SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.01020 · 2022

MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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 4 have no contract verdict; 1 failure 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/2202.01020.json · badge: /api/ran/2202.01020.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
jonathanfrawley/mednerf canonical (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
abrilcf/mednerf canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
color_depth_map Ran
ran on a synthesized input
jonathanfrawley/mednerf/graf-main/graf/utils.py
code served (permissive licence) · get_code("71ec2a9308fa61f3")
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) 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

# Create a small depth map (HxW numpy array)
# Using distinct dimensions: 4 height, 3 width
depths = np.random.rand(4, 3) * 10.0

# Create ARGS dictionary with all parameters
ARGS = {
    "depths": depths,
    "scale": None
}
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 3) 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
count_trainable_parameters Ran
ran on a synthesized input
jonathanfrawley/mednerf/graf-main/graf/utils.py
code served (permissive licence) · get_code("7de1ceff1fdc469d")
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 int64, ndim 0, dtype family int, 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int64, ndim 0, dtype family int, 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_nsamples Ran
ran on a synthesized input
jonathanfrawley/mednerf/graf-main/graf/utils.py
code served (permissive licence) · get_code("07358b1c5ae29b4a")
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 2, dtype family float, shape (6, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Create a simple data loader that yields tensors
# The function calls next(data_loader) and expects tensors with .cuda() and .size(0)
class SimpleDataLoader:
    def __init__(self, num_batches=5, batch_size=2, feature_dim=4):
        self.num_batches = num_batches
        self.batch_size = batch_size
        self.feature_dim = feature_dim
        self.current_batch = 0
    
    def __iter__(self):
        self.current_batch = 0
        return self
    
    def __next__(self):
        if self.current_batch >= self.num_batches:
            raise StopIteration
        self.current_batch += 1
        # Return a tensor of shape (batch_size, feature_dim)
        return torch.randn(self.batch_size, self.feature_dim)

# Create data loader instance
data_loader = iter(SimpleDataLoader(num_batches=5, batch_size=2, feature_dim=4))

# N is the number of samples to retrieve
N = 6

ARGS = {
    "data_loader": data_loader,
    "N": N
}
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 2, dtype family float, shape (6, 4) — shape (6, 4) 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_output Ran
ran, honoured the contract we drafted
abrilcf/mednerf/graf-main/render_xray_G.py
code served (permissive licence) · get_code("fe5e56bffc7fef7b")
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 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function accesses output[0] and output[1], so output must be indexable
# with at least 2 elements. metrics_engine is not used in the function body.

# Create a minimal metrics_engine (not used, but required parameter)
class MetricsEngine:
    pass

metrics_engine = MetricsEngine()

# Create output as a tuple/list with at least 2 elements
# Using small tensors as the elements
output = (
    torch.randn(2, 4),  # output[0]
    torch.randn(2, 3)   # output[1]
)

ARGS = {
    "metrics_engine": metrics_engine,
    "output": output
}
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 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
get_rays Ran
ran; our contract draft was wrong, not the code
abrilcf/mednerf/graf-main/render_xray_G.py
code served (permissive licence) · get_code("d58b76f6693bc650")
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 Tensor, ndim 3, dtype family float, shape (2, 2, 3) 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 torch.nn as nn

torch.manual_seed(0)

class RaySampler(nn.Module):
    def __init__(self):
        super().__init__()
        self.focal = 500.0
    
    def val_ray_sampler(self, height, width, focal, pose):
        # Returns a tuple where first element is the rays
        # Create a dummy ray tensor of shape (height, width, 3)
        rays = torch.randn(height, width, 3)
        return (rays,)

class Generator(nn.Module):
    def __init__(self):
        super().__init__()
        self.val_ray_sampler = RaySampler().val_ray_sampler
        self.focal = 500.0

# Create instances
generator = Generator()
pose = torch.randn(4, 4)  # Standard camera pose matrix
img_size = 2

ARGS = {
    "pose": pose,
    "generator": generator,
    "img_size": img_size
}
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 Tensor, ndim 3, dtype family float, shape (2, 2, 3) — shape (2, 2, 3) 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
update_config Ran
ran on a synthesized input
jonathanfrawley/mednerf/graf-main/graf/config.py
code served (permissive licence) · get_code("559fa10dfa807ea5")
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 dict. 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)

# Construct a nested config dict with various types
config = {
    'model': {
        'hidden_size': 128,
        'num_layers': 3,
        'dropout': 0.5,
        'use_attention': True,
        'optimizer': None
    },
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 100,
    'use_gpu': False
}

# Construct unknown arguments list with both nested (k1:k2) and flat (k) style arguments
unknown = [
    '--model:hidden_size', '256',
    '--model:num_layers', '5',
    '--model:use_attention', 'false',
    '--learning_rate', '0.0005',
    '--epochs', '200'
]

ARGS = {
    'config': config,
    'unknown': unknown
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_data Not yet run
unverified (harvested, no recorded run)
jonathanfrawley/mednerf/graf-main/graf/config.py
code served (permissive licence) · get_code("bbca3fa5fe628f83")
How it ran

no invocation recorded.

get_render_poses Not yet run
unverified (harvested, no recorded run)
jonathanfrawley/mednerf/graf-main/graf/config.py
code served (permissive licence) · get_code("677c56fac6ae59a2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
color_depth_map 1 other paper
1 dated earlier
2007.02442 (2020-07)
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
count_trainable_parameters 1 other paper
1 dated earlier
2007.02442 (2020-07)
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
get_render_poses 1 other paper
1 dated earlier
2007.02442 (2020-07)
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
update_config 1 other paper
1 dated earlier
2007.02442 (2020-07)
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

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

Computed tomography (CT) is an effective medical imaging modality, widely used in the field of clinical medicine for the diagnosis of various pathologies. Advances in Multidetector CT imaging technology have enabled additional functionalities, including generation of thin slice multiplanar cross-sectional body imaging and 3D reconstructions. However, this involves patients being exposed to a considerable dose of ionising radiation. Excessive ionising radiation can lead to deterministic and harmful effects on the body. This paper proposes a Deep Learning model that learns to reconstruct CT projections from a few or even a single-view X-ray. This is based on a novel architecture that builds from neural radiance fields, which learns a continuous representation of CT scans by disentangling the shape and volumetric depth of surface and internal anatomical structures from 2D images. Our model is trained on chest and knee datasets, and we demonstrate qualitative and quantitative high-fidelity renderings and compare our approach to other recent radiance field-based methods. Our code and link to our datasets are available at https://github.com/abrilcf/mednerf

For agents

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

get_harvested_code_for_paper("2202.01020")
get_code_for_paper("2202.01020")
have("2202.01020")

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

curl https://syntology.ai/api/ran/2202.01020.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.01020.svg)](https://syntology.ai/paper/2202.01020)

Connect an agent — have() is free.