Pith Number

pith:NFR7D3TK

pith:2026:NFR7D3TKF5FJXHBHE35KARRZL3

not attested not anchored not stored refs pending

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

Dandan Tu, Haoliang Li, Hui Liu, Kecheng Chen, Lingpeng Kong, Rui Liu, Shi Wu, Suiyun Zhang, Xijia Tao, Xinyu Fu, Yibing Liu, Ziru Liu

A new optimization framework for diffusion language models uses self-distilled inference trajectories and Boltzmann modeling of entropies to close the gap with standard supervised fine-tuning.

arxiv:2605.11854 v2 · 2026-05-12 · 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{NFR7D3TKF5FJXHBHE35KARRZL3}

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

TABOM achieves substantial gains in new domains, expands the effective knowledge boundary of DLMs, and significantly mitigates catastrophic forgetting compared with standard SFT.

C2weakest assumption

That modeling the inference unmasking preference as a Boltzmann distribution over predictive entropies and deriving a pairwise ranking objective from it will produce genuine knowledge acquisition rather than marginal or illusory gains.

C3one line summary

TABOM models inference unmasking preferences as a Boltzmann distribution over predictive entropies and derives a ranking loss to align DLM training with observed trajectories, yielding gains in new domains and reduced catastrophic forgetting versus standard SFT.

Cited by

2 papers in Pith

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

Receipt and verification

First computed	2026-05-20T00:04:36.307179Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6963f1ee6a2f4a9b9c2726faa046395efde5b325c11605e8d6fbf224148341e0

Aliases

arxiv: 2605.11854 · arxiv_version: 2605.11854v2 · doi: 10.48550/arxiv.2605.11854 · pith_short_12: NFR7D3TKF5FJ · pith_short_16: NFR7D3TKF5FJXHBH · pith_short_8: NFR7D3TK

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/NFR7D3TKF5FJXHBHE35KARRZL3 \
  | 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: 6963f1ee6a2f4a9b9c2726faa046395efde5b325c11605e8d6fbf224148341e0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dc78199a10256301f0dcd74b28737650a982dce09dcd11f273d65eb6aabd7b7c",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-12T09:39:06Z",
    "title_canon_sha256": "81b1fcd3984a8bed55856acf3b3d8e6dbe00b7b2cfc8a57fc276301cb0e49e40"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11854",
    "kind": "arxiv",
    "version": 2
  }
}