SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15734 · 2024

Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2402.15734.json · badge: /api/ran/2402.15734.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
delta-lab-ai/data_efficient_nopt canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
add_weight_decay Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from PolymathicAI/multiple_physics_pretraining
pointer only · get_code("f7286d5a53b111fe")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

grad_clone Ran
ran; our contract draft was wrong, not the code
delta-lab-ai/data_efficient_nopt/pretrain_basic.py
code served (permissive licence) · get_code("7591530c94cb82e1")
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) and returned list. 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)

# Create a simple model with parameters
model = nn.Linear(4, 3)

# Get the parameters
parameters = list(model.parameters())

# Simulate a backward pass to populate gradients
x = torch.randn(2, 4)
y = torch.randn(2, 3)
loss = nn.MSELoss()(model(x), y)
loss.backward()

# Now parameters have gradients
ARGS = {
    "parameters": parameters
}
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 list — a list output has no array shape of its own; none is 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
grad_norm Ran
ran, honoured the contract we drafted
delta-lab-ai/data_efficient_nopt/train_basic.py
code served (permissive licence) · get_code("630e6bdb88095b73")
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) and returned float, ndim 0, dtype family float, shape () 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple model with parameters that have gradients
model = nn.Sequential(
    nn.Linear(4, 3),
    nn.ReLU(),
    nn.Linear(3, 2)
)

# Create dummy input and target
x = torch.randn(2, 4)
y = torch.randn(2, 2)

# Forward pass
output = model(x)
loss = nn.MSELoss()(output, y)

# Backward pass to compute gradients
loss.backward()

# Extract parameters (which now have gradients)
parameters = list(model.parameters())

ARGS = {
    "parameters": parameters
}
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 float, ndim 0, dtype family float, shape () — shape () 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
l2_err Ran
ran; our contract draft was wrong, not the code
delta-lab-ai/data_efficient_nopt/train_basic.py
code served (permissive licence) · get_code("3cc1d78804edbcdc")
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) and returned Tensor, ndim 0, dtype family float, shape () 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)

# Create small tensors for pred and target
# spatial_dim=(-1, -2, -3) means we sum over last 3 dimensions
# So we need at least 3 spatial dimensions plus a batch dimension
# Shape: (batch, channel, depth, height, width) = (2, 3, 4, 5, 6)
pred = torch.randn(2, 3, 4, 5, 6)
target = torch.randn(2, 3, 4, 5, 6)

ARGS = {
    "pred": pred,
    "target": target,
    "spatial_dim": (-1, -2, -3)
}
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 0, dtype family float, shape () — shape () 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

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
add_weight_decay 1 other paper
1 dated earlier
2310.02994 (2023-10)
Multiple Physics Pretraining for Physical Surrogate Models

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

Recent years have witnessed the promise of coupling machine learning methods and physical domain-specific insights for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these methods still require a large amount of PDE data. This reintroduces the need for expensive numerical PDE solutions, partially undermining the original goal of avoiding these expensive simulations. In this work, seeking data efficiency, we design unsupervised pretraining for PDE operator learning. To reduce the need for training data with heavy simulation costs, we mine unlabeled PDE data without simulated solutions, and we pretrain neural operators with physics-inspired reconstruction-based proxy tasks. To improve out-of-distribution performance, we further assist neural operators in flexibly leveraging a similarity-based method that learns in-context examples, without incurring extra training costs or designs. Extensive empirical evaluations on a diverse set of PDEs demonstrate that our method is highly data-efficient, more generalizable, and even outperforms conventional vision-pretrained models. We provide our code at https://github.com/delta-lab-ai/data_efficient_nopt.

For agents

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

get_harvested_code_for_paper("2402.15734")
get_code_for_paper("2402.15734")
have("2402.15734")

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

curl https://syntology.ai/api/ran/2402.15734.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.15734.svg)](https://syntology.ai/paper/2402.15734)

Connect an agent — have() is free.