SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.16709 · NeurIPS · 2022

Data-Driven Computational Imaging for Scientific Discovery

Andrew Olsen, Yolanda Hu, Vidya Ganapati

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 6 have no contract verdict; 0 failures of our instrument; 0 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/2210.16709.json · badge: /api/ran/2210.16709.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
vganapati/LED_PVAE canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
F Ran
ran on a synthesized input
vganapati/LED_PVAE/SyntheticMNIST_functions.py
code served (permissive licence) · get_code("2bf6026b29195dcd")
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 EagerTensor, ndim 2, dtype family float, shape (4, 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 tensorflow as tf
import numpy as np

# Create a small 2D matrix for FFT processing
# Using distinct dimensions (4x3) for clarity
mat2D = tf.constant(np.random.randn(4, 3), dtype=tf.complex64)

ARGS = {
    "mat2D": mat2D
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
Ft Ran
ran on a synthesized input
vganapati/LED_PVAE/SyntheticMNIST_functions.py
code served (permissive licence) · get_code("3b5ce89a6401dbc1")
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 EagerTensor, ndim 2, dtype family float, shape (4, 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 tensorflow as tf
import numpy as np

# Create a small 2D complex matrix for FFT operations
# Shape: (4, 3) to have distinct dimensions
mat2d = tf.constant(
    np.random.randn(4, 3) + 1j * np.random.randn(4, 3),
    dtype=tf.complex64
)

ARGS = {
    "mat2D": mat2d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
create_img_stack Ran
ran on a synthesized input
vganapati/LED_PVAE/SyntheticMNIST_multislice_functions.py
code served (permissive licence) · get_code("30a3a16d38fea6ec")
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 float, shape (2, 3, 4) 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 training dataset
# The function expects x_train to be a numpy array that supports:
# - np.random.shuffle() (in-place shuffling)
# - .copy() method
# - stacking via np.stack()

np.random.seed(0)
x_train = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    'x_train': x_train,
    'num_slices': 3,
    'different_slices': False
}
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 float, shape (2, 3, 4) — shape (2, 3, 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
find_conv_output_dim Ran
ran on a synthesized input
vganapati/LED_PVAE/models_v2.py
code served (permissive licence) · get_code("4a31f718a33cb710")
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 numpy as np

# Analyze the function:
# - input_length: used as argument to np.zeros, indexed with [0::stride] and [:-kernel_size + 1]
# - stride: used in slicing [0::stride]
# - kernel_size: used in slicing [:-kernel_size + 1]
# All are used numerically, so we need integers

# The function creates an array of size input_length, marks positions at stride intervals,
# then removes the last (kernel_size - 1) elements, and sums.
# For valid execution, we need:
# - input_length: positive integer
# - stride: positive integer (stride >= 1)
# - kernel_size: positive integer (kernel_size >= 1, typically kernel_size <= input_length)

input_length = 10
stride = 2
kernel_size = 3

ARGS = {
    "input_length": input_length,
    "stride": stride,
    "kernel_size": kernel_size
}
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 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
find_fpm_params Ran
ran on a synthesized input
vganapati/LED_PVAE/SyntheticMNIST_functions.py
code served (permissive licence) · get_code("a2ad764cfc5c8c3d")
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.

import numpy as np

ARGS = {
    'N_obj': np.array([128, 128]),
    'LED_radius': 8,
    'LED_radius_inner': 2,
    'upsample_factor': 2,
    'dpix_c': 6.5,
    'wavelength': 0.518,
    'NA': 0.5,
    'mag': 20.0,
    'ds_led_x': 4000.0,
    'ds_led_y': 4000.0,
    'z_led': 69500.0,
}
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 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
pupilGen Ran
ran on a synthesized input
vganapati/LED_PVAE/dpc_algorithm.py
code served (permissive licence) · get_code("fe3dc87a0390d22f")
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 2, dtype family float, shape (3, 4) 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 1D spatial frequency coordinates
fxlin = np.linspace(-100, 100, 4)
fylin = np.linspace(-50, 50, 3)

# Set wavelength and numerical aperture parameters
wavelength = 0.5e-6  # 500 nm in meters
na = 0.9  # numerical aperture
na_in = 0.0  # no inner aperture

ARGS = {
    "fxlin": fxlin,
    "fylin": fylin,
    "wavelength": wavelength,
    "na": na,
    "na_in": na_in
}
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 2, dtype family float, shape (3, 4) — shape (3, 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

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

In computational imaging, hardware for signal sampling and software for object reconstruction are designed in tandem for improved capability. Examples of such systems include computed tomography (CT), magnetic resonance imaging (MRI), and superresolution microscopy. In contrast to more traditional cameras, in these devices, indirect measurements are taken and computational algorithms are used for reconstruction. This allows for advanced capabilities such as super-resolution or 3dimensional imaging, pushing forward the frontier of scientific discovery. However, these techniques generally require a large number of measurements, causing low throughput, motion artifacts, and/or radiation damage, limiting applications. Datadriven approaches to reducing the number of measurements needed have been proposed, but they predominately require a ground truth or reference dataset, which may be impossible to collect. This work outlines a self-supervised approach and explores the future work that is necessary to make such a technique usable for real applications. Light-emitting diode (LED) array microscopy, a modality that allows visualization of transparent objects in two and three dimensions with high resolution and field-of-view, is used as an illustrative example.

For agents

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

get_harvested_code_for_paper("2210.16709")
get_code_for_paper("2210.16709")
have("2210.16709")

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

curl https://syntology.ai/api/ran/2210.16709.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.16709.svg)](https://syntology.ai/paper/2210.16709)

Connect an agent — have() is free.