pith. machine review for the scientific record. sign in
Pith Number

pith:WERPE3RT

pith:2025:WERPE3RT226B7XDJYI4L7CGJGT
not attested not anchored not stored refs pending

Thyme: Think Beyond Images

Bin Wen, Changyi Liu, Chaoyou Fu, Fan Yang, Guorui Zhou, Haojie Ding, Haonan Fan, Jiankang Chen, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Liang Wang, Shukang Yin, Tianke Zhang, Tingting Gao, Wei Chen, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Zhang Zhang

Thyme lets multimodal models autonomously generate and run code to manipulate images and perform calculations during reasoning.

arxiv:2508.11630 v1 · 2025-08-15 · cs.CV

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open

Claims

C1strongest claim

Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.

C2weakest assumption

That the RL phase with GRPO-ATS will produce reliable autonomous decisions on when and how to apply code-based image manipulations without introducing execution errors or overfitting to the manually collected high-resolution QA pairs.

C3one line summary

Thyme trains MLLMs to autonomously generate executable code for image processing and math computations, yielding gains on high-resolution perception and complex reasoning benchmarks.

Formal links

2 machine-checked theorem links

Cited by

26 papers in Pith

Receipt and verification
First computed2026-05-17T23:39:19.705585Z
Builderpith-number-builder-2026-05-17-v1
SignaturePith Ed25519 (pith-v1-2026-05) · public key
Schemapith-number/v1.0

Canonical hash

b122f26e33d6bc1fdc69c238bf88c934c50526300d8cfec83d124e95ce85034a

Aliases

arxiv: 2508.11630 · arxiv_version: 2508.11630v1 · doi: 10.48550/arxiv.2508.11630
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/WERPE3RT226B7XDJYI4L7CGJGT \
  | 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: b122f26e33d6bc1fdc69c238bf88c934c50526300d8cfec83d124e95ce85034a
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "da3bb5704052413b3507b5af1b9bb79a11d60aed77148309406f0ae202179661",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-08-15T17:59:49Z",
    "title_canon_sha256": "f2f6b8736d88a031f9b2a8d0a45dda295e0567afec694387533599d48bff4345"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.11630",
    "kind": "arxiv",
    "version": 1
  }
}