pith. sign in
Pith Number

pith:IOAUKH62

pith:2026:IOAUKH622IANBKDQEPR6F55X5X
not attested not anchored not stored refs pending

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models

Chengqiang Lu, Congxi Xiao, Hui Xiong, Liyi Chen, Qimeng Wang, Tianfu Wang, Wei Wu, Yan Gao, Yao Hu, Yi Wu

Dynamic outlier truncation during RL training counters length shift in reasoning models, cutting tokens by 78% while boosting accuracy.

arxiv:2601.03969 v2 · 2026-01-07 · cs.AI · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{IOAUKH622IANBKDQEPR6F55X5X}

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 approach significantly pushes the efficiency-performance Pareto frontier outward. Notably, on the AIME-24, our method reduces inference token usage by 78% while simultaneously increasing accuracy compared to the initial policy and surpassing state-of-the-art efficient reasoning methods.

C2weakest assumption

That selectively truncating only the extreme tail of response lengths within correct rollout groups will not degrade the model's ability to learn long-horizon reasoning on complex problems.

C3one line summary

Dynamic Outlier Truncation during training reduces token usage by 78% on AIME-24 while increasing accuracy by suppressing extreme-length correct rollouts and adding KL regularization.

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-17T23:39:16.699768Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

4381451fdad200d0a87023e3e2f7b7edd854a0fbd6910255222fc5941321bffb

Aliases

arxiv: 2601.03969 · arxiv_version: 2601.03969v2 · doi: 10.48550/arxiv.2601.03969 · pith_short_12: IOAUKH622IAN · pith_short_16: IOAUKH622IANBKDQ · pith_short_8: IOAUKH62
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/IOAUKH622IANBKDQEPR6F55X5X \
  | 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: 4381451fdad200d0a87023e3e2f7b7edd854a0fbd6910255222fc5941321bffb
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "d957aed52f06d32163ff066e42dbe1c0311372ef4c98a1318662217d0246d440",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-01-07T14:31:07Z",
    "title_canon_sha256": "dbdd4b9df4587477ef3565737c066a1bbc88c4d7321146d29860b177aea0af81"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.03969",
    "kind": "arxiv",
    "version": 2
  }
}