Pith Number

pith:U5C3O7EE

pith:2025:U5C3O7EEN5LMQ632VIUCJHHSVV

not attested not anchored not stored refs resolved

Do-Undo Bench: Reversibility for Action Understanding in Image Generation

Apratim Bhattacharyya, Fatih Porikli, Hoang Le, Munawar Hayat, Rajeev Yasarla, Shreya Kadambi, Shweta Mahajan

Requiring image generators to apply and then undo real actions tests genuine cause-and-effect understanding.

arxiv:2512.13609 v2 · 2025-12-15 · cs.CV · 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{U5C3O7EEN5LMQ632VIUCJHHSVV}

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

our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits.

C2weakest assumption

That the curated high-quality benchmark of reversible actions from real-world scenarios actually isolates genuine cause-and-effect understanding rather than other visual or linguistic cues.

C3one line summary

Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation.

References

36 extracted · 36 resolved · 5 Pith anchors

[1] Unibench: Visual reasoning requires rethinking vision- language beyond scaling.Advances in Neural Information Processing Systems, 37:82411–82437, 2024 2024

[2] Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning 2025 · arXiv:2503.15558

[3] Long-term image boundary prediction 2018

[4] Visual jenga: Discovering object dependencies via counterfactual inpainting 2025

[5] In- structpix2pix: Learning to follow image editing instructions 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:00.507833Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a745b77c846f56c87b7aaa28249cf2ad4332b787fd3f77570e7a4cfedafe2a9a

Aliases

arxiv: 2512.13609 · arxiv_version: 2512.13609v2 · doi: 10.48550/arxiv.2512.13609 · pith_short_12: U5C3O7EEN5LM · pith_short_16: U5C3O7EEN5LMQ632 · pith_short_8: U5C3O7EE

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/U5C3O7EEN5LMQ632VIUCJHHSVV \
  | 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: a745b77c846f56c87b7aaa28249cf2ad4332b787fd3f77570e7a4cfedafe2a9a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f89072e56889315888a55dc83d87b8b6e2dbe976d9cd2b3e60201ef1663b0f2d",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-12-15T18:03:42Z",
    "title_canon_sha256": "19f29ab9f5f71b95e8fbc752b3b51d3db835b8f8327b2454454fe455178e582e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.13609",
    "kind": "arxiv",
    "version": 2
  }
}