SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.00318 · ICML · 2025

Sub-Sequential Physics-Informed Learning with State Space Model

Jinjun Xiong, Chenhui Xu, Dancheng Liu, Yuting Hu, Jiajie Li, Ruiyang Qin, Qingxiao Zheng

arXiv · PDF · Open in the Atlas

Code that ran

3 of 10 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; 1 failure of our instrument; 7 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2502.00318.json · badge: /api/ran/2502.00318.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
minihuihui/pinnmamba canonical (classifier label)
classifier basis: classifier_2025
3 ran · 7 no recorded run
FunctionStatusWhere it lives
compute_ntk Ran
ran; our contract draft was wrong, not the code
minihuihui/pinnmamba/wave_pinnmamba.py
code served (permissive licence) · get_code("6e905a5727433888")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 2) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:20:48Z). 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)

# J1 and J2 are Jacobian matrices used in NTK computation
# They should be 2D tensors where matmul(J1, J2.T) is valid
# J1 shape: (batch_size, feature_dim)
# J2 shape: (batch_size, feature_dim)

J1 = torch.randn(2, 4)
J2 = torch.randn(2, 4)

ARGS = {
    "J1": J1,
    "J2": J2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 2) — shape (2, 2) 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
PScan Ran
ran on a synthesized input · constructed an object; no result was computed
minihuihui/pinnmamba/models/PINNMamba.py
code served (permissive licence) · get_code("8b60a9d7a50c8950")
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, PScan: 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 math

torch.manual_seed(0)

# PScan.apply takes two arguments: A_in and X_in
# Looking at the forward method:
# A_in : (B, L, D, N)
# X_in : (B, L, D, N)
# where B is batch, L is sequence length (must be power of 2 for pscan), D is feature dim, N is another dim

# Create small tensors with distinct sizes for each dimension
B = 2  # batch size
L = 4  # sequence length (power of 2)
D = 3  # feature dimension
N = 5  # another dimension

A_in = torch.randn(B, L, D, N, requires_grad=True)
X_in = torch.randn(B, L, D, N, requires_grad=True)

ARGS = {
    "A_in": A_in,
    "X_in": X_in,
}
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 PScan — 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 PScan 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
SSM Ran
ran on a synthesized input · constructed an object; no result was computed
minihuihui/pinnmamba/models/PINNMamba.py
code served (permissive licence) · get_code("8fa401ba9b13e4cb")
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, SSM: 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
import math

torch.manual_seed(0)

# SSM requires: in_features, dt_rank, dim_inner, d_state
# Based on the forward method:
# - x has shape (batch, L, in_features)
# - deltaBC_layer outputs (batch, L, dt_rank + 2*d_state)
# - delta has shape (batch, L, dt_rank)
# - B, C have shape (batch, L, d_state)
# - dt_proj_layer takes dt_rank -> dim_inner
# - A_log has shape (dim_inner, d_state)
# - D has shape (dim_inner,)
# - selective_scan_seq expects x with last dim = in_features
# - pscan is called with deltaA (batch, dim_inner, L, d_state) and BX (batch, dim_inner, L, d_state)

ARGS = {
    "in_features": 4,
    "dt_rank": 3,
    "dim_inner": 5,
    "d_state": 2,
}
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 SSM — 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 SSM 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
Encoder Not yet run
unverified (harvested, no recorded run)
minihuihui/pinnmamba/models/PINNMamba.py
code served (permissive licence) · get_code("95d1e9fea2c34b62")
How it ran

no invocation recorded.

EncoderLayer Not yet run
unverified (harvested, no recorded run)
minihuihui/pinnmamba/models/PINNMamba.py
code served (permissive licence) · get_code("324f795e218611c5")
How it ran

no invocation recorded.

Model Not yet run
unverified (harvested, no recorded run)
minihuihui/pinnmamba/models/PINNMamba.py
code served (permissive licence) · get_code("3f7dd75401d52c69")
How it ran

no invocation recorded.

h Not yet run
unverified (harvested, no recorded run)
minihuihui/pinnmamba/reaction_pinnmamba.py
code served (permissive licence) · get_code("1d94d4c45235539f")
How it ran

no invocation recorded.

u_ana Not yet run
unverified (harvested, no recorded run)
minihuihui/pinnmamba/reaction_pinnmamba.py
code served (permissive licence) · get_code("ff28b6f1b4308bf4")
How it ran

no invocation recorded.

u_ana Not yet run
unverified (harvested, no recorded run)
minihuihui/pinnmamba/wave_pinnmamba.py
code served (permissive licence) · get_code("f85efe880ead956a")
How it ran

no invocation recorded.

u_res Not yet run
unverified (harvested, no recorded run)
minihuihui/pinnmamba/convection_pinnmamba.py
code served (permissive licence) · get_code("f51c041b8e73dbdc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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
h 1 other paper
1 dated earlier
2405.14369 (2024-05)
RoPINN: Region Optimized Physics-Informed Neural Networks
u_ana 1 other paper
1 dated earlier
2405.14369 (2024-05)
RoPINN: Region Optimized Physics-Informed Neural Networks
u_ana 1 other paper
1 dated earlier
2405.14369 (2024-05)
RoPINN: Region Optimized Physics-Informed Neural Networks

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

Physics-Informed Neural Networks (PINNs) are a kind of deep-learning-based numerical solvers for partial differential equations (PDEs). Existing PINNs often suffer from failure modes of being unable to propagate patterns of initial conditions. We discover that these failure modes are caused by the simplicity bias of neural networks and the mismatch between PDE's continuity and PINN's discrete sampling. We reveal that the State Space Model (SSM) can be a continuous-discrete articulation allowing initial condition propagation, and that simplicity bias can be eliminated by aligning a sequence of moderate granularity. Accordingly, we propose PINN-Mamba, a novel framework that introduces subsequence modeling with SSM. Experimental results show that PINNMamba can reduce errors by up to 86.3% compared with state-of-the-art architecture. Our code is available at https:// github.com/miniHuiHui/PINNMamba.

For agents

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

get_harvested_code_for_paper("2502.00318")
get_code_for_paper("2502.00318")
have("2502.00318")

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

curl https://syntology.ai/api/ran/2502.00318.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.00318.svg)](https://syntology.ai/paper/2502.00318)

Connect an agent — have() is free.