SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.12941 · 2022

EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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, 1 violated it and 3 have no contract verdict; 0 failures of our instrument; 4 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/2211.12941.json · badge: /api/ran/2211.12941.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
hirl-team/eurnet-image canonical (classifier label)
classifier basis not recorded on the link
5 ran · 4 no recorded run
FunctionStatusWhere it lives
add_quotation_to_string Ran
ran on a synthesized input
hirl-team/eurnet-image/eurnet/utils/config_utils.py
code served (permissive licence) · get_code("b6e1824d78f8a850")
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 str. 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 numpy as np
from typing import List

def is_number_or_bool_or_none(x):
    try:
        float(x)
        return True
    except ValueError:
        return x in ['True', 'False', 'None']

def add_quotation_to_string(s: str, split_chars: List[str]=None) -> str:
    if split_chars is None:
        split_chars = ['[', ']', '{', '}', ',', ' ']
        if '{' in s and '}' in s:
            split_chars.append(':')
    s_mark, marker = (s, chr(1))
    for split_char in split_chars:
        s_mark = s_mark.replace(split_char, marker)
    s_quoted = ''
    for value in s_mark.split(marker):
        if len(value) == 0:
            continue
        st = s.find(value)
        if is_number_or_bool_or_none(value):
            s_quoted += s[:st] + value
        elif value.startswith("'") and value.endswith("'") or (value.startswith('"') and value.endswith('"')):
            s_quoted += s[:st] + value
        else:
            s_quoted += s[:st] + '"' + value + '"'
        s = s[st + len(value):]
    return s_quoted + s

ARGS = {
    "s": "hello world [1, 2, 3] {key: value}",
    "split_chars": None
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
all_reduce_mean Ran
ran, honoured the contract we drafted
hirl-team/eurnet-image/eurnet/utils/dist.py
code served (permissive licence) · get_code("3dc19396537db789")
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 float, ndim 0, dtype family float, shape () 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
import torch.distributed as dist

torch.manual_seed(0)

# The function all_reduce_mean takes a single parameter 'x'
# Looking at the function body:
# - x is converted to a torch.tensor
# - If world_size > 1, it's moved to cuda and used with dist.all_reduce
# - Otherwise, x is returned as-is
# Since we're CPU-only and dist is not initialized, the function will return x unchanged
# We need to provide a numeric value that can be converted to a tensor

ARGS = {
    "x": 5.0
}
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 float, ndim 0, dtype family float, 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
check_keywords_in_name Ran
ran, violated the contract we drafted
hirl-team/eurnet-image/eurnet/utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("b0a5beb34716d5a6")
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 leaplabthu/inline, 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.

get_params_groups Ran
ran on a synthesized input
hirl-team/eurnet-image/eurnet/utils/misc.py
code served (permissive licence) · get_code("33777b13e9f279e7")
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 list, ndim 1, dtype family float; 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
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal model with parameters that will be categorized
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        # Regular parameters (will be regularized)
        self.weight1 = nn.Parameter(torch.randn(4, 3))
        self.weight2 = nn.Parameter(torch.randn(5, 2))
        
        # Bias parameters (will NOT be regularized - endswith '.bias')
        self.bias1 = nn.Parameter(torch.randn(4))
        
        # 1-D parameter (will NOT be regularized - len(param.shape) == 1)
        self.scale = nn.Parameter(torch.randn(3))
        
        # A parameter that should be skipped via skip_keywords
        self.bn_weight = nn.Parameter(torch.randn(6))

model = SimpleModel()

# Create arguments for the function
ARGS = {
    'model': model,
    'skip_list': (),
    'skip_keywords': ('bn',)
}
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 list, ndim 1, dtype family float — a list 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
is_number_or_bool_or_none Ran
ran on a synthesized input
hirl-team/eurnet-image/eurnet/utils/config_utils.py
code served (permissive licence) · get_code("4f0fc1b40e2da4bc")
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 bool, ndim 0, dtype family float, 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 numpy as np

torch.manual_seed(0)

# The function is_number_or_bool_or_none takes a single parameter 'x'
# It attempts to convert x to float, or checks if x is in ['True', 'False', 'None']
# So x should be something that can be passed to float() or be a string

