Pith Number

pith:WE6ONQ4V

pith:2026:WE6ONQ4VWP4JBDXVC7YOYNV5SF

not attested not anchored not stored refs pending

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

Weitong Zhang, Xiaoyun Wang, Yuxiao Yang

Outcome-guided logit steering calibrates teacher responses in on-policy self-distillation by contrasting successful and failed trajectories, reducing reflection bias for better LLM reasoning.

arxiv:2605.12400 v2 · 2026-05-12 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WE6ONQ4VWP4JBDXVC7YOYNV5SF}

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

By combining outcome-level correctness with dense token-level guidance through logit steering, OGLS-SD stabilizes self-distillation and improves reasoning performance over standard OPSD and other variants across diverse benchmarks.

C2weakest assumption

That verifiable outcome rewards can reliably contrast successful and failed on-policy trajectories to calibrate teacher logits and mitigate reflection-induced bias without introducing new calibration issues or depending on tasks where outcomes are easily verifiable.

C3one line summary

OGLS-SD improves LLM reasoning by using verifiable outcome rewards to guide logit steering that calibrates teacher distributions in on-policy self-distillation, addressing reflection-induced mismatches.

Formal links

2 machine-checked theorem links

Cited by

2 papers in Pith

A Brief Overview: On-Policy Self-Distillation In Large Language Models

Receipt and verification

First computed	2026-06-02T01:03:48.438082Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b13ce6c395b3f8908ef517f0ec36bd9178cc3a3844be93dfdc059ab8275b4f73

Aliases

arxiv: 2605.12400 · arxiv_version: 2605.12400v2 · doi: 10.48550/arxiv.2605.12400 · pith_short_12: WE6ONQ4VWP4J · pith_short_16: WE6ONQ4VWP4JBDXV · pith_short_8: WE6ONQ4V

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/WE6ONQ4VWP4JBDXVC7YOYNV5SF \
  | 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: b13ce6c395b3f8908ef517f0ec36bd9178cc3a3844be93dfdc059ab8275b4f73

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a8c9c992aed92afea13155de0dc839558215e5b084a3f35b61b942ac9967fdda",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T17:00:53Z",
    "title_canon_sha256": "4496316516826098f6407c5ab502ca827ecb01db1d825e03d18de392fd5ba39f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12400",
    "kind": "arxiv",
    "version": 2
  }
}