SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.06442 · 2022

Equivariant Graph Mechanics Networks with Constraints

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 2 have no contract verdict; 3 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/2203.06442.json · badge: /api/ran/2203.06442.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
hanjq17/gmn canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
get_rotation_matrix Ran
ran on a synthesized input
hanjq17/gmn/spatial_graph/n_body_system/dataset/physical_objects.py
code served (permissive licence) · get_code("9aaa0db2616bb599")
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, 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

# Construct arguments for get_rotation_matrix
# The function takes:
# - theta: a scalar angle in radians
# - d: a direction vector (array-like with 3 elements: x, y, z)

theta = np.pi / 4  # 45 degrees as example angle

# Direction vector - should be normalized for typical use but function doesn't enforce it
d = np.array([1.0, 0.0, 0.0])  # Unit vector along x-axis

ARGS = {
    'theta': theta,
    'd': d
}
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, 3) — shape (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
get_velocity_attr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hanjq17/gmn/spatial_graph/main_md17.py
code served (permissive licence) · get_code("efc11ed98d6d5af4")
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 2, dtype family float, shape (4, 1) 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)

# Create small tensors for the function
# loc: node locations, shape (num_nodes, feature_dim)
# vel: node velocities, shape (num_nodes, feature_dim)
# rows, cols: edge indices

num_nodes = 5
feature_dim = 4

loc = torch.randn(num_nodes, feature_dim)
vel = torch.randn(num_nodes, feature_dim)

# Create edge indices (rows and cols)
# These should be valid indices into loc and vel
rows = torch.tensor([0, 1, 2, 3])
cols = torch.tensor([1, 2, 3, 4])

ARGS = {
    "loc": loc,
    "vel": vel,
    "rows": rows,
    "cols": cols,
}
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 2, dtype family float, shape (4, 1) — shape (4, 1) 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
projection Ran
ran on a synthesized input
hanjq17/gmn/spatial_graph/n_body_system/dataset/physical_objects.py
code served (permissive licence) · get_code("0f4545be8210f37b")
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 1, dtype family float, shape (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 two small numpy arrays for vector projection
# va: vector a (will be projected onto vb)
# vb: vector b (the basis vector)

va = np.array([1.0, 2.0, 3.0, 4.0])
vb = np.array([1.0, 0.0, 1.0, 0.0])

ARGS = {
    "va": va,
    "vb": vb
}
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 1, dtype family float, shape (4,) — shape (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
unsorted_segment_mean Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hanjq17/gmn/spatial_graph/models/gcl.py
code served (permissive licence) · get_code("bc66f19be57720e7")
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 (2, 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 torch

torch.manual_seed(0)

# Create sample data tensor with shape (batch_size, feature_dim)
# Using distinct sizes: 2 for batch, 4 for features
data = torch.randn(2, 4)

# Create segment_ids tensor that maps each data point to a segment
# Values should be in range [0, num_segments)
segment_ids = torch.tensor([0, 1])

# Number of segments to aggregate into
num_segments = 2

ARGS = {
    "data": data,
    "segment_ids": segment_ids,
    "num_segments": num_segments,
}
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 (2, 4) — shape (2, 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
unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
hanjq17/gmn/spatial_graph/models/gcl.py
code served (permissive licence) · get_code("dfdf6dc1a0720e57")
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 (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 torch
import numpy as np

torch.manual_seed(0)

# Create tiny tensors for testing
# data: shape (batch_size, feature_dim) - the values to sum
# segment_ids: shape (batch_size,) - which segment each row belongs to
# num_segments: int - total number of segments

batch_size = 2
feature_dim = 4
num_segments = 3

data = torch.randn(batch_size, feature_dim)
segment_ids = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    "data": data,
    "segment_ids": segment_ids,
    "num_segments": num_segments,
}
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 Tensor, 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 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
unsorted_segment_mean 20 other papers
4 dated earlier, 16 later · 1 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2102.09844 (2021-02)
E(n) Equivariant Graph Neural Networks
2110.14811 (2021-10)
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
and 17 more not named here
unsorted_segment_sum 19 other papers
4 dated earlier, 15 later · 2 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.02547 (2019-06)
Combining Generative and Discriminative Models for Hybrid Inference
2102.09844 (2021-02)
E(n) Equivariant Graph Neural Networks
and 16 more not named here
get_velocity_attr 5 other papers
5 later
2305.14642 (2023-05)
Newton-Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems
2309.16342 (2023-09)
LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite
2401.11037 (2024-01)
Equivariant Graph Neural Operator for Modeling 3D Dynamics
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

Learning to reason about relations and dynamics over multiple interacting objects is a challenging topic in machine learning. The challenges mainly stem from that the interacting systems are exponentially-compositional, symmetrical, and commonly geometrically-constrained. Current methods, particularly the ones based on equivariant Graph Neural Networks (GNNs), have targeted on the first two challenges but remain immature for constrained systems. In this paper, we propose Graph Mechanics Network (GMN) which is combinatorially efficient, equivariant and constraint-aware. The core of GMN is that it represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object. In this manner, the geometrical constraints are implicitly and naturally encoded in the forward kinematics. Moreover, to allow equivariant message passing in GMN, we have developed a general form of orthogonality-equivariant functions, given that the dynamics of constrained systems are more complicated than the unconstrained counterparts. Theoretically, the proposed equivariant formulation is proved to be universally expressive under certain conditions. Extensive experiments support the advantages of GMN compared to the state-of-the-art GNNs in terms of prediction accuracy, constraint satisfaction and data efficiency on the simulated systems consisting of particles, sticks and hinges, as well as two real-world datasets for molecular dynamics prediction and human motion capture.

For agents

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

get_harvested_code_for_paper("2203.06442")
get_code_for_paper("2203.06442")
have("2203.06442")

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

curl https://syntology.ai/api/ran/2203.06442.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.06442.svg)](https://syntology.ai/paper/2203.06442)

Connect an agent — have() is free.