# Test with a number
x_number = 42

ARGS = {
    'x': x_number
}
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 bool, ndim 0, dtype family float, 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_2d_relative_pos_embed Not yet run
unverified (harvested, no recorded run)
hirl-team/eurnet-image/eurnet/utils/position_embed.py
pointer only (licence: MIT); the stored copy get_code serves, from KHU-AGI/HMDC, is pointer only (licence: NONE) · get_code("571021715428528c")
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 KHU-AGI/HMDC, 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. No invocation recorded.

get_2d_sincos_pos_embed Not yet run
unverified (harvested, no recorded run)
hirl-team/eurnet-image/eurnet/utils/position_embed.py
pointer only (licence: MIT); the stored copy get_code serves, from yunongLiu1/IKEA-Manuals-at-Work, is pointer only (licence: NONE) · get_code("3185afc3e87293ed")
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 yunongLiu1/IKEA-Manuals-at-Work, 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. No invocation recorded.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
hirl-team/eurnet-image/eurnet/utils/position_embed.py
pointer only (licence: MIT); the stored copy get_code serves, from zhangyifei01/LMIM, is pointer only (licence: NONE) · get_code("f10004e059714d42")
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 zhangyifei01/LMIM, 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. No invocation recorded.

param_groups_lrd Not yet run
unverified (harvested, no recorded run)
hirl-team/eurnet-image/eurnet/utils/misc.py
code served (permissive licence) · get_code("915ef88ed1bd4765")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 6 later) and 3 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
get_2d_sincos_pos_embed_from_grid 190 other papers
15 dated earlier, 1 the same month, 174 later · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
get_2d_sincos_pos_embed 95 other papers
11 dated earlier, 1 the same month, 83 later · 33 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 92 more not named here
check_keywords_in_name 31 other papers
8 dated earlier, 23 later
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 28 more not named here
all_reduce_mean 25 other papers
2 dated earlier, 23 later
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2204.09435 (2022-04)
Hephaestus: A large scale multitask dataset towards InSAR understanding
2301.11445 (2023-01)
3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
and 22 more not named here
param_groups_lrd 14 other papers
1 dated earlier, 13 later
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
aaai_25300 (2023 (year only))
Exploring Stochastic Autoregressive Image Modeling for Visual Representation
2301.11445 (2023-01)
3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
and 11 more not named here
get_2d_relative_pos_embed 4 other papers
1 dated earlier, 3 later
2206.00272 (2022-06)
Vision GNN: An Image is Worth Graph of Nodes
2304.04269 (2023-04)
HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation
2310.16175 (2023-10)
G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation
and 1 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

Modeling spatial relationship in the data remains critical across many different tasks, such as image classification, semantic segmentation and protein structure understanding. Previous works often use a unified solution like relative positional encoding. However, there exists different kinds of spatial relations, including short-range, medium-range and long-range relations, and modeling them separately can better capture the focus of different tasks on the multi-range relations (e.g., short-range relations can be important in instance segmentation, while long-range relations should be upweighted for semantic segmentation). In this work, we introduce the EurNet for Efficient multi-range relational modeling. EurNet constructs the multi-relational graph, where each type of edge corresponds to short-, medium- or long-range spatial interactions. In the constructed graph, EurNet adopts a novel modeling layer, called gated relational message passing (GRMP), to propagate multi-relational information across the data. GRMP captures multiple relations within the data with little extra computational cost. We study EurNets in two important domains for image and protein structure modeling. Extensive experiments on ImageNet classification, COCO object detection and ADE20K semantic segmentation verify the gains of EurNet over the previous SoTA FocalNet. On the EC and GO protein function prediction benchmarks, EurNet consistently surpasses the previous SoTA GearNet. Our results demonstrate the strength of EurNets on modeling spatial multi-relational data from various domains. The implementations of EurNet for image modeling are available at https://github.com/hirl-team/EurNet-Image . The implementations for other applied domains/tasks will be released soon.

For agents

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

get_harvested_code_for_paper("2211.12941")
get_code_for_paper("2211.12941")
have("2211.12941")

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

curl https://syntology.ai/api/ran/2211.12941.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.12941.svg)](https://syntology.ai/paper/2211.12941)

Connect an agent — have() is free.