SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.11468 · 2023

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 2 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 7 failures 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/2305.11468.json · badge: /api/ran/2305.11468.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
zhouyuxuanyx/blockgcn canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
downsample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhouyuxuanyx/blockgcn/feeders/tools.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liujf69/MMCL-Action, is pointer only (licence: NONE) · get_code("8b14974e8aa7320f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from liujf69/MMCL-Action, 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.

edge2mat Ran
ran; our contract draft was wrong, not the code
zhouyuxuanyx/blockgcn/graph/tools.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hyer/HDFormer, is pointer only (licence: NONE) · get_code("5f5ae82020ac7ec2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from hyer/HDFormer, 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_k_scale_graph Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhouyuxuanyx/blockgcn/graph/tools.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ai-lh/MotionHiFlow, is pointer only (licence: NONE) · get_code("d3e8dd52d4a2755a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ai-lh/MotionHiFlow, 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_sgp_mat Ran
ran; our contract draft was wrong, not the code
zhouyuxuanyx/blockgcn/graph/tools.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ai-lh/MotionHiFlow, is pointer only (licence: NONE) · get_code("5940d00ced3d0637")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ai-lh/MotionHiFlow, 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.

import_class Ran
ran; our contract draft was wrong, not the code
zhouyuxuanyx/blockgcn/model/BlockGCN.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from iamjeff7/j-va-aagcn, is pointer only (licence: NONE) · get_code("ffed4f85d50832c9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from iamjeff7/j-va-aagcn, 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.

import_class Ran
ran; our contract draft was wrong, not the code
zhouyuxuanyx/blockgcn/torchlight/torchlight/util.py
code served (permissive licence) · get_code("4e946d7c92be9d41")
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 type. 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 sys
import traceback

def import_class(import_str):
    mod_str, _sep, class_str = import_str.rpartition('.')
    __import__(mod_str)
    try:
        return getattr(sys.modules[mod_str], class_str)
    except AttributeError:
        raise ImportError('Class %s cannot be found (%s)' % (class_str, traceback.format_exception(*sys.exc_info())))


# Setup: Create a valid import string that points to a real class
# We'll use a built-in class that exists in a standard module
# 'collections.OrderedDict' is a valid class that can be imported

ARGS = {
    'import_str': 'collections.OrderedDict'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
ngpu Ran
ran, honoured the contract we drafted
zhouyuxuanyx/blockgcn/torchlight/torchlight/gpu.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeiWangR/video-ar, is pointer only (licence: NONE) · get_code("83ed4b272b1e38d0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeiWangR/video-ar, 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.

str2bool Ran
ran, violated the contract we drafted
zhouyuxuanyx/blockgcn/torchlight/torchlight/util.py
code served (permissive licence) · get_code("f017532fc389cbfe")
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 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 argparse

def str2bool(v):
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Setup code to construct valid arguments
ARGS = {
    'v': 'true'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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
str2dict Ran
ran on a synthesized input
zhouyuxuanyx/blockgcn/torchlight/torchlight/util.py
code served (permissive licence) · get_code("1e89b2b546737164")
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 dict. 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

torch.manual_seed(0)

# str2dict takes a string parameter 'v' and evaluates it as a dict constructor call
# The function does: eval(f'dict({v})')
# So 'v' should be a string that, when placed inside 'dict(...)' and eval'd, produces a valid dict

# Examples of valid strings:
# "a=1, b=2" -> dict(a=1, b=2) -> {'a': 1, 'b': 2}
# "key1='value1', key2='value2'" -> dict(key1='value1', key2='value2') -> {'key1': 'value1', 'key2': 'value2'}

ARGS = {
    'v': "x=1, y=2, z='test'"
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
valid_crop_resize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhouyuxuanyx/blockgcn/feeders/tools.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liujf69/MMCL-Action, is pointer only (licence: NONE) · get_code("37939bae213ecfd4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from liujf69/MMCL-Action, 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.

visible_gpu Ran
ran, honoured the contract we drafted
zhouyuxuanyx/blockgcn/torchlight/torchlight/gpu.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeiWangR/video-ar, is pointer only (licence: NONE) · get_code("621e08e84928c5c3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeiWangR/video-ar, 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.

