Pith Number

pith:IWPYLERG

pith:2026:IWPYLERGCBVQK4KIMNIRTU3MBX

not attested not anchored not stored refs pending

Supervised sparse auto-encoders for interpretable and compositional representations

Haixuan Xavier Tao, Hugo Wallner, Ouns El Harzli, Yoonsoo Nam

Supervised sparse auto-encoders achieve compositional generalization by jointly learning sparse concept embeddings and decoder weights.

arxiv:2602.00924 v3 · 2026-01-31 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IWPYLERGCBVQK4KIMNIRTU3MBX}

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

Validated on Stable Diffusion 3.5, our approach demonstrates compositional generalization, successfully reconstructing images with concept combinations unseen during training, and enabling feature-level intervention for semantic image editing without prompt modification.

C2weakest assumption

That jointly learning sparse concept embeddings with decoder weights will produce features that align with human semantics and support true compositional generalization without overfitting to the supervised training concepts or losing reconstruction fidelity.

C3one line summary

Supervised SAEs using concept embeddings from neural collapse theory achieve compositional generalization on unseen concept combinations in Stable Diffusion 3.5 for reconstruction and feature-level image editing.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:04:23.959441Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

459f859226106b057148635119d36c0dd29b1e7db78a291333705dceef851ba1

Aliases

arxiv: 2602.00924 · arxiv_version: 2602.00924v3 · doi: 10.48550/arxiv.2602.00924 · pith_short_12: IWPYLERGCBVQ · pith_short_16: IWPYLERGCBVQK4KI · pith_short_8: IWPYLERG

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/IWPYLERGCBVQK4KIMNIRTU3MBX \
  | 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: 459f859226106b057148635119d36c0dd29b1e7db78a291333705dceef851ba1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1c7b5a1f077e465aafbf6c1cd9cbf0b0269a3e935b4e23eb801430934d259132",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-01-31T22:47:54Z",
    "title_canon_sha256": "bfa5a1126602dbd2b9a2d6632a4e83070f74210d3a43e7e5451ab40fd5551906"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.00924",
    "kind": "arxiv",
    "version": 3
  }
}