SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.02463 · 2023

Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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, 2 violated it and 0 have no contract verdict; 4 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/2308.02463.json · badge: /api/ran/2308.02463.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
chaoyi-wu/radfm canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran; our contract draft was wrong, not the code
chaoyi-wu/radfm/Quick_demo/Model/RadFM/helpers.py
code served (permissive licence) · get_code("4d75570b4e91d0b4")
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 Sequential. 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 = {
    "dim": 64,
    "mult": 4
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
build_position_encoding Ran
ran; our contract draft was wrong, not the code
chaoyi-wu/radfm/Quick_demo/Model/RadFM/position_encoding.py
code served (permissive licence) · get_code("c8f7b3c548c9d56a")
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 PositionEmbeddingSine. 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)

class TensorListMock:
    """Mock class to simulate tensor_list with tensors and mask attributes"""
    def __init__(self, tensors, mask):
        self.tensors = tensors
        self.mask = mask

class ArgsMock:
    """Mock args object for build_position_encoding"""
    def __init__(self, hidden_dim, position_embedding):
        self.hidden_dim = hidden_dim
        self.position_embedding = position_embedding

# Create small test tensors
batch_size = 2
height = 4
width = 3
hidden_dim = 128

# Create a small feature tensor
tensors = torch.randn(batch_size, hidden_dim, height, width)

# Create a mask (False for valid positions, True for padding)
mask = torch.zeros(batch_size, height, width, dtype=torch.bool)
mask[0, -1, :] = True  # Add some padding to first sample
mask[1, -1, -1] = True  # Add some padding to second sample

# Create tensor_list mock
tensor_list = TensorListMock(tensors=tensors, mask=mask)

# Create args mock for sine version
args_sine = ArgsMock(hidden_dim=128, position_embedding='sine')

# Create args mock for learned version
args_learned = ArgsMock(hidden_dim=128, position_embedding='learned')

ARGS = {
    'args': args_sine
}
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 PositionEmbeddingSine — a PositionEmbeddingSine output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PositionEmbeddingSine 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
exists Ran
ran, violated the contract we drafted
chaoyi-wu/radfm/Quick_demo/Model/RadFM/helpers.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

getattr_recursive Ran
ran; our contract draft was wrong, not the code
chaoyi-wu/radfm/Quick_demo/Model/RadFM/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from sony/aki, is pointer only (licence: NOASSERTION) · get_code("fe68fff801021b23")
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 sony/aki, 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.

pair Ran
ran, violated the contract we drafted
chaoyi-wu/radfm/Quick_demo/Model/RadFM/vit_3d.py
code served (permissive licence) · get_code("6ba8cee9f5daea41")
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, ndim 1, dtype family int; 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 torch

torch.manual_seed(0)

# The function 'pair' takes a single parameter 't' and returns it as a tuple if it isn't already one
# We need to test both cases: when t is a tuple and when it's not

# Case 1: t is not a tuple (e.g., an integer, string, tensor, etc.)
t_not_tuple = 5

# Case 2: t is already a tuple
t_is_tuple = (3, 7)

# We'll use the non-tuple case as the primary test
ARGS = {
    "t": t_not_tuple
}
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, ndim 1, dtype family int — 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
vision_load_pretrain Ran
ran; our contract draft was wrong, not the code
chaoyi-wu/radfm/Quick_demo/Model/RadFM/utils.py
code served (permissive licence) · get_code("5eab665292b38cf2")
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 SimpleResNet. 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 minimal ResNet-like model that has load_state_dict method
class SimpleResNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 8)
        self.layer2 = nn.Linear(8, 4)
    
    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        return x

# Create a resnet instance
resnet = SimpleResNet()

# Create a mock checkpoint file with the expected structure
# The function expects 'state_dict' key and filters for keys containing '.visual'
checkpoint = {
    'state_dict': {
        'module.visual.layer1.weight': torch.randn(8, 4),
        'module.visual.layer1.bias': torch.randn(8),
        'module.visual.layer2.weight': torch.randn(4, 8),
        'module.visual.layer2.bias': torch.randn(4),
        'other.key': torch.randn(2, 2),  # This will be filtered out
    }
}

