Pith Number

pith:FUVJ4FIL

pith:2025:FUVJ4FILYEKL7L4KHTKDY4TULB

not attested not anchored not stored refs resolved

Qwen2.5-1M Technical Report

An Yang, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoyan Huang, Jiandong Jiang, Jianhong Tu, Jianwei Zhang, Jingren Zhou, Junyang Lin, Kai Dang, Kexin Yang, Le Yu, Mei Li, Minmin Sun, Qin Zhu, Rui Men, Tao He, Weijia Xu, Wenbiao Yin, Wenyuan Yu, Xiafei Qiu, Xingzhang Ren, Xinlong Yang, Yong Li, Zhiying Xu, Zipeng Zhang

Qwen2.5-1M models reach 1 million token context length while outperforming GPT-4o-mini on long-context tasks.

arxiv:2501.15383 v1 · 2025-01-26 · 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{FUVJ4FILYEKL7L4KHTKDY4TULB}

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

the Qwen2.5-14B-Instruct-1M model significantly outperforms GPT-4o-mini in long-context tasks and supports contexts eight times longer.

C2weakest assumption

That the long data synthesis and progressive pre-training produce genuine generalization rather than overfitting to the synthetic long sequences used in training.

C3one line summary

Qwen2.5-1M models reach 1M token context with improved long-context performance, no short-context loss, and 3-7x prefill speedup via open inference optimizations.

References

25 extracted · 25 resolved · 17 Pith anchors

[1] arXiv preprint arXiv:2402.17463 , year=

[2] Program Synthesis with Large Language Models · arXiv:2108.07732

[3] Qwen Technical Report · arXiv:2309.16609

[4] Efficient training of language models to fill in the middle

[5] Efficient training of language models to fill in the middle · doi:10.48550/arxiv.2207.14255

Formal links

2 machine-checked theorem links

Cited by

34 papers in Pith

Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning

CacheClip: Accelerating RAG with Effective KV Cache Reuse

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training

Receipt and verification

First computed	2026-05-17T23:38:53.396695Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2d2a9e150bc114bfaf8a3cd43c7274584bcf1221a7d521df84c62256a575a932

Aliases

arxiv: 2501.15383 · arxiv_version: 2501.15383v1 · doi: 10.48550/arxiv.2501.15383 · pith_short_12: FUVJ4FILYEKL · pith_short_16: FUVJ4FILYEKL7L4K · pith_short_8: FUVJ4FIL

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/FUVJ4FILYEKL7L4KHTKDY4TULB \
  | 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: 2d2a9e150bc114bfaf8a3cd43c7274584bcf1221a7d521df84c62256a575a932

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a3167e49b630b5c233468baabd7798084c3dd1a790b5345b3aba47aacde405ca",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-01-26T03:47:25Z",
    "title_canon_sha256": "97f99d8e3785dddb75a5f020e45143cd23e7f0b9a01ed26aa1ffef9640745ec7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2501.15383",
    "kind": "arxiv",
    "version": 1
  }
}