Pith Number

pith:ST72OZ27

pith:2026:ST72OZ27VVT6YN5Q7GI4TNQNWP

not attested not anchored not stored refs resolved

Does Engram Do Memory Retrieval in Autoregressive Image Generation?

Chunbin Gu, Jinghao Wang, Pheng-Ann Heng, Qiyuan He

The Engram module in autoregressive image generation acts as a gated side-pathway rather than a content-addressed memory retriever.

arxiv:2605.13179 v1 · 2026-05-13 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ST72OZ27VVT6YN5Q7GI4TNQNWP}

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

these findings indicate that the Engram in AR image generation behaves not as a content-addressed retriever but as a gated architectural side-pathway: a hash-keyed residual stream whose benefit is dominated by the pathway itself, with the learned table contributing only a small distributional refinement.

C2weakest assumption

The 2D spatial n-gram hashing and gated fusion adaptations faithfully preserve the original Engram mechanism while allowing fair comparison to the pure AR baseline; if these changes fundamentally alter how the module operates, the mechanistic conclusions would not hold.

C3one line summary

Engram in AR image generation saves backbone FLOPs but trails pure AR baselines in FID and behaves as a gated side-pathway rather than a content-addressed retriever.

References

19 extracted · 19 resolved · 4 Pith anchors

[1] Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, and William T. Freeman. Maskgit: Masked generative image transformer. InCVPR, 2022 2022

[2] Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models 2026 · arXiv:2601.07372

[3] Imagenet: A large-scale hierarchical image database 2009

[4] Taming transformers for high-resolution image synthesis 2021

[5] Neural Turing Machines 2014 · arXiv:1410.5401

Receipt and verification

First computed	2026-05-18T03:08:56.439157Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

94ffa7675fad67ec37b0f991c9b60db3d7d59b5c85fd913127b89bc9ef44bc10

Aliases

arxiv: 2605.13179 · arxiv_version: 2605.13179v1 · doi: 10.48550/arxiv.2605.13179 · pith_short_12: ST72OZ27VVT6 · pith_short_16: ST72OZ27VVT6YN5Q · pith_short_8: ST72OZ27

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/ST72OZ27VVT6YN5Q7GI4TNQNWP \
  | 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: 94ffa7675fad67ec37b0f991c9b60db3d7d59b5c85fd913127b89bc9ef44bc10

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c5febe5cd2b72b0f2bf9fb9dcbaa6d7931bd6d335f183aa191ac84ac3bb5009a",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T08:40:46Z",
    "title_canon_sha256": "e9da8adc981aafb886a763f45d2312e71bb6b1248acf040732c3c48d6e592140"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13179",
    "kind": "arxiv",
    "version": 1
  }
}