SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.07993 · 2023

In-Context Operator Learning with Data Prompts for Differential Equation Problems

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2304.07993.json · badge: /api/ran/2304.07993.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
LiuYangMage/in-context-operator-networks canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
append_dict_list Ran
ran; our contract draft was wrong, not the code
LiuYangMage/in-context-operator-networks/icon-lm/operator_weno/analysis.py
pointer only (licence: MIT); the stored copy get_code serves, from margotyjx/fmint, is pointer only (licence: NONE) · get_code("ea1821fedc537073")
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 margotyjx/fmint, 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.

get_error Ran
ran, honoured the contract we drafted
LiuYangMage/in-context-operator-networks/icon-lm/operator_weno/analysis_plot.py
code served (permissive licence) · get_code("ccc3d008753c19f3")
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 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 numpy as np
import tempfile
import os

# Create temporary directory and .npz files
temp_dir = tempfile.mkdtemp()

# Create first test file with matching shapes (3D)
label1 = np.random.randn(2, 4, 3)
out1 = np.random.randn(2, 4, 3)
file1_path = os.path.join(temp_dir, 'test1.npz')
np.savez(file1_path, label=label1, out=out1)

# Create second test file with 4D label and 3D output
label2 = np.random.randn(2, 1, 4, 3)
out2 = np.random.randn(2, 4, 3)
file2_path = os.path.join(temp_dir, 'test2.npz')
np.savez(file2_path, label=label2, out=out2)

ARGS = {
    'file_name_list': [file1_path, file2_path]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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
get_error_tune Ran
ran, honoured the contract we drafted
LiuYangMage/in-context-operator-networks/icon-lm/operator_weno/analysis_plot.py
code served (permissive licence) · get_code("53e1fee72ab7a268")
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 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 numpy as np
import tempfile
import os

# Create a temporary .npz file with the required structure
temp_dir = tempfile.gettempdir()
temp_file = os.path.join(temp_dir, "test_error_tune.npz")

# Create dummy data with appropriate shapes
# label shape: (batch, 1, height, width) -> (2, 1, 4, 3)
# pred_tune shape: (batch, num_tune_params, 1, height, width) -> (2, 5, 1, 4, 3)
batch_size = 2
num_tune_params = 5
height = 4
width = 3

label = np.random.randn(batch_size, 1, height, width).astype(np.float32)
pred_tune = np.random.randn(batch_size, num_tune_params, 1, height, width).astype(np.float32)

np.savez(temp_file, label=label, pred_tune=pred_tune)

ARGS = {
    "file_name": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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
load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
LiuYangMage/in-context-operator-networks/icon-lm/models_gpt2_source.py
code served (permissive licence) · get_code("c4bac98236c1fc2c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 0 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
load_tf_weights_in_gpt2 5 other papers
4 dated earlier, 1 later
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
2009.06367 (2020-09)
GeDi: Generative Discriminator Guided Sequence Generation
2009.12719 (2020-09)
Stylized Dialogue Response Generation Using Stylized Unpaired Texts
and 2 more not named here
append_dict_list 2 other papers
2 later
2308.05061 (2023-08)
Fine-Tune Language Models as Multi-Modal Differential Equation Solvers
2404.14688 (2024-04)
FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model
get_error 1 other paper
1 later
2308.05061 (2023-08)
Fine-Tune Language Models as Multi-Modal Differential Equation Solvers
get_error_tune 1 other paper
1 later
2308.05061 (2023-08)
Fine-Tune Language Models as Multi-Modal Differential Equation Solvers

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

This paper introduces a new neural-network-based approach, namely In-Context Operator Networks (ICON), to simultaneously learn operators from the prompted data and apply it to new questions during the inference stage, without any weight update. Existing methods are limited to using a neural network to approximate a specific equation solution or a specific operator, requiring retraining when switching to a new problem with different equations. By training a single neural network as an operator learner, we can not only get rid of retraining (even fine-tuning) the neural network for new problems, but also leverage the commonalities shared across operators so that only a few demos in the prompt are needed when learning a new operator. Our numerical results show the neural network's capability as a few-shot operator learner for a diversified type of differential equation problems, including forward and inverse problems of ordinary differential equations (ODEs), partial differential equations (PDEs), and mean-field control (MFC) problems, and also show that it can generalize its learning capability to operators beyond the training distribution.

For agents

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

get_harvested_code_for_paper("2304.07993")
get_code_for_paper("2304.07993")
have("2304.07993")

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

curl https://syntology.ai/api/ran/2304.07993.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.07993.svg)](https://syntology.ai/paper/2304.07993)

Connect an agent — have() is free.