SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.14714 · NeurIPS · 2024

Defining error accumulation in ML atmospheric simulators

Raghul Parthipan, Damon Wischik, J Hosking, Mohit Anand, Hannah Christensen

arXiv · PDF · Open in the Atlas

Code that ran

1 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 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/2405.14714.json · badge: /api/ran/2405.14714.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
pangeo-data/WeatherBench canonical (classifier label)
classifier basis: census
1 ran · 3 no recorded run
FunctionStatusWhere it lives
build_cnn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pangeo-data/WeatherBench/src/train_nn.py
code served (permissive licence) · get_code("7cf9a61b1af4ac12")
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 Functional. 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 tensorflow as tf
import numpy as np

ARGS = {
    'filters': [16, 32, 8],
    'kernels': [3, 5, 3],
    'input_shape': (4, 5, 2),
    'dr': 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
add_2d Not yet run
unverified (harvested, no recorded run)
pangeo-data/WeatherBench/src/add_lat_lon_2d.py
code served (permissive licence) · get_code("ea8de9e9291e665d")
How it ran

no invocation recorded.

convert_z_to_orography Not yet run
unverified (harvested, no recorded run)
pangeo-data/WeatherBench/src/add_lat_lon_2d.py
code served (permissive licence) · get_code("b55da739853cb4e2")
How it ran

no invocation recorded.

extract Not yet run
unverified (harvested, no recorded run)
pangeo-data/WeatherBench/src/extract_level.py
code served (permissive licence) · get_code("1187845f43dd3cc3")
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 (4 with at least one paper dated earlier, 0 the same month, 0 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
add_2d 2 other papers
2 dated earlier
2008.08626 (2020-08)
Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench
2205.00865 (2022-05)
WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline models
convert_z_to_orography 2 other papers
2 dated earlier
2008.08626 (2020-08)
Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench
2205.00865 (2022-05)
WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline models
extract 2 other papers
2 dated earlier
2008.08626 (2020-08)
Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench
2205.00865 (2022-05)
WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline models
build_cnn 1 other paper
1 dated earlier
2008.08626 (2020-08)
Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench

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

Machine learning (ML) has recently shown significant promise in modelling atmospheric systems, such as the weather. Many of these ML models are autoregressive, and error accumulation in their forecasts is a key problem. However, there is no clear definition of what 'error accumulation' actually entails. In this paper, we propose a definition and an associated metric to measure it. Our definition distinguishes between errors which are due to model deficiencies, which we may hope to fix, and those due to the intrinsic properties of atmospheric systems (chaos, unobserved variables), which are not fixable. We illustrate the usefulness of this definition by proposing a simple regularization loss penalty inspired by it. This approach shows performance improvements (according to RMSE and spread/skill) in a selection of atmospheric systems, including the real-world weather prediction task.

For agents

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

get_harvested_code_for_paper("2405.14714")
get_code_for_paper("2405.14714")
have("2405.14714")

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

curl https://syntology.ai/api/ran/2405.14714.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.14714.svg)](https://syntology.ai/paper/2405.14714)

Connect an agent — have() is free.