Pith Number

pith:V6TLOTG4

pith:2025:V6TLOTG4PKFMUULQ7FMC7RG2MH

not attested not anchored not stored refs pending

Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning

Alex Su, Fangzhen Lin, Haozhe Wang, Weiming Ren, Wenhu Chen

Vision-language models can reason directly in pixel space using operations like zoom-in and frame selection to achieve new open-source highs on visual benchmarks.

arxiv:2505.15966 v3 · 2025-05-21 · cs.CV · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{V6TLOTG4PKFMUULQ7FMC7RG2MH}

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 7B model, Pixel Reasoner, achieves 84% on V* bench, 74% on TallyQA-Complex, and 84% on InfographicsVQA, marking the highest accuracy achieved by any open-source model to date.

C2weakest assumption

The curiosity-driven reward scheme will successfully balance exploration of pixel-space operations with textual reasoning without the model reverting to familiar text-only strategies or exploiting the reward in unintended ways.

C3one line summary

Pixel Reasoner equips VLMs with pixel-space operations and uses curiosity-driven RL to improve visual reasoning, achieving top open-source results on V*, TallyQA-Complex, and InfographicsVQA.

Formal links

3 machine-checked theorem links

Cited by

49 papers in Pith

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming

DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model

When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning

Receipt and verification

First computed	2026-05-18T02:39:16.984324Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

afa6b74cdc7a8aca5170f9582fc4da61e4444390fc2620520edd8bf07af4a5fb

Aliases

arxiv: 2505.15966 · arxiv_version: 2505.15966v3 · doi: 10.48550/arxiv.2505.15966 · pith_short_12: V6TLOTG4PKFM · pith_short_16: V6TLOTG4PKFMUULQ · pith_short_8: V6TLOTG4

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/V6TLOTG4PKFMUULQ7FMC7RG2MH \
  | 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: afa6b74cdc7a8aca5170f9582fc4da61e4444390fc2620520edd8bf07af4a5fb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "13fa2021d633cbcd726c6218ae04a8537475157c5fc39ae87a2616339b10f070",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-05-21T19:35:08Z",
    "title_canon_sha256": "8a94c8ff782df7bc890b2729354604b210b5e0714caef36845c6c12ce7030c23"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.15966",
    "kind": "arxiv",
    "version": 3
  }
}