SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.08770 · CVPR · 2022

GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning

Siheng Chen, Ya Zhang, Chenxin Xu, Maosen Li, Zhenyang Ni

arXiv · PDF · Open in the Atlas

Code that ran

12 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 5 failures of our instrument; 7 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/2204.08770.json · badge: /api/ran/2204.08770.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
mediabrain-sjtu/groupnet marked official in Papers with Code
Papers with Code archive
12 ran · 7 no recorded run
FunctionStatusWhere it lives
DecomposeBlock Ran
ran on a synthesized input · constructed an object; no result was computed
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("e3e7054af55c8e24")
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, DecomposeBlock: 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
from torch import nn

torch.manual_seed(0)

# Define ARGS dict with all parameters for DecomposeBlock
ARGS = {
    'past_len': 10,
    'future_len': 5,
    'input_dim': 8
}
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 DecomposeBlock — 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 DecomposeBlock 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
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("02e5a62dbbc9ab28")
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, MLP: 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 = {
    'input_dim': 4,
    'output_dim': 3,
    'hidden_size': (1024, 512),
    'activation': 'relu',
    'discrim': False,
    'dropout': -1
}
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 MLP — 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 MLP 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
MLP2 Ran
ran on a synthesized input · constructed an object; no result was computed
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("79cb60aaae6dc184")
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, MLP2: 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'input_dim': 4,
    'hidden_dims': (128, 128),
    'activation': 'tanh'
}
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 MLP2 — 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 MLP2 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
MLP_dict_softmax Ran
ran on a synthesized input · constructed an object; no result was computed
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("e1b62c2a7bfe079b")
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, MLP_dict_softmax: the run constructed the object and did not call it, so no result was computed. 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 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'input_dim': 4,
    'output_dim': 3,
    'hidden_size': (8, 6),
    'activation': 'relu',
    'discrim': False,
    'dropout': -1,
    'edge_types': 5
}
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 MLP_dict_softmax — 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 MLP_dict_softmax 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
Normal Ran
ran on a synthesized input · constructed an object; no result was computed
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("f14cfe7a9278509d")
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, Normal: 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

torch.manual_seed(0)

# Construct arguments for Normal.__init__
# The function accepts three parameters: mu, logvar, and params

# Create small tensors with batch size 2 and dimension 4
mu = torch.randn(2, 4)
logvar = torch.randn(2, 4)
params = None  # We'll test the mu/logvar path

ARGS = {
    "mu": mu,
    "logvar": logvar,
    "params": params
}
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 Normal — 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 Normal 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
PositionalAgentEncoding Ran
ran on a synthesized input
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("c4350ee83527a499")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, 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 numpy as np
from torch import nn

class PositionalAgentEncoding(nn.Module):

    def __init__(self, d_model, dropout=0.1, max_t_len=200, concat=True):
        super(PositionalAgentEncoding, self).__init__()
        self.dropout = nn.Dropout(p=dropout)
        self.concat = concat
        self.d_model = d_model
        if concat:
            self.fc = nn.Linear(2 * d_model, d_model)
        pe = self.build_pos_enc(max_t_len)
        self.register_buffer('pe', pe)

    def build_pos_enc(self, max_len):
        pe = torch.zeros(max_len, self.d_model)
        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, self.d_model, 2).float() * (-np.log(10000.0) / self.d_model))
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        return pe

    def get_pos_enc(self, num_t, num_a, t_offset):
        pe = self.pe[t_offset:num_t + t_offset, :]
        pe = pe[None].repeat(num_a, 1, 1)
        return pe

    def get_agent_enc(self, num_t, num_a, a_offset):
        ae = self.ae[a_offset:num_a + a_offset, :]
        ae = ae.repeat(num_t, 1, 1)
        return ae

    def forward(self, x, num_a, t_offset=0):
        num_t = x.shape[1]
        pos_enc = self.get_pos_enc(num_t, num_a, t_offset)
        if self.concat:
            feat = [x, pos_enc]
            x = torch.cat(feat, dim=-1)
            x = self.fc(x)
        else:
            x += pos_enc
        return self.dropout(x)


INIT_ARGS = {
    'd_model': 4,
    'dropout': 0.1,
    'max_t_len': 50,
    'concat': True
}

ARGS = {
    'x': torch.randn(2, 3, 4),
    'num_a': 2,
    't_offset': 0
}

if __name__ == '__main__':
    model = PositionalAgentEncoding(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
edge_aggregation Ran
ran on a synthesized input · constructed an object; no result was computed
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("115943afcd1d7f92")
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, edge_aggregation: 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'input_dim': 4,
    'output_dim': 8,
    'hidden_size': (64, 32),
    'activation': 'relu',
    'discrim': False,
    'dropout': -1,
    'edge_types': 3
}
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 edge_aggregation — 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 edge_aggregation 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
encode_onehot Ran
ran; our contract draft was wrong, not the code
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("3ab88254add4c192")
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 int, shape (6, 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

