Pith Number

pith:FJJMA63L

pith:2026:FJJMA63LVYYRGPML4L6WI7YEZA

not attested not anchored not stored refs resolved

Emulating the Forced Response of Climate Models with Flow Matching

Anasatase Charantonis, Claire Monteleoni, Graham Clyne, Julia Kaltenborn, Peer Nowack

A flow matching deep learning model trained on multiple SSPs generates climate responses to forcing combinations not seen during training.

arxiv:2605.16929 v1 · 2026-05-16 · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{FJJMA63LVYYRGPML4L6WI7YEZA}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We here train a Deep Learning (DL) model on multiple SSPs and successfully generate scenarios unseen during training. Our research demonstrates the capacity to generate such changing climate states in response to a variety of simultaneous climate forcings (e.g., carbon dioxide, methane, nitrous oxide, sulphate aerosols, and ozone).

C2weakest assumption

That a flow matching model conditioned only on the provided climate forcings from training SSPs can accurately generalize to produce physically consistent responses for entirely unseen forcing combinations without being dominated by internal variability or emulator-specific artifacts.

C3one line summary

A flow matching deep learning emulator trained on multiple SSPs generates forced climate responses for unseen scenarios and is validated against the MESMER-M statistical emulator.

References

73 extracted · 73 resolved · 0 Pith anchors

[1] In Christopher B 2014 · doi:10.1017/cbo9781107415379.025

[2] InAerosols and Climate, pages 9–52 2022 · doi:10.1016/b978-0-12-819766-0.00008-0

[3] Acosta, Sergi Palomas, Stella V 2024 · doi:10.5194/gmd-17-3081-2024

[4] Ander- sson, Jacklynn Stott, Remi Lam, Matthew Willson, Alvaro Sanchez-Gonzalez, and Peter Battaglia 2025

[5] Lea Beusch, Lukas Gudmundsson, and Sonia I. Seneviratne. Emulating Earth system model temperatures with MESMER: From global mean temperature trajectories to grid-point- 30 0 10 20 30 40 50 60 70 80 Ye 2040 · doi:10.5194/esd-11-139-2020

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:31.318206Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2a52c07b6bae31133d8be2fd647f04c8284c73b9efb1468928f5703e2a513ec0

Aliases

arxiv: 2605.16929 · arxiv_version: 2605.16929v1 · doi: 10.48550/arxiv.2605.16929 · pith_short_12: FJJMA63LVYYR · pith_short_16: FJJMA63LVYYRGPML · pith_short_8: FJJMA63L

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/FJJMA63LVYYRGPML4L6WI7YEZA \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 2a52c07b6bae31133d8be2fd647f04c8284c73b9efb1468928f5703e2a513ec0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b3bdc11d507aa14c22b0b7d4c993beced616db9bf7ab144bd5834085bf590737",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-16T10:54:35Z",
    "title_canon_sha256": "195029b85ccac0eb4d0a0869393e13f07fb9a11263ff7c9cb7b35611ded58eb1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16929",
    "kind": "arxiv",
    "version": 1
  }
}