SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.00792 · 2026

Neural Latent Arbitrary Lagrangian-Eulerian Grids for Fluid-Solid Interaction

Zhanxing Zhu, Zhe Feng, Yunhuai Liu, Weichen Zhang, Shilong Tao, Shaohan Chen

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 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; 0 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/2603.00792.json · badge: /api/ran/2603.00792.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
therontau0054/Fisale community
Papers with Code archive
7 ran · 4 no recorded run
FunctionStatusWhere it lives
ALEGrid Ran
ran on a synthesized input · constructed an object; no result was computed
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("b7b81e957a49b8c3")
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, ALEGrid: 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 = {
    'dim': 2,
    'hidden_dim': 64,
    'grid_shape': (4, 5),
    'neighbors_num': 3,
}
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 ALEGrid — 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 ALEGrid 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
ALEGridUpdate Ran
ran on a synthesized input
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("4373cd2cb0c92b91")
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_geometric.data import Data

INIT_ARGS = {
    'hidden_dim': 4,
    'heads_num': 2
}

# Create small stand-in tensors and objects
batch_size = 2
node_count = 3
hidden_dim = INIT_ARGS['hidden_dim']
edge_count = 4

# Input tensors for forward pass
u_proj = torch.randn(batch_size, node_count, hidden_dim)
ps_proj = torch.randn(batch_size, node_count, hidden_dim)
pf_proj = torch.randn(batch_size, node_count, hidden_dim)
pb_proj = torch.randn(batch_size, node_count, hidden_dim)

# Edge index tensor (2, edge_count)
edge_index = torch.randint(0, node_count, (2, edge_count))

ARGS = {
    'u_proj': u_proj,
    'ps_proj': ps_proj,
    'pf_proj': pf_proj,
    'pb_proj': pb_proj,
    'edge_index': edge_index
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
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 Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:ValueError)
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)
Attention Ran
ran on a synthesized input · constructed an object; no result was computed
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("d17d8a42692307b4")
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, Attention: 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 = {
    'query_dim': 4,
    'key_dim': 4,
    'value_dim': 4,
    'output_dim': 8,
    'heads_num': 2,
    'dropout': 0.1,
    'bias': False,
    'attn_type': 'vanilla',
    'linear_type': 'galerkin'
}
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 Attention — 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 Attention 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
AttentionLayer Ran
ran on a synthesized input · constructed an object; no result was computed
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("7120dfd0aa412331")
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, AttentionLayer: 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 = {
    'query_dim': 4,
    'key_dim': 4,
    'value_dim': 4,
    'output_dim': 8,
    'heads_num': 2,
    'mlp_ratio': 2,
    'dropout': 0.1,
    'act': 'gelu',
    'bias': False,
    'attn_type': 'linear',
    'linear_type': 'l1',
    'experts_num': 1,
}
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 AttentionLayer — 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 AttentionLayer 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
Deprojection Ran
ran on a synthesized input
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("57db093f1a5b5118")
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 2, 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 torch.nn as nn

class Deprojection(nn.Module):

    def __init__(self, hidden_dim=64):
        super().__init__()
        self.fc_out = nn.Sequential(nn.LayerNorm(hidden_dim), nn.Linear(hidden_dim, hidden_dim))

    def forward(self, p_proj, weight):
        _up = self.fc_out(weight.softmax(-1) @ p_proj)
        return _up


INIT_ARGS = {
    'hidden_dim': 64
}

ARGS = {
    'p_proj': torch.randn(2, 64),
    'weight': torch.randn(2, 2)
}

if __name__ == '__main__':
    model = Deprojection(**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
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 — 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)
FFN Ran
ran on a synthesized input · constructed an object; no result was computed
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("98f57121a42d9901")
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, FFN: 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,
    'hidden_dim': 8,
    'output_dim': 3,
    'layer_num': 2,
    'act': 'gelu',
    'res': True,
    'norm': True,
    'experts_num': 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 FFN — 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 FFN 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
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("9169ae6a92206a71")
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,
    'hidden_dim': 8,
    'output_dim': 3,
    'layer_num': 2,
    'act': 'gelu',
    'res': True,
    'norm': True
}
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
ALEBlock Not yet run
unverified (harvested, no recorded run)
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("aa840b42734bd683")
How it ran

no invocation recorded.

ALEModule Not yet run
unverified (harvested, no recorded run)
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("fc7772ad1b261576")
How it ran

no invocation recorded.

Fisale Not yet run
unverified (harvested, no recorded run)
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("3d96e16d6aaf84cb")
How it ran

no invocation recorded.

Projection Not yet run
unverified (harvested, no recorded run)
therontau0054/Fisale/model/fisale.py
code served (permissive licence) · get_code("02db83bc5015811a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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

Fluid-solid interaction (FSI) problems are fundamental in many scientific and engineering applications, yet effectively capturing the highly nonlinear two-way interactions remains a significant challenge. Most existing deep learning methods are limited to simplified one-way FSI scenarios, often assuming rigid and static solid to reduce complexity. Even in two-way setups, prevailing approaches struggle to capture dynamic, heterogeneous interactions due to the lack of cross-domain awareness. In this paper, we introduce Fisale, a data-driven framework for handling complex two-way FSI problems. It is inspired by classical numerical methods, namely the Arbitrary Lagrangian-Eulerian (ALE) method and the partitioned coupling algorithm. Fisale explicitly models the coupling interface as a distinct component and leverages multiscale latent ALE grids to provide unified, geometryaware embeddings across domains. A partitioned coupling module (PCM) further decomposes the problem into structured substeps, enabling progressive modeling of nonlinear interdependencies. Compared to existing models, Fisale introduces a more flexible framework that iteratively handles complex dynamics of solid, fluid and their coupling interface on a unified representation, and enables scalable learning of complex two-way FSI behaviors. Experimentally, Fisale excels in three reality-related challenging FSI scenarios, covering 2D, 3D and various tasks. The code is available at https://github.com/therontau0054/Fisale.

For agents

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

get_harvested_code_for_paper("2603.00792")
get_code_for_paper("2603.00792")
have("2603.00792")

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

curl https://syntology.ai/api/ran/2603.00792.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.00792.svg)](https://syntology.ai/paper/2603.00792)

Connect an agent — have() is free.