SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.08802 · 2020

Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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, 2 violated it and 3 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2003.08802.json · badge: /api/ran/2003.08802.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
limaosen0/DMGNN community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
define_actions Ran
ran on a synthesized input
limaosen0/DMGNN/cmu-long/processor/data_tools.py
code served (permissive licence) · get_code("4cce013f2ec81966")
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

ARGS = {
    'action': 'walking'
}
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
get_hop_distance Ran
ran; our contract draft was wrong, not the code
limaosen0/DMGNN/cmu-long/net/utils/graph.py
pointer only (licence: MIT); the stored copy get_code serves, from zechengli19/uni-sign, is pointer only (licence: NONE) · get_code("c257ac36cba643a2")
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 zechengli19/uni-sign, 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.

load_data Ran
ran on a synthesized input
limaosen0/DMGNN/cmu-long/processor/data_tools.py
code served (permissive licence) · get_code("95aee57e66890145")
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
import os
import tempfile
import shutil

# Create a temporary directory structure with test data files
temp_dir = tempfile.mkdtemp()

# Define actions
actions = ['walk', 'run']

# Create directory structure and data files
for action in actions:
    action_dir = os.path.join(temp_dir, action)
    os.makedirs(action_dir, exist_ok=True)
    
    # Create 2 example files per action
    for examp_index in range(1, 3):
        filename = os.path.join(action_dir, f'{action}_{examp_index}.txt')
        # Create sample data: 4 timesteps, 3 dimensions
        data = np.random.rand(4, 3).astype(np.float32)
        np.savetxt(filename, data, delimiter=',', fmt='%.6f')

ARGS = {
    'data_path': temp_dir,
    'actions': actions
}
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
node2edge Ran
ran on a synthesized input
limaosen0/DMGNN/cmu-long/net/utils/operation.py
code served (permissive licence) · get_code("8873d3a3fa4ec3fc")
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 3, dtype family float, shape (2, 4, 10) 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)

# Analyze the function:
# - x: used in matmul with rel_rec and rel_send, result has dim=2 (indexing [..., 2])
# - rel_rec: matmul with x to produce receivers
# - rel_send: matmul with x to produce senders
# - The function does matmul(rel_rec, x) and matmul(rel_send, x)
# - Results are concatenated on dim=2
# - This suggests x is shape (batch, num_nodes, features)
# - rel_rec and rel_send are (num_edges, num_nodes) for mapping

batch_size = 2
num_nodes = 3
num_edges = 4
node_features = 5

# x: (batch, num_nodes, node_features)
x = torch.randn(batch_size, num_nodes, node_features)

# rel_rec: (num_edges, num_nodes) - receiver matrix
# When matmul with (batch, num_nodes, node_features) gives (batch, num_edges, node_features)
rel_rec = torch.randn(num_edges, num_nodes)

# rel_send: (num_edges, num_nodes) - sender matrix
rel_send = torch.randn(num_edges, num_nodes)

ARGS = {
    "x": x,
    "rel_rec": rel_rec,
    "rel_send": rel_send,
}
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 3, dtype family float, shape (2, 4, 10) — shape (2, 4, 10) 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
normalize_digraph Ran
ran, violated the contract we drafted
limaosen0/DMGNN/cmu-long/net/utils/graph.py
pointer only (licence: MIT); the stored copy get_code serves, from zechengli19/uni-sign, is pointer only (licence: NONE) · get_code("8158f4435afa26b7")
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 zechengli19/uni-sign, 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.

normalize_undigraph Ran
ran, violated the contract we drafted
limaosen0/DMGNN/cmu-long/net/utils/graph.py
code served (permissive licence) · get_code("f3dfe2628c96a73d")
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 (4, 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 adjacency matrix for an undirected graph
# Using a 4x4 matrix with some connections
A = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 1],
    [0, 1, 1, 0]
], dtype=np.float32)

ARGS = {
    "A": A
}
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 (4, 4) — shape (4, 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
read_txt_as_data Ran
ran, honoured the contract we drafted
limaosen0/DMGNN/cmu-long/processor/data_tools.py
pointer only (licence: MIT); the stored copy get_code serves, from mediabrain-sjtu/auxformer, is pointer only (licence: NONE) · get_code("238bc05bde05cf2f")
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 mediabrain-sjtu/auxformer, 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.

edge2node_mean Not yet run
unverified (harvested, no recorded run)
limaosen0/DMGNN/cmu-long/net/utils/operation.py
code served (permissive licence) · get_code("4ffc67c1b5c7a144")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 later) and 4 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_hop_distance 11 other papers
1 dated earlier, 10 later · 3 only as an assembly brick
1904.12659 (2019-04)
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
Zhu_Modeling_the_Relative_Visual_Tempo_for_Self-supervised_Skeleton-based_Action_Recognition_ICCV_2023_paper (2023 (year only))
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition
2302.01825 (2023-02)
HDFormer: High-order Directed Transformer for 3D Human Pose Estimation
and 8 more not named here
normalize_digraph 11 other papers
1 dated earlier, 10 later · 3 only as an assembly brick
1904.12659 (2019-04)
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
Zhu_Modeling_the_Relative_Visual_Tempo_for_Self-supervised_Skeleton-based_Action_Recognition_ICCV_2023_paper (2023 (year only))
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition
2302.01825 (2023-02)
HDFormer: High-order Directed Transformer for 3D Human Pose Estimation
and 8 more not named here
normalize_undigraph 7 other papers
1 dated earlier, 6 later
1904.12659 (2019-04)
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
Zhu_Modeling_the_Relative_Visual_Tempo_for_Self-supervised_Skeleton-based_Action_Recognition_ICCV_2023_paper (2023 (year only))
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition
2302.09018 (2023-02)
Self-Supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
and 4 more not named here
read_txt_as_data 1 other paper
1 later
2308.08942 (2023-08)
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction

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 2026-11-21.

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 novel dynamic multiscale graph neural networks (DMGNN) to predict 3D skeleton-based human motions. The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning. This multiscale graph is adaptive during training and dynamic across network layers. Based on this graph, we propose a multiscale graph computational unit (MGCU) to extract features at individual scales and fuse features across scales. The entire model is action-category-agnostic and follows an encoder-decoder framework. The encoder consists of a sequence of MGCUs to learn motion features. The decoder uses a proposed graph-based gate recurrent unit to generate future poses. Extensive experiments show that the proposed DMGNN outperforms state-of-the-art methods in both short and long-term predictions on the datasets of Human 3.6M and CMU Mocap. We further investigate the learned multiscale graphs for the interpretability. The codes could be downloaded from https://github.com/limaosen0/DMGNN.

For agents

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

get_harvested_code_for_paper("2003.08802")
get_code_for_paper("2003.08802")
have("2003.08802")

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

curl https://syntology.ai/api/ran/2003.08802.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.08802.svg)](https://syntology.ai/paper/2003.08802)

Connect an agent — have() is free.