SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.08754 · NeurIPS · 2023

ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation

Stephan Mandt, Rose Yu, Mit, Elizabeth Barnes, Pierre Baldi, Yu Huang, Tom Beucler, Ucla, Ritwik Gupta, Columbia, Nyu, Noah Brenowitz, and 54 more

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 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/2306.08754.json · badge: /api/ran/2306.08754.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
leap-stc/ClimSim canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
eice Ran
ran on a synthesized input
leap-stc/ClimSim/climsim_utils/data_utils.py
code served (permissive licence) · get_code("561782c7b170b096")
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 ndarray, ndim 1, dtype family float, shape (4,) 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 numpy as np

# The function eice takes a single parameter T (temperature in K)
# T can be a scalar or array-like value
# The function performs array operations on T, so it should be a numpy array or scalar

# Create a small test temperature array in Kelvin
# Using values around the freezing point and below
T_values = np.array([250.0, 260.0, 273.15, 280.0])

ARGS = {
    "T": T_values
}
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 ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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
eliq Ran
ran on a synthesized input
leap-stc/ClimSim/climsim_utils/data_utils.py
code served (permissive licence) · get_code("a00f0e3089f828f0")
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 ndarray, ndim 1, dtype family float, shape (4,) 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 numpy as np

# The function eliq takes a single parameter T (temperature in K)
# and expects a numeric value or array-like input
# It uses np.maximum and np.polyval which work with scalars and arrays

# Create valid test cases
T_scalar = 273.16  # Freezing point of water in Kelvin
T_array = np.array([273.16, 280.0, 290.0, 300.0])  # Array of temperatures

ARGS = {
    "T": T_array
}
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 ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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
schedule Ran
ran on a synthesized input
leap-stc/ClimSim/baseline_models/ED/training/ClimSIM_ED_1_3_train.py
code served (permissive licence) · get_code("1dfe90af653014df")
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 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)

lr_init = 0.0001

def schedule(epoch):
    """
    learning rate scheduler based on Behrens 2022, divides lr after each 7th epoch by factor 5
    """
    if epoch < 7:
        return lr_init
    elif epoch < 14:
        return lr_init / 5
    elif epoch < 21:
        return lr_init / 25
    elif epoch < 28:
        return lr_init / 125
    elif epoch < 35:
        return lr_init / 625
    elif epoch < 42:
        return lr_init / 3125

ARGS = {
    "epoch": 0
}
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 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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.

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

Modern climate projections lack adequate spatial and temporal resolution due to computational constraints, leading to inaccuracies in representing critical processes like thunderstorms that occur on the sub-resolution scale. Hybrid methods combining physics with machine learning (ML) offer faster, higher fidelity climate simulations by outsourcing compute-hungry, high-resolution simulations to ML emulators. However, these hybrid ML-physics simulations require domain-specific data and workflows that have been inaccessible to many ML experts. As an extension of the ClimSim dataset (Yu et al., 2024), we present ClimSim-Online, which also includes an end-to-end workflow for developing hybrid ML-physics simulators. The ClimSim dataset includes 5.7 billion pairs of multivariate input/output vectors, capturing the influence of high-resolution, high-fidelity physics on a host climate simulator's macro-scale state. The dataset is global and spans ten years at a high sampling frequency. We provide a cross-platform, containerized pipeline to integrate ML models into operational climate simulators for hybrid testing. We also implement various ML baselines, alongside a hybrid baseline simulator, to highlight the ML challenges of building stable, skillful emulators. The data (https://huggingface.co/datasets/LEAP/ClimSim_high-res 1 ) and code (https://leap-stc.github.io/ClimSim and https://github.com/leap-stc/ climsim-online/) are publicly released to support the development of hybrid ML-physics and high-fidelity climate simulations.

For agents

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

get_harvested_code_for_paper("2306.08754")
get_code_for_paper("2306.08754")
have("2306.08754")

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

curl https://syntology.ai/api/ran/2306.08754.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.08754.svg)](https://syntology.ai/paper/2306.08754)

Connect an agent — have() is free.