# The function encode_onehot takes labels as input
# labels should be an array-like of class labels (integers, strings, etc.)
# The function creates a one-hot encoding mapping for unique classes

# Create sample labels with multiple distinct classes
labels = np.array([0, 1, 2, 1, 0, 2], dtype=int)

ARGS = {
    "labels": labels
}
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 int, shape (6, 3) — shape (6, 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
gumbel_softmax Ran
ran; our contract draft was wrong, not the code
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("422ac583248740e3")
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. 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create logits tensor: [batch_size=2, n_class=4]
logits = torch.randn(2, 4, requires_grad=True)

# Define ARGS with all parameters for gumbel_softmax
ARGS = {
    "logits": logits,
    "tau": 1.0,
    "hard": False,
    "eps": 1e-10,
}
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
gumbel_softmax_sample Ran
ran; our contract draft was wrong, not the code
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("2cecb1236580790d")
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. 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create a small logits tensor (batch_size=2, num_classes=4)
logits = torch.randn(2, 4)

# Define ARGS with all parameters for gumbel_softmax_sample
ARGS = {
    "logits": logits,
    "tau": 1.0,
    "eps": 1e-10
}
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
my_softmax Ran
ran; our contract draft was wrong, not the code
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("2d3a9f3a787bd820")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a small tensor for testing
# The function transposes along axis and applies softmax, then transposes back
# We need a 2D tensor at minimum for transpose to work meaningfully
input_tensor = torch.randn(2, 4)

ARGS = {
    "input": input_tensor,
    "axis": 1
}
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
sample_gumbel Ran
ran; our contract draft was wrong, not the code
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("3a4679b159e12db9")
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)

ARGS = {
    "shape": (2, 4),
    "eps": 1e-10,
}
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
Decoder Not yet run
unverified (harvested, no recorded run)
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("f6bd7ed0195d6371")
How it ran

no invocation recorded.

FutureEncoder Not yet run
unverified (harvested, no recorded run)
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("3f701c6c089fdec8")
How it ran

no invocation recorded.

GroupNet Not yet run
unverified (harvested, no recorded run)
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("5924141847b3fa88")
How it ran

no invocation recorded.

MS_HGNN_hyper Not yet run
unverified (harvested, no recorded run)
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("3a8a6ecf7bac048a")
How it ran

no invocation recorded.

MS_HGNN_oridinary Not yet run
unverified (harvested, no recorded run)
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("4eb731b79e21f6be")
How it ran

no invocation recorded.

PastEncoder Not yet run
unverified (harvested, no recorded run)
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("4e8c0eb4817fc6f3")
How it ran

no invocation recorded.

initialize_weights Not yet run
unverified (harvested, no recorded run)
mediabrain-sjtu/groupnet/model/GroupNet_nba.py
code served (permissive licence) · get_code("439a7633d36b0d3d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 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, 2 later) and 15 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
encode_onehot
brick of this paper's assembly: helper
12 other papers
8 dated earlier, 3 later, 1 same year, order not determinable
1609.02907 (2016-09)
Semi-Supervised Classification with Graph Convolutional Networks
1710.10903 (2017-10)
Graph Attention Networks
1803.03735 (2018-03)
Attention-based Graph Neural Network for Semi-supervised Learning
and 9 more not named here
MLP
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2207.10435 (2022-07)
Human Trajectory Prediction via Neural Social Physics
2308.08942 (2023-08)
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
my_softmax
brick of this paper's assembly: helper
2 other papers
2 dated earlier
1802.04687 (2018-02)
Neural Relational Inference for Interacting Systems
1904.12659 (2019-04)
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
gumbel_softmax
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1904.12659 (2019-04)
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition

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

Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction. However, previous works only consider pair-wise interactions with limited relational reasoning. To promote more comprehensive interaction modeling for relational reasoning, we propose GroupNet, a multiscale hypergraph neural network, which is novel in terms of both interaction capturing and representation learning. From the aspect of interaction capturing, we propose a trainable multiscale hypergraph to capture both pair-wise and group-wise interactions at multiple group sizes. From the aspect of interaction representation learning, we propose a three-element format that can be learnt end-to-end and explicitly reason some relational factors including the interaction strength and category. We apply GroupNet into both CVAE-based prediction system and previous state-of-the-art prediction systems for predicting socially plausible trajectories with relational reasoning. To validate the ability of relational reasoning, we experiment with synthetic physics simulations to reflect the ability to capture group behaviors, reason interaction strength and interaction category. To validate the effectiveness of prediction, we conduct extensive experiments on three real-world trajectory prediction datasets, including NBA, SDD and ETH-UCY; and we show that with GroupNet, the CVAE-based prediction system outperforms state-of-the-art methods. We also show that adding GroupNet will further improve the performance of previous state-of-the-art prediction systems.

For agents

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

get_harvested_code_for_paper("2204.08770")
get_code_for_paper("2204.08770")
have("2204.08770")

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

curl https://syntology.ai/api/ran/2204.08770.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.08770.svg)](https://syntology.ai/paper/2204.08770)

Connect an agent — have() is free.