Pith Number

pith:QIGCND7F

pith:2026:QIGCND7F5EA5UUZFFISGBCF4LU

not attested not anchored not stored refs resolved

Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers

Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi, Marcella Cornia, Sara Sarto

A small set of massive activation channels in Diffusion Transformers controls image semantics in function, space, and transfer.

arxiv:2605.13974 v1 · 2026-05-13 · cs.CV · cs.AI · cs.MM

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{QIGCND7F5EA5UUZFFISGBCF4LU}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

despite their sparsity, these few channels effectively draw the whole picture, in three complementary senses: functionally critical, spatially organized, and transferable.

C2weakest assumption

That the identification of massive channels via magnitude statistics is stable across prompts and models and that the controlled disruption probe isolates their causal role without confounding effects from the rest of the network dynamics.

C3one line summary

A sparse set of massive activation channels in DiTs carries semantic information, proven critical by disruption tests, spatially aligned with image subjects via clustering, and transferable for semantic interpolation between prompts.

References

41 extracted · 41 resolved · 4 Pith anchors

[1] Building normalizing flows with stochastic interpolants 2023

[2] All are Worth Words: A ViT Backbone for Diffusion Models 2023

[3] Tiny Inference-Time Scaling with Latent Verifiers 2026

[4] SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation 2025

[5] Vision Transformers Need Registers 2024

Receipt and verification

First computed	2026-05-17T23:39:13.458382Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

820c268fe5e901da53252a246088bc5d17b86e8743f2d57332aefa6ff59f0df3

Aliases

arxiv: 2605.13974 · arxiv_version: 2605.13974v1 · doi: 10.48550/arxiv.2605.13974 · pith_short_12: QIGCND7F5EA5 · pith_short_16: QIGCND7F5EA5UUZF · pith_short_8: QIGCND7F

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/QIGCND7F5EA5UUZFFISGBCF4LU \
  | 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: 820c268fe5e901da53252a246088bc5d17b86e8743f2d57332aefa6ff59f0df3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "72e124ef19189a9715e1e702a5809224fc9ed0ca6baee97b9179e5ebe6338d0e",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.MM"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T18:00:12Z",
    "title_canon_sha256": "ebcb4ed9a826ce4fa6a782d6e769fc40ec2ea6c98664c13101099536b6fae800"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13974",
    "kind": "arxiv",
    "version": 1
  }
}