Pith Number

pith:T2OEVGYJ

pith:2026:T2OEVGYJ4EERBPHEFGGIXRM2XR

not attested not anchored not stored refs resolved

The Diffusion Encoder

Akhil Premkumar, Sarah Lucioni

Diffusion models can replace standard encoders in autoencoders when trained alternately with the decoder to align latent estimates.

arxiv:2605.13399 v1 · 2026-05-13 · cs.LG · cs.IT · math.IT

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{T2OEVGYJ4EERBPHEFGGIXRM2XR}

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

Our method enables more reliable synchronization between encoder and decoder, while preserving the simple and efficient training objective of standard diffusion models.

C2weakest assumption

That an alternating training schedule inspired by EM can transmit decoder gradients back to the diffusion encoder without causing instability or divergence in the latent estimates.

C3one line summary

A diffusion model serves as the encoder in an autoencoder when trained alternately with the decoder to resolve opposing update directions while retaining the standard diffusion training objective.

References

46 extracted · 46 resolved · 4 Pith anchors

[1] Auto-Encoding Variational Bayes 2014 · arXiv:1312.6114

[2] DIME: Diffusion-Based Maximum Entropy Reinforcement Learning 2025

[3] Soft Actor-Critic: Off- Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor 2018

[4] Q-Learning with Adjoint Matching 2026

[5] Inference Suboptimality in Variational Autoencoders 2018

Receipt and verification

First computed	2026-05-18T02:44:47.610852Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9e9c4a9b09e10910bce4298c8bc59abc7c17a36a7144adc1765bbae4e5498037

Aliases

arxiv: 2605.13399 · arxiv_version: 2605.13399v1 · doi: 10.48550/arxiv.2605.13399 · pith_short_12: T2OEVGYJ4EER · pith_short_16: T2OEVGYJ4EERBPHE · pith_short_8: T2OEVGYJ

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/T2OEVGYJ4EERBPHEFGGIXRM2XR \
  | 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: 9e9c4a9b09e10910bce4298c8bc59abc7c17a36a7144adc1765bbae4e5498037

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "20cb237f9e864eb1045f98640be732ce1f677698723774c2fe46a7c708d8711c",
    "cross_cats_sorted": [
      "cs.IT",
      "math.IT"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T11:54:43Z",
    "title_canon_sha256": "be762bfc797ccf2cd10a08b478f26dc5cab13e9d14ce9fa3a4dba410e09c5e8c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13399",
    "kind": "arxiv",
    "version": 1
  }
}