Pith Number

pith:BE3XEHDF

pith:2026:BE3XEHDFIO333TGJSXD235QPQH

not attested not anchored not stored refs pending

Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration

Bryan Kian Hsiang Low, Manh Cuong Dao, Phi Le Nguyen, Quang Hung Pham, Thao Nguyen Truong, Trong Nghia Hoang

Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions.

arxiv:2602.08920 v2 · 2026-02-09 · 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{BE3XEHDFIO333TGJSXD235QPQH}

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

Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution. This probability path can then be recompiled on a diffusion process with a unified transition model to enable principled propagation of representation uncertainty throughout the pre-trained model's architecture while maintaining its original predictive performance.

C2weakest assumption

That modeling each feature transformation block as a probabilistic mapping accurately captures and propagates representation uncertainty without introducing systematic biases or changing the model's learned behavior in unintended ways.

C3one line summary

Diffusion-inspired probabilistic mappings enable principled uncertainty propagation through pre-trained transformer layers without degrading accuracy.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:23.692577Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd

Aliases

arxiv: 2602.08920 · arxiv_version: 2602.08920v2 · doi: 10.48550/arxiv.2602.08920 · pith_short_12: BE3XEHDFIO33 · pith_short_16: BE3XEHDFIO333TGJ · pith_short_8: BE3XEHDF

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/BE3XEHDFIO333TGJSXD235QPQH \
  | 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: 0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3b38d6ee4539924e9dff3f78f5919e8b3a2aa8934f8050ecaae12b555d80e742",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-02-09T17:24:47Z",
    "title_canon_sha256": "276eeb634f74cbb01273749e5037273208011d522f29e72ffc205b22f4a5bf9b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.08920",
    "kind": "arxiv",
    "version": 2
  }
}