SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.00943 · NeurIPS · 2024

State Space Models on Temporal Graphs: A First-Principles Study

Liang Chen, Jintang Li, Ruofan Wu, Zibin Zheng, Xinzhou Jin, Boqun Ma

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 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/2406.00943.json · badge: /api/ran/2406.00943.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
edisonleeeee/graphssm canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
EdisonLeeeee/GraphSSM canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
Conv1DTokenMixer Ran
ran on a synthesized input · constructed an object; no result was computed
edisonleeeee/graphssm/graphssm/models/s6.py
code served (permissive licence) · get_code("ae2b3228b0986ca9")
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, Conv1DTokenMixer: 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)

# Construct arguments for Conv1DTokenMixer
d_input = 4
window_size = 2
use_padding = True

# Create a small list of tensors to pass as xs
# The forward method expects xs to be a list that gets stacked
# Shape should be (d_input,) per element since it stacks on dim=-1
batch_size = 3
xs = [torch.randn(d_input) for _ in range(batch_size)]

ARGS = {
    'd_input': d_input,
    'window_size': window_size,
    'use_padding': use_padding,
}

# Test instantiation and forward pass
if __name__ == "__main__":
    model = nn.Conv1DTokenMixer(**ARGS)
    output = model(xs)
    print(f"Output shape: {output.shape}")
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv1DTokenMixer — 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 Conv1DTokenMixer 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
DiagonalS6SSM Ran
ran on a synthesized input · constructed an object; no result was computed
edisonleeeee/graphssm/graphssm/models/s6.py
code served (permissive licence) · get_code("6c042e958fcb26b8")
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, DiagonalS6SSM: 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
from torch_geometric.data import Data

torch.manual_seed(0)

# Create minimal snapshot data objects
# The forward method calls data.x and data.edge_index
snapshots = [
    Data(x=torch.randn(2, 4), edge_index=torch.tensor([[0, 1], [1, 0]], dtype=torch.long)),
    Data(x=torch.randn(2, 4), edge_index=torch.tensor([[0, 1], [1, 0]], dtype=torch.long)),
]

ARGS = {
    'in_channels': 4,
    'out_channels': 3,
    'hidden_channels': 8,
    'ssm_format': 'siso',
    'd_state': 4,
    'num_layers': 2,
    'token_mixer': 'conv1d',
    'pre_token_mix': False,
    'bn': False,
    'layer': 'sage',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, numpy, torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DiagonalS6SSM — 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 DiagonalS6SSM 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
InterpolationTokenMixer Ran
ran on a synthesized input · constructed an object; no result was computed
edisonleeeee/graphssm/graphssm/models/s6.py
code served (permissive licence) · get_code("35b7a7397b15dd4d")
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, InterpolationTokenMixer: 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)

# The InterpolationTokenMixer constructor takes d_input as a parameter
# d_input is the feature dimension used in Linear layers
d_input = 4

ARGS = {
    "d_input": d_input,
}
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 InterpolationTokenMixer — 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 InterpolationTokenMixer 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
prepare_idx Ran
ran; our contract draft was wrong, not the code
EdisonLeeeee/GraphSSM/graphssm/data.py
code served (permissive licence) · get_code("25331b0bbe0601c9")
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 slice. 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)

# Test case 1: integer input
idx_int = 5

# Test case 2: list input
idx_list = [0, 2, 4]

# Test case 3: tuple input
idx_tuple = (1, 3)

# Test case 4: slice input
idx_slice = slice(0, 3)

# Test case 5: long tensor input
idx_long_tensor = torch.tensor([0, 1, 2], dtype=torch.long)

# Test case 6: bool tensor input
idx_bool_tensor = torch.tensor([True, False, True, False], dtype=torch.bool)

# We'll test with the integer case as the main example
ARGS = {
    "idx": 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 slice — a slice output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a slice 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
to_data Ran
ran; our contract draft was wrong, not the code
EdisonLeeeee/GraphSSM/graphssm/ssm_tmall.py
code served (permissive licence) · get_code("3d125024d26e932f")
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 Data. 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
from torch_geometric.data import Data

torch.manual_seed(0)

class TemporalData:
    def __init__(self, x, edge_index, y):
        self.x = x
        self.edge_index = edge_index
        self.y = y

# Create small tensors with distinct dimensions
x = torch.randn(2, 4)  # 2 nodes, 4 features
edge_index = torch.tensor([[0, 1], [1, 0]], dtype=torch.long)  # 2 edges
y = torch.tensor([0, 1], dtype=torch.long)  # 2 labels

temporal_data = TemporalData(x=x, edge_index=edge_index, y=y)

ARGS = {
    "temporal_data": temporal_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Data — a Data 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
InitStrategyS6 Not yet run
unverified (harvested, no recorded run)
edisonleeeee/graphssm/graphssm/models/s6.py
code served (permissive licence) · get_code("89c1c5615ffd983d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Over the past few years, research on deep graph learning has shifted from static graphs to temporal graphs in response to real-world complex systems that exhibit dynamic behaviors. In practice, temporal graphs are formalized as an ordered sequence of static graph snapshots observed at discrete time points. Sequence models such as RNNs or Transformers have long been the predominant backbone networks for modeling such temporal graphs. Yet, despite the promising results, RNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity. Recently, state space models (SSMs), which are framed as discretized representations of an underlying continuous-time linear dynamical system, have garnered substantial attention and achieved breakthrough advancements in independent sequence modeling. In this work, we undertake a principled investigation that extends SSM theory to temporal graphs by integrating structural information into the online approximation objective via the adoption of a Laplacian regularization term. The emergent continuous-time system introduces novel algorithmic challenges, thereby necessitating our development of GRAPHSSM, a graph state space model for modeling the dynamics of temporal graphs. Extensive experimental results demonstrate the effectiveness of our GRAPHSSM framework across various temporal graph benchmarks.

For agents

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

get_harvested_code_for_paper("2406.00943")
get_code_for_paper("2406.00943")
have("2406.00943")

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

curl https://syntology.ai/api/ran/2406.00943.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.00943.svg)](https://syntology.ai/paper/2406.00943)

Connect an agent — have() is free.