Pith Number

pith:PTD65LSX

pith:2026:PTD65LSX2M2R3BXULUJO5Q7SXE

not attested not anchored not stored refs resolved

Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning

Shan Yang

Audited olympiad corpus and RL recipe lift 8B vision model 18 points on physics reasoning.

arxiv:2605.14040 v1 · 2026-05-13 · 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{PTD65LSX2M2R3BXULUJO5Q7SXE}

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

Across 3 seeds, Physics-R1 lifts the audited corpus over the 8B base by +18.3 pp on PhysOlym-A liberal (8.0 -> 26.3 +/- 1.7; 7.1 pp behind Sonnet 4.5), +15.7 pp on PhysReason (23.9 -> 39.6 +/- 6.4; ahead of Qwen3-VL-32B and Gemini 2.5 Pro), +6.9 pp on OlympiadBench-Physics, and +4.1 pp on PhyX MCQ.

C2weakest assumption

The three-stage audit (5-gram Jaccard then embedding cosine then LLM judge) has removed essentially all contamination and the new PhysOlym-A set is truly held-out with no overlap to any training data used for the base model or the recipe.

C3one line summary

Audited olympiad corpus and Physics-R1 recipe improve 8B VLM by up to 18 points on held-out physics problems while exposing contamination in prior evals.

References

52 extracted · 52 resolved · 3 Pith anchors

[1] Shen, Hui and Wu, Taiqiang and Han, Qi and others , journal=

[2] He, Chaoqun and Luo, Renjie and Bai, Yuzhuo and Hu, Shengding and others , booktitle=

[3] Xu, Xin and Xu, Qiyun and Xiao, Tong and others , journal=

[4] Zhang, Xinyu and Dong, Yuxuan and Wu, Yanrui and others , journal=

[5] Yue, Xiang and Ni, Yuansheng and Zhang, Kai and Zheng, Tianyu and others , booktitle=

Receipt and verification

First computed	2026-05-17T23:39:12.752032Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7cc7eeae57d3351d86f45d12eec3f2b9364d8962e2c0ac6816fa47a93ea0833d

Aliases

arxiv: 2605.14040 · arxiv_version: 2605.14040v1 · doi: 10.48550/arxiv.2605.14040 · pith_short_12: PTD65LSX2M2R · pith_short_16: PTD65LSX2M2R3BXU · pith_short_8: PTD65LSX

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/PTD65LSX2M2R3BXULUJO5Q7SXE \
  | 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: 7cc7eeae57d3351d86f45d12eec3f2b9364d8962e2c0ac6816fa47a93ea0833d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c522a13c994253ecb45d4197889cc7582ba966311a168f6695e21dd6d4d9178e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T19:00:57Z",
    "title_canon_sha256": "eaf2659cc4471db9b1210af5f89624c2126d08882e71808f45882da09876f34d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14040",
    "kind": "arxiv",
    "version": 1
  }
}