Pith Number

pith:TFE67VM3

pith:2026:TFE67VM32IMOJC2JF3LBMDWZR7

not attested not anchored not stored refs resolved

R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning

Donghyeok Lee, Jinsik Kim, Sanghyeob Song, Sungroh Yoon

A non-centered objective in self-predictive learning resolves zero-centering conflicts to stabilize representations under intensive experience reuse.

arxiv:2605.14026 v1 · 2026-05-13 · cs.LG · 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{TFE67VM32IMOJC2JF3LBMDWZR7}

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

At a UTD ratio of 20, R2R2 improves TD7 by ~22% and provides additional gains on top of SimbaV2-SPL, which itself establishes a new state-of-the-art.

C2weakest assumption

That the identified conflict between standard zero-centering and SPL spectral properties is the primary driver of representation instability, and that the proposed non-centered objective directly causes the observed performance gains rather than other unstated experimental factors.

C3one line summary

R2R2 introduces a non-centered regularization objective for SPL that addresses conflicts with spectral properties, leading to better performance on continuous control tasks at high UTD ratios.

References

42 extracted · 42 resolved · 5 Pith anchors

[1] Lillicrap and Jonathan J 2016

[2] 9th International Conference on Learning Representations, 2021

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

[4] Soft Actor-Critic Algorithms and Applications 2018 · arXiv:1812.05905

[5] Forty-second International Conference on Machine Learning, 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:12.892050Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9949efd59bd218e48b492ed6160ed98fd96894e604f503eaf748c8584a1bbea3

Aliases

arxiv: 2605.14026 · arxiv_version: 2605.14026v1 · doi: 10.48550/arxiv.2605.14026 · pith_short_12: TFE67VM32IMO · pith_short_16: TFE67VM32IMOJC2J · pith_short_8: TFE67VM3

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/TFE67VM32IMOJC2JF3LBMDWZR7 \
  | 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: 9949efd59bd218e48b492ed6160ed98fd96894e604f503eaf748c8584a1bbea3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1df157a638430dd2d94906311f82297777152af0776ee975bb312b5ac726780d",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T18:38:32Z",
    "title_canon_sha256": "c31eda74cff35518c2b3c575cdccd4f6365eedf9fe3f61f218166ccb8bddbe9f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14026",
    "kind": "arxiv",
    "version": 1
  }
}