Pith Number

pith:6GKAZ5ZO

pith:2025:6GKAZ5ZOSCCBYT5KMXD5YZQGQ4

not attested not anchored not stored refs pending

JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

Ben Kao, Fei Yuan, Jingyang Gong, Kai Chen, Lei Li, Qiaosheng Chen, Qipeng Guo, Qiushi Sun, Yang Liu

A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both.

arxiv:2510.23538 v3 · 2025-10-27 · cs.AI · cs.CL · cs.CV · cs.SE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6GKAZ5ZOSCCBYT5KMXD5YZQGQ4}

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 unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models.

C2weakest assumption

The synthesized JanusCode-800K dataset is assumed to be high-quality and representative enough to train models that generalize to real-world visual-programmatic tasks, without detailed validation against human-created or external benchmarks mentioned in the abstract.

C3one line summary

JanusCoder is a unified visual-programmatic model for code generation from text and/or visual inputs, powered by the new JanusCode-800K multimodal dataset.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Visual-ERM: Reward Modeling for Visual Equivalence

Receipt and verification

First computed	2026-05-21T01:04:18.083080Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120

Aliases

arxiv: 2510.23538 · arxiv_version: 2510.23538v3 · doi: 10.48550/arxiv.2510.23538 · pith_short_12: 6GKAZ5ZOSCCB · pith_short_16: 6GKAZ5ZOSCCBYT5K · pith_short_8: 6GKAZ5ZO

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/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4 \
  | 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: f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "58a39ceca1186ce3e0bea2382f3b762ddcf14a35c6fad75c1d47ede1ae0da1eb",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.CV",
      "cs.SE"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-10-27T17:13:49Z",
    "title_canon_sha256": "4849db6f7f01aec2b0b6cebe79650905d7ef0fe4e69397139a6aefc3e709dfb4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.23538",
    "kind": "arxiv",
    "version": 3
  }
}