Pith Number

pith:PRXD77GH

pith:2025:PRXD77GHVSLLAXHBB2CTEWO3PA

not attested not anchored not stored refs pending

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback

Benjamin Matthias Ruppik, Carel van Niekerk, Hsien-Chin Lin, Milica Ga\v{s}i\'c, Renato Vukovic

arxiv:2507.21931 v1 · 2025-07-29 · cs.CL · 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{PRXD77GHVSLLAXHBB2CTEWO3PA}

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

5 papers in Pith

When Do Intrinsic Rewards Work for Code Reasoning? A Comprehensive Study

GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling

Trust Region On-Policy Distillation

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

Self-Rewarding Vision-Language Model via Reasoning Decomposition

Receipt and verification

First computed	2026-07-05T11:45:10.011308Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7c6e3ffcc7ac96b05ce10e853259db7838665a45e2f8247acbe1f05e61946987

Aliases

arxiv: 2507.21931 · arxiv_version: 2507.21931v1 · doi: 10.48550/arxiv.2507.21931 · pith_short_12: PRXD77GHVSLL · pith_short_16: PRXD77GHVSLLAXHB · pith_short_8: PRXD77GH

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/PRXD77GHVSLLAXHBB2CTEWO3PA \
  | 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: 7c6e3ffcc7ac96b05ce10e853259db7838665a45e2f8247acbe1f05e61946987

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "80ea73671bcbe11cda5466f9ca35f3d196451f5032dbb749b304440b6c650207",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-07-29T15:46:26Z",
    "title_canon_sha256": "76334b005aa82acabf355edd7dd40b1cdf6f57535886294522a6dfd75bcf16dc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2507.21931",
    "kind": "arxiv",
    "version": 1
  }
}