# Create a temporary file to save the checkpoint
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pt') as f:
    model_path = f.name
    torch.save(checkpoint, f)

try:
    ARGS = {
        'resnet': resnet,
        'model_path': model_path,
    }
finally:
    # Clean up will happen after execution
    pass
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 SimpleResNet — a SimpleResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleResNet 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_visual_encoder Not yet run
unverified (harvested, no recorded run)
chaoyi-wu/radfm/Quick_demo/Model/RadFM/utils.py
code served (permissive licence) · get_code("fb9045fc9e031a91")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 5 later) and 2 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
exists 486 other papers
206 dated earlier, 17 the same month, 257 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
pair 90 other papers
33 dated earlier, 2 the same month, 52 later, 2 same year, order not determinable, 1 undated · 8 only as an assembly brick
2004.13649 (2020-04)
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2103.15691 (2021-03)
ViViT: A Video Vision Transformer
and 87 more not named here
FeedForward 47 other papers
1 dated earlier, 2 the same month, 44 later · 4 only as an assembly brick
2204.14198 (2022-04)
Flamingo: a Visual Language Model for Few-Shot Learning
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
2308.09905 (2023-08)
DiffusionTrack: Diffusion Model For Multi-Object Tracking
and 44 more not named here
build_position_encoding 8 other papers
5 dated earlier, 3 later
2104.12763 (2021-04)
MDETR -Modulated Detection for End-to-End Multi-Modal Understanding
2108.11084 (2021-08)
Transformer for Single Image Super-Resolution
2111.12085 (2021-11)
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
and 5 more not named here
getattr_recursive 5 other papers
5 later · 1 only as an assembly brick
2310.00647 (2023-10)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
2402.10805 (2024-02)
Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
2408.05926 (2024-08)
BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation
and 2 more not named here

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 this study, we aim to initiate the development of Radiology Foundation Model, termed as RadFM. We consider the construction of foundational models from three perspectives, namely, dataset construction, model design, and thorough evaluation. Our contribution can be concluded as follows: (i), we construct a large-scale Medical Multi-modal Dataset, MedMD, which consists of 16M 2D and 3D medical scans with high-quality text descriptions or reports across various data formats, modalities, and tasks, covering over 5000 distinct diseases. To the best of our knowledge, this is the first large-scale, high-quality, medical visual-language dataset, with both 2D and 3D scans; (ii), we propose an architecture that enables visually conditioned generative pre-training, i.e., allowing for integration of text input with 2D or 3D medical scans, and generate responses for diverse radiologic tasks. The model was initially pre-trained on MedMD and subsequently fine-tuned on the domain-specific dataset, which is a radiologic cleaned version of MedMD, containing 3M radiologic visual-language pairs, termed as RadMD; (iii), we propose a new evaluation benchmark, RadBench, that comprises five tasks, including modality recognition, disease diagnosis, visual question answering, report generation and rationale diagnosis, aiming to comprehensively assess the capability of foundation models in handling practical clinical problems. We conduct both automatic and human evaluation on RadBench, in both cases, RadFM outperforms existing multi-modal foundation models, that are publicaly accessible, including Openflamingo, MedFlamingo, MedVInT and GPT-4V. Additionally, we also adapt RadFM for different public benchmarks, surpassing existing SOTAs on diverse datasets. All codes, data, and model checkpoint will all be made publicly available to promote further research and development in the field.

For agents

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

get_harvested_code_for_paper("2308.02463")
get_code_for_paper("2308.02463")
have("2308.02463")

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

curl https://syntology.ai/api/ran/2308.02463.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.02463.svg)](https://syntology.ai/paper/2308.02463)

Connect an agent — have() is free.