Pith Number

pith:ZSJZXFHZ

pith:2026:ZSJZXFHZKAXSCGF7S6E4XD3HC7

not attested not anchored not stored refs pending

Qwen3-Coder-Next Technical Report

Binyuan Hui, Fan Zhou, Jiajun Zhang, Jiawei Chen, Jiaxi Yang, Jinxi Wei, Junyang Lin, Kaixin Li, Kashun Shum, Lei Zhang, Mingze Li, Mouxiang Chen, Ruisheng Cao, Wenting Zhao, Xuwu Wang, Yuheng Jing, Yunlong Feng, Zeyao Ma, Zeyu Cui, Zongmeng Zhang

An 80-billion-parameter model activates only three billion at inference to reach competitive results on coding agent benchmarks.

arxiv:2603.00729 v1 · 2026-02-28 · 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{ZSJZXFHZKAXSCGF7S6E4XD3HC7}

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

Qwen3-Coder-Next achieves competitive performance relative to its active parameter count across agent-centric benchmarks including SWE-Bench and Terminal-Bench.

C2weakest assumption

That large-scale synthesis of verifiable coding tasks paired with executable environments produces training signals that generalize to real-world coding agent use cases without significant distribution shift.

C3one line summary

An 80B model with 3B active parameters achieves competitive coding-agent performance through agentic training on verifiable tasks and releases open weights.

Formal links

2 machine-checked theorem links

Cited by

22 papers in Pith

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning

Receipt and verification

First computed	2026-05-17T23:38:46.557853Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cc939b94f9502f2118bf9789cb8f6717df69436d947181f1da1dd97ab78eacb0

Aliases

arxiv: 2603.00729 · arxiv_version: 2603.00729v1 · doi: 10.48550/arxiv.2603.00729 · pith_short_12: ZSJZXFHZKAXS · pith_short_16: ZSJZXFHZKAXSCGF7 · pith_short_8: ZSJZXFHZ

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/ZSJZXFHZKAXSCGF7S6E4XD3HC7 \
  | 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: cc939b94f9502f2118bf9789cb8f6717df69436d947181f1da1dd97ab78eacb0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bb52bbc009df70c868ff6136ce1cbd69618c2d633c6881c1d6e9ca62c5771629",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-02-28T16:25:04Z",
    "title_canon_sha256": "688f60c3d31d34179dbd3273b33f3f4353959d060b9876d47f0c75acf0af7a92"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.00729",
    "kind": "arxiv",
    "version": 1
  }
}