Pith Number

pith:7XEA25FQ

pith:2026:7XEA25FQG2QRI2FNXXF7MDASVD

not attested not anchored not stored refs pending

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models

B. Aditya Prakash, Haoxin Liu, Jindong Wang, Josiah Hester, Lucheng Fu, Srijan Kumar, Yijia Xiao, Yinyi Luo, Yiqiao Jin, Yiyang Wang

A unified framework makes self-distillation a reliable way to adapt large language models without stronger teachers.

arxiv:2605.06597 v2 · 2026-05-07 · cs.CL · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7XEA25FQG2QRI2FNXXF7MDASVD}

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

UniSDfull, an integrated pipeline that combines complementary components, achieves the strongest overall performance, improving over the base model by +5.4 points and the strongest baseline by +2.8 points.

C2weakest assumption

That the listed mechanisms (multi-teacher agreement, EMA, token contrastive learning, feature matching, divergence clipping) reliably address supervision instability in free-form self-generated trajectories and that their interactions can be isolated and combined without post-hoc selection bias affecting the reported gains.

C3one line summary

UniSD unifies complementary self-distillation mechanisms for autoregressive LLMs and achieves up to +5.4 point gains over base models and +2.8 over baselines across six benchmarks and six models.

Cited by

2 papers in Pith

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

Receipt and verification

First computed	2026-05-22T02:04:41.944621Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fdc80d74b036a11468adbdcbf60c12a8fba5c294aa7459c60fd9f78cb640d93d

Aliases

arxiv: 2605.06597 · arxiv_version: 2605.06597v2 · doi: 10.48550/arxiv.2605.06597 · pith_short_12: 7XEA25FQG2QR · pith_short_16: 7XEA25FQG2QRI2FN · pith_short_8: 7XEA25FQ

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/7XEA25FQG2QRI2FNXXF7MDASVD \
  | 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: fdc80d74b036a11468adbdcbf60c12a8fba5c294aa7459c60fd9f78cb640d93d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "609fb5e8e5266b7b8008b4f1e30100c9dc1b5b20f5eb31361abcd749c2054462",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-07T17:22:11Z",
    "title_canon_sha256": "9ee1af973d04efab55c7bc8c341184da8f541824251ef46afd93b72e02342787"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.06597",
    "kind": "arxiv",
    "version": 2
  }
}