SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.00225 · AAAI · 2022

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

Zhe Jiang, Jiahao Ji, Jingyuan Wang, Hu Zhang, Jiawei Jiang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 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; 0 failures of our instrument; 5 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/2209.00225.json · badge: /api/ran/2209.00225.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
echo-ji/stden marked official in Papers with Code
Papers with Code archive
2 ran · 5 no recorded run
FunctionStatusWhere it lives
DiffeqSolver Ran
ran on a synthesized input · constructed an object; no result was computed
echo-ji/stden/model/stden_model.py
code served (permissive licence) · get_code("83b0c81d8d748e1c")
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, DiffeqSolver: 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 torchdiffeq import odeint

torch.manual_seed(0)

# Define a minimal ODE function that odeint can work with
class ODEFunc(nn.Module):
    def __init__(self, latent_dim):
        super(ODEFunc, self).__init__()
        self.latent_dim = latent_dim
        self.nfe = 0
        self.fc = nn.Linear(latent_dim, latent_dim)
    
    def forward(self, t, y):
        self.nfe += 1
        return self.fc(y)

# Create instances for the DiffeqSolver
latent_dim = 4
odefunc = ODEFunc(latent_dim)
method = "dopri"
odeint_rtol = 0.0001
odeint_atol = 1e-05

# Build arguments dict
ARGS = {
    "odefunc": odefunc,
    "method": method,
    "latent_dim": latent_dim,
    "odeint_rtol": odeint_rtol,
    "odeint_atol": odeint_atol,
}

# Verify the setup by creating a DiffeqSolver instance
solver = nn.Module.__new__(type('DiffeqSolver', (nn.Module,), {
    '__init__': lambda self, odefunc, method, latent_dim, odeint_rtol=0.0001, odeint_atol=1e-05: (
        nn.Module.__init__(self),
        setattr(self, 'ode_method', method),
        setattr(self, 'odefunc', odefunc),
        setattr(self, 'latent_dim', latent_dim),
        setattr(self, 'rtol', odeint_rtol),
        setattr(self, 'atol', odeint_atol),
    ),
    'forward': lambda self, first_point, time_steps_to_pred: None
}))

ARGS
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchdiffeq — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DiffeqSolver — 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 DiffeqSolver 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
LayerParams Ran
ran on a synthesized input · constructed an object; no result was computed
echo-ji/stden/model/stden_model.py
code served (permissive licence) · get_code("6c7a1d4dc516d7ae")
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, LayerParams: 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
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal nn.Module that can have parameters registered to it
class MinimalRNNNetwork(nn.Module):
    def __init__(self):
        super().__init__()
    
    def forward(self, x):
        return x

# Instantiate the RNN network
rnn_network = MinimalRNNNetwork()

# Define arguments for LayerParams constructor
ARGS = {
    'rnn_network': rnn_network,
    'layer_type': 'lstm'
}
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 LayerParams — 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 LayerParams 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
Decoder Not yet run
unverified (harvested, no recorded run)
echo-ji/stden/model/stden_model.py
code served (permissive licence) · get_code("aca25da3501c729d")
How it ran

no invocation recorded.

EncoderAttrs Not yet run
unverified (harvested, no recorded run)
echo-ji/stden/model/stden_model.py
code served (permissive licence) · get_code("6e4478656a8bbe0b")
How it ran

no invocation recorded.

Encoder_z0_RNN Not yet run
unverified (harvested, no recorded run)
echo-ji/stden/model/stden_model.py
code served (permissive licence) · get_code("b685e4a7cb7d510c")
How it ran

no invocation recorded.

ODEFunc Not yet run
unverified (harvested, no recorded run)
echo-ji/stden/model/stden_model.py
code served (permissive licence) · get_code("bace489fae3c657f")
How it ran

no invocation recorded.

STDENModel Not yet run
unverified (harvested, no recorded run)
echo-ji/stden/model/stden_model.py
code served (permissive licence) · get_code("00c96f18610fb97e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
DiffeqSolver
brick of this paper's assembly: model
1 other paper
1 later
2402.03784 (2024-02)
AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
LayerParams
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2402.03784 (2024-02)
AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality 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 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio-Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications.

For agents

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

get_harvested_code_for_paper("2209.00225")
get_code_for_paper("2209.00225")
have("2209.00225")

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

curl https://syntology.ai/api/ran/2209.00225.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.00225.svg)](https://syntology.ai/paper/2209.00225)

Connect an agent — have() is free.