Pith Number

pith:IBATJDLO

pith:2026:IBATJDLOU3LETEJXTQF67NBOJN

not attested not anchored not stored refs pending

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning

Jing Tang, Minrui Xu, Xiaodan Liang, Yifan Song, Yiwei Wang, Yongxin Wang, Zhicheng Yang, Zhijiang Guo

Prune-OPD makes on-policy distillation for long-horizon reasoning more efficient by pruning unreliable teacher rewards in real time.

arxiv:2605.07804 v2 · 2026-05-08 · 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{IBATJDLOU3LETEJXTQF67NBOJN}

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

Prune-OPD reduces training time by 37.6%--68.0% while preserving, and often improving, performance on challenging benchmarks (AMC, AIME, HMMT) by dynamically aligning computation with supervision reliability across diverse teacher-student combinations.

C2weakest assumption

That top-k overlap between student and teacher predictions is a reliable real-time indicator of when dense teacher rewards lose local exploitability, and that monotonic down-weighting plus truncation does not discard critical learning signals needed for long-horizon improvement.

C3one line summary

Prune-OPD dynamically prunes unreliable teacher rewards in on-policy distillation by monitoring prefix drift via top-k overlap, reducing training time 37.6-68% on AMC/AIME/HMMT while preserving or improving performance.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-29T02:05:46.258958Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4041348d6ea6d64991379c0befb42e4b55be755766871ddb865528ac4527a08d

Aliases

arxiv: 2605.07804 · arxiv_version: 2605.07804v2 · doi: 10.48550/arxiv.2605.07804 · pith_short_12: IBATJDLOU3LE · pith_short_16: IBATJDLOU3LETEJX · pith_short_8: IBATJDLO

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/IBATJDLOU3LETEJXTQF67NBOJN \
  | 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: 4041348d6ea6d64991379c0befb42e4b55be755766871ddb865528ac4527a08d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6e600b008c47516456ddd1fa78f0bb9609bf7056c0cd27b6bb77a80754a25007",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-08T14:38:53Z",
    "title_canon_sha256": "1ddfef6338d71579cc32c9d572291023565d114402883f18cd7f0ae117a97825"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.07804",
    "kind": "arxiv",
    "version": 2
  }
}