Pith Number

pith:QOA5QNG3

pith:2015:QOA5QNG3U2R3MSNHHC6ARRQAF2

not attested not anchored not stored refs pending

Taming the Noise in Reinforcement Learning via Soft Updates

Ari Pakman, Naftali Tishby, Roy Fox

arxiv:1512.08562 v4 · 2015-12-28 · 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{QOA5QNG3U2R3MSNHHC6ARRQAF2}

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.

Cited by

6 papers in Pith

Multi-Armed Sampling Problem and the End of Exploration

Failure Modes of Maximum Entropy RLHF

Training Language Models to Self-Correct via Reinforcement Learning

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

Receipt and verification

First computed	2026-05-18T00:24:45.418249Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95

Aliases

arxiv: 1512.08562 · arxiv_version: 1512.08562v4 · doi: 10.48550/arxiv.1512.08562 · pith_short_12: QOA5QNG3U2R3 · pith_short_16: QOA5QNG3U2R3MSNH · pith_short_8: QOA5QNG3

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/QOA5QNG3U2R3MSNHHC6ARRQAF2 \
  | 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: 8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fdf93c4cbea5e0303e892876d91ee27fa323c7aaf22fd5dc3e7904d7fecf7fae",
    "cross_cats_sorted": [
      "cs.IT",
      "math.IT"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2015-12-28T23:59:12Z",
    "title_canon_sha256": "c4435343ce97d059fa561682a4773276d3c57c3bfbae22dc02d77c5a4a32f5f3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1512.08562",
    "kind": "arxiv",
    "version": 4
  }
}