SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.02584 · CVPR · 2023

Super-Resolution Neural Operator

Min Wei, Xuesong Zhang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure 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/2303.02584.json · badge: /api/ran/2303.02584.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
2y7c3/super-resolution-neural-operator marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
2y7c3/super-resolution-neural-operator/models/sronet.py
code served (permissive licence) · get_code("47640adea5c38b64")
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, LayerNorm: 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
import torch.nn as nn

torch.manual_seed(0)

class LayerNorm(nn.Module):

    def __init__(self, d_model, eps=1e-05):
        super(LayerNorm, self).__init__()
        self.weight = nn.Parameter(torch.ones(d_model))
        self.bias = nn.Parameter(torch.zeros(d_model))
        self.eps = eps

    def forward(self, x):
        mean = x.mean(-1, keepdim=True)
        std = x.std(-1, keepdim=True)
        out = (x - mean) / (std + self.eps)
        out = self.weight * out + self.bias
        return out


# Create arguments for LayerNorm constructor
d_model = 4
eps = 1e-05

# Test by instantiating the module
layer_norm_instance = LayerNorm(d_model=d_model, eps=eps)

# Create a test input tensor (batch_size=2, seq_len=3, d_model=4)
test_input = torch.randn(2, 3, 4)

# Execute forward pass to verify it works
output = layer_norm_instance(test_input)

ARGS = {
    'd_model': d_model,
    'eps': eps
}
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 LayerNorm — 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 LayerNorm 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
make_coord Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
2y7c3/super-resolution-neural-operator/models/sronet.py
code served (permissive licence) · get_code("4cfa61b9787a4c6b")
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 (24, 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

torch.manual_seed(0)

# shape: tuple of integers representing grid dimensions
# ranges: optional list of tuples specifying (v0, v1) for each dimension
# flatten: boolean controlling whether to flatten the output

ARGS = {
    "shape": (2, 3, 4),
    "ranges": [(-1, 1), (-1, 1), (-1, 1)],
    "flatten": True
}
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 (24, 3) — shape (24, 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
simple_attn Ran
ran on a synthesized input · constructed an object; no result was computed
2y7c3/super-resolution-neural-operator/models/sronet.py
code served (permissive licence) · get_code("8d385b6da111afab")
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, simple_attn: 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'midc': 8,
    'heads': 2,
}
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 simple_attn — 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 simple_attn 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
SRNO Not yet run
unverified (harvested, no recorded run)
2y7c3/super-resolution-neural-operator/models/sronet.py
code served (permissive licence) · get_code("6daa38bcd54a8d31")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 1 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
LayerNorm
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2507.23521 (2025-07)
JPEG Processing Neural Operator for Backward-Compatible Coding
make_coord
brick of this paper's assembly: helper
1 other paper
1 the same month
2303.16513 (2023-03)
Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution

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

We propose Super-resolution Neural Operator (SRNO), a deep operator learning framework that can resolve highresolution (HR) images at arbitrary scales from the lowresolution (LR) counterparts. Treating the LR-HR image pairs as continuous functions approximated with different grid sizes, SRNO learns the mapping between the corresponding function spaces. From the perspective of approximation theory, SRNO first embeds the LR input into a higher-dimensional latent representation space, trying to capture sufficient basis functions, and then iteratively approximates the implicit image function with a kernel integral mechanism, followed by a final dimensionality reduction step to generate the RGB representation at the target coordinates. The key characteristics distinguishing SRNO from prior continuous SR works are: 1) the kernel integral in each layer is efficiently implemented via the Galerkintype attention, which possesses non-local properties in the spatial domain and therefore benefits the grid-free continuum; and 2) the multilayer attention architecture allows for the dynamic latent basis update, which is crucial for SR problems to "hallucinate" high-frequency information from the LR image. Experiments show that SRNO outperforms existing continuous SR methods in terms of both accuracy and running time. Our code is at https://github.com/ 2y7c3/Super-Resolution-Neural-Operator.

For agents

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

get_harvested_code_for_paper("2303.02584")
get_code_for_paper("2303.02584")
have("2303.02584")

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

curl https://syntology.ai/api/ran/2303.02584.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.02584.svg)](https://syntology.ai/paper/2303.02584)

Connect an agent — have() is free.