temporal_slice Not yet run
unverified (harvested, no recorded run)
zhouyuxuanyx/blockgcn/feeders/tools.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liujf69/MMCL-Action, is pointer only (licence: NONE) · get_code("2f7f389f0584c97e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from liujf69/MMCL-Action, 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.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 2 the same month, 12 later) and 0 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
str2bool 82 other papers
60 dated earlier, 2 the same month, 17 later, 3 same year, order not determinable
1510.03055 (2015-10)
A Diversity-Promoting Objective Function for Neural Conversation Models
1703.06490 (2017-03)
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
1710.10467 (2017-10)
Generalized End-to-End Loss for Speaker Verification
and 79 more not named here
import_class 18 other papers
9 dated earlier, 9 later · 1 only as an assembly brick
1804.07453 (2018-04)
View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
1911.04131 (2019-11)
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
2008.00188 (2020-08)
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
and 15 more not named here
downsample 10 other papers
5 dated earlier, 5 later
1904.12659 (2019-04)
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
ijcai2022_0511 (2022 (year only))
EGCN: An Ensemble-based Learning Framework for Exploring Effective Skeleton-based Rehabilitation Exercise Assessment
2201.02849 (2022-01)
Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
and 7 more not named here
import_class 10 other papers
4 dated earlier, 1 the same month, 5 later · 2 only as an assembly brick
2104.14466 (2021-04)
3D Human Action Representation Learning via Cross-View Consistency Pursuit
2207.09767 (2022-07)
Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition
2208.05318 (2022-08)
Generative Action Description Prompts for Skeleton-based Action Recognition
and 7 more not named here
temporal_slice 10 other papers
5 dated earlier, 5 later
1904.12659 (2019-04)
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
ijcai2022_0511 (2022 (year only))
EGCN: An Ensemble-based Learning Framework for Exploring Effective Skeleton-based Rehabilitation Exercise Assessment
2201.02849 (2022-01)
Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
and 7 more not named here
edge2mat 7 other papers
3 dated earlier, 4 later
2208.10741 (2022-08)
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
2302.01825 (2023-02)
HDFormer: High-order Directed Transformer for 3D Human Pose Estimation
and 4 more not named here
valid_crop_resize 7 other papers
3 dated earlier, 4 later
2201.02849 (2022-01)
Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
2208.10741 (2022-08)
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
and 4 more not named here
ngpu 4 other papers
2 dated earlier, 2 later
2208.10741 (2022-08)
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
03697 (2024 (year only))
Upper-body Hierarchical Graph for Skeleton Based Emotion Recognition in Assistive Driving
and 1 more not named here
visible_gpu 4 other papers
2 dated earlier, 2 later
2208.10741 (2022-08)
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
03697 (2024 (year only))
Upper-body Hierarchical Graph for Skeleton Based Emotion Recognition in Assistive Driving
and 1 more not named here
str2dict 3 other papers
2 dated earlier, 1 later
2208.10741 (2022-08)
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
03697 (2024 (year only))
Upper-body Hierarchical Graph for Skeleton Based Emotion Recognition in Assistive Driving
get_k_scale_graph 2 other papers
1 dated earlier, 1 later
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
2604.23264 (2026-04)
MotionHiFlow: Text-to-Motion via Hierarchical Flow Matching
get_sgp_mat 2 other papers
1 dated earlier, 1 later
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
2604.23264 (2026-04)
MotionHiFlow: Text-to-Motion via Hierarchical Flow Matching

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

Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacency matrix. However, an inherent flaw has come to light in these cutting-edge models: they tend to optimize the adjacency matrix jointly with the model weights. This process, while seemingly efficient, causes a gradual decay of bone connectivity data, culminating in a model indifferent to the very topology it sought to map. As a remedy, we propose a threefold strategy: (1) We forge an innovative pathway that encodes bone connectivity by harnessing the power of graph distances. This approach preserves the vital topological nuances often lost in conventional GCNs. (2) We highlight an oft-overlooked feature - the temporal mean of a skeletal sequence, which, despite its modest guise, carries highly action-specific information. (3) Our investigation revealed strong variations in joint-to-joint relationships across different actions. This finding exposes the limitations of a single adjacency matrix in capturing the variations of relational configurations emblematic of human movement, which we remedy by proposing an efficient refinement to Graph Convolutions (GC) - the BlockGC. This evolution slashes parameters by a substantial margin (above 40%), while elevating performance beyond original GCNs. Our full model, the BlockGCN, establishes new standards in skeleton-based action recognition for small model sizes. Its high accuracy, notably on the large-scale NTU RGB+D 120 dataset, stand as compelling proof of the efficacy of BlockGCN.

For agents

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

get_harvested_code_for_paper("2305.11468")
get_code_for_paper("2305.11468")
have("2305.11468")

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

curl https://syntology.ai/api/ran/2305.11468.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.11468.svg)](https://syntology.ai/paper/2305.11468)

Connect an agent — have() is free.