SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_27766 · AAAI · 2024

Inducing Point Operator Transformer: A Flexible and Scalable Architecture for Solving PDEs

Seungjun Lee, Taeil Oh

Open in the Atlas

Code that ran

8 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 5 have no contract verdict; 0 failures of our instrument; 1 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/aaai_27766.json · badge: /api/ran/aaai_27766.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
7tl7qns7ch/IPOT canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
build_position_encoding Ran
ran on a synthesized input
7tl7qns7ch/IPOT/models/ipot/position_encoding.py
code served (permissive licence) · get_code("92655046480cb7fb")
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 tuple, ndim 1, 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
import numpy as np

torch.manual_seed(0)

ARGS = {
    'position_encoding_type': 'fourier',
    'out_channel': 256,
    'project_pos_channel': 128,
    'trainable_position_encoding_kwargs': {
        'index_dims': (4, 3),
        'num_channel': 128
    },
    'fourier_position_encoding_kwargs': {
        'num_bands': (4, 3),
        'max_resolution': (8, 6),
        'concat_pos': True,
        'sine_only': False
    },
    'pos2fourier_position_encoding_kwargs': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
count_params Ran
ran, honoured the contract we drafted
7tl7qns7ch/IPOT/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from UncertaintyQuantification/forecast_ndvi, is pointer only (licence: NONE) · get_code("ff3cd8971ff1bc18")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from UncertaintyQuantification/forecast_ndvi, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

default Ran
ran, violated the contract we drafted
7tl7qns7ch/IPOT/models/ipot/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

exists Ran
ran, violated the contract we drafted
7tl7qns7ch/IPOT/models/ipot/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_fourier_features Ran
ran on a synthesized input
7tl7qns7ch/IPOT/models/ipot/position_encoding.py
code served (permissive licence) · get_code("d036c13aec5d2ac8")
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 3, dtype family float, shape (2, 3, 20) 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 numpy as np

torch.manual_seed(0)

# Construct a small position tensor
# Shape: (batch_size=2, num_points=3, spatial_dim=4)
pos = torch.randn(2, 3, 4)

# num_bands should be a sequence (one per dimension) matching spatial_dim
num_bands = [2, 2, 2, 2]  # 4 bands for 4 spatial dimensions

# max_resolution should be a tuple matching spatial_dim
max_resolution = (2**10, 2**10, 2**10, 2**10)

concat_pos = True
sine_only = False

ARGS = {
    "pos": pos,
    "num_bands": num_bands,
    "max_resolution": max_resolution,
    "concat_pos": concat_pos,
    "sine_only": sine_only,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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, shape (2, 3, 20) — shape (2, 3, 20) 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
torch1dgrid Ran
ran on a synthesized input
7tl7qns7ch/IPOT/pde_datasets/data_utils.py
code served (permissive licence) · get_code("69e57ea176e3656f")
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 (5, 1) 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 = {
    "num": 5,
    "bot": 0,
    "top": 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 (5, 1) — shape (5, 1) 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
torch2dgrid Ran
ran on a synthesized input
7tl7qns7ch/IPOT/pde_datasets/data_utils.py
code served (permissive licence) · get_code("da5ecb392437274c")
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 3, dtype family float, shape (5, 3, 2) 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 = {
    "num_x": 5,
    "num_y": 3,
    "bot": (0, 0),
    "top": (1, 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 3, dtype family float, shape (5, 3, 2) — shape (5, 3, 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
torch3dgrid Ran
ran on a synthesized input
7tl7qns7ch/IPOT/pde_datasets/data_utils.py
code served (permissive licence) · get_code("5440aed56e75c72a")
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 4, dtype family float, shape (3, 4, 5, 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 torch

torch.manual_seed(0)

ARGS = {
    "num_x": 3,
    "num_y": 4,
    "num_z": 5,
    "bot": (0, 0, 0),
    "top": (1, 1, 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 4, dtype family float, shape (3, 4, 5, 3) — shape (3, 4, 5, 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
cache_fn Not yet run
unverified (harvested, no recorded run)
7tl7qns7ch/IPOT/models/ipot/layers.py
code served (permissive licence) · get_code("e56401f8aa027f99")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 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
exists 486 other papers
283 dated earlier, 53 later, 148 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 163 other papers
112 dated earlier, 16 later, 34 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
count_params 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable
2209.10098 (2022-09)
NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation
2212.07477 (2022-12)
Guiding continuous operator learning through Physics-based boundary constraints
2309.16971 (2023-09)
Multi-Resolution Active Learning of Fourier Neural Operators
and 2 more not named here
cache_fn 4 other papers
2 dated earlier, 1 later, 1 same year, order not determinable
2103.03206 (2021-03)
Perceiver: General Perception with Iterative Attention
2311.09115 (2023-11)
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
2409.12121 (2024-09)
WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification
and 1 more not named here

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

Solving partial differential equations (PDEs) by learning the solution operators has emerged as an attractive alternative to traditional numerical methods. However, implementing such architectures presents two main challenges: flexibility in handling irregular and arbitrary input and output formats and scalability to large discretizations. Most existing architectures are limited by their desired structure or infeasible to scale large inputs and outputs. To address these issues, we introduce an attention-based model called an inducing point operator transformer (IPOT). Inspired by inducing points methods, IPOT is designed to handle any input function and output query while capturing global interactions in a computationally efficient way. By detaching the inputs/outputs discretizations from the processor with a smaller latent bottleneck, IPOT offers flexibility in processing arbitrary discretizations and scales linearly with the size of inputs/outputs. Our experimental results demonstrate that IPOT achieves strong performances with manageable computational complexity on an extensive range of PDE benchmarks and real-world weather forecasting scenarios, compared to state-of-the-art methods. Our code is publicly available at https://github.com/7tl7qns7ch/IPOT.

For agents

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

get_harvested_code_for_paper("aaai_27766")
get_code_for_paper("aaai_27766")
have("aaai_27766")

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

curl https://syntology.ai/api/ran/aaai_27766.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_27766.svg)](https://syntology.ai/paper/aaai_27766)

Connect an agent — have() is free.