-batched as primary test case
X = X_2d
batched = False
delta_lst = [1.0, 1.0, 1.0]

ARGS = {
    "X": X,
    "batched": batched,
    "delta_lst": delta_lst,
}
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 Tensor, ndim 3, dtype family float, shape (4, 3, 2) — shape (4, 3, 2) 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
gradient_c Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
peirong26/UNA/FluidAnomaly/DiffEqs/pde.py
code served (permissive licence) · get_code("88ec8a133fcd7c8c")
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 (4, 3, 2) 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

torch.manual_seed(0)

# Test case 1: 1D non-batched tensor
X_1d = torch.randn(5, dtype=torch.float)

# Test case 2: 2D non-batched tensor
X_2d = torch.randn(4, 3, dtype=torch.float)

# Test case 3: 3D non-batched tensor
X_3d = torch.randn(4, 3, 5, dtype=torch.float)

# Test case 4: 1D batched tensor
X_1d_batched = torch.randn(2, 5, dtype=torch.float)

# Test case 5: 2D batched tensor
X_2d_batched = torch.randn(2, 4, 3, dtype=torch.float)

# Test case 6: 3D batched tensor
X_3d_batched = torch.randn(2, 4, 3, 5, dtype=torch.float)

# Custom delta list
delta_lst = [1.0, 1.0, 1.0]

# Create ARGS for a 2D non-batched case (representative test)
ARGS = {
    "X": X_2d,
    "batched": False,
    "delta_lst": delta_lst
}
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 Tensor, ndim 3, dtype family float, shape (4, 3, 2) — shape (4, 3, 2) 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
gradient_f Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
peirong26/UNA/FluidAnomaly/DiffEqs/pde.py
code served (permissive licence) · get_code("3a5fc1f37d0bb941")
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 (4, 3, 2) 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

torch.manual_seed(0)

# Case 1: 1D non-batched tensor
X_1d = torch.randn(5)

# Case 2: 2D non-batched tensor
X_2d = torch.randn(4, 3)

# Case 3: 3D non-batched tensor
X_3d = torch.randn(4, 3, 2)

# Case 4: 1D batched tensor (n_batch, dim)
X_1d_batched = torch.randn(2, 5)

# Case 5: 2D batched tensor (n_batch, height, width)
X_2d_batched = torch.randn(2, 4, 3)

# Case 6: 3D batched tensor (n_batch, depth, height, width)
X_3d_batched = torch.randn(2, 4, 3, 2)

# Delta list for spacing
delta_lst = [1.0, 1.0, 1.0]

# Test with 2D non-batched case
ARGS = {
    "X": X_2d,
    "batched": False,
    "delta_lst": delta_lst
}
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 Tensor, ndim 3, dtype family float, shape (4, 3, 2) — shape (4, 3, 2) 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
AdvDiffPDE Not yet run
unverified (harvested, no recorded run)
peirong26/UNA/FluidAnomaly/DiffEqs/pde.py
code served (permissive licence) · get_code("74e052c1fdfed06f")
How it ran

no invocation recorded.

AdvDiffPartial Not yet run
unverified (harvested, no recorded run)
peirong26/UNA/FluidAnomaly/DiffEqs/pde.py
code served (permissive licence) · get_code("dafe81f9d9acb911")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 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.

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

Data-driven machine learning has made significant strides in medical image analysis. However, most existing methods are tailored to specific modalities and assume a particular resolution (often isotropic). This limits their generalizability in clinical settings, where variations in scan appearance arise from differences in sequence parameters, resolution, and orientation. Furthermore, most general-purpose models are designed for healthy subjects and suffer from performance degradation when pathology is present. We introduce UNA (Unraveling Normal Anatomy), the first modality-agnostic learning approach for normal brain anatomy reconstruction that can handle both healthy scans and cases with pathology. We propose a fluid-driven anomaly randomization method that generates an unlimited number of realistic pathology profiles on-the-fly. UNA is trained on a combination of synthetic and real data, and can be applied directly to real images with potential pathology without the need for fine-tuning. We demonstrate UNA's effectiveness in reconstructing healthy brain anatomy and showcase its direct application to anomaly detection, using both simulated and real images from 3D healthy and stroke datasets, including CT and MRI scans. By bridging the gap between healthy and diseased images, UNA enables the use of general-purpose models on diseased images, opening up new opportunities for large-scale analysis of uncurated clinical images in the presence of pathology. Code is available at https://github.com/peirong26/UNA.

For agents

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

get_harvested_code_for_paper("2501.13370")
get_code_for_paper("2501.13370")
have("2501.13370")

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

curl https://syntology.ai/api/ran/2501.13370.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.13370.svg)](https://syntology.ai/paper/2501.13370)

Connect an agent — have() is free.