pith. sign in
Pith Number

pith:T64LZBYP

pith:2025:T64LZBYPDQ4SE7RCWRJP7J3Q6Q
not attested not anchored not stored refs pending

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Chengfeng Zhao, Huanxuan Liao, Jun Zhao, Kang Liu, Minzheng Wang, Qiunan Lu, Shizhu He, Tian Liang, Yuqiao Tan

arxiv:2512.19673 v3 · 2025-12-22 · cs.LG · cs.AI · cs.CL

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?
Add to your LaTeX paper 
\usepackage{pith}
\pithnumber{T64LZBYPDQ4SE7RCWRJP7J3Q6Q}

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

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Uncertainty Propagation in LLM-Based Systems
HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Receipt and verification
First computed 2026-06-01T01:02:27.841128Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

9fb8bc870f1c39227e22b452ffa770f4223fc82e447352543cb9502e25024a83

Aliases

arxiv: 2512.19673 · arxiv_version: 2512.19673v3 · doi: 10.48550/arxiv.2512.19673 · pith_short_12: T64LZBYPDQ4S · pith_short_16: T64LZBYPDQ4SE7RC · pith_short_8: T64LZBYP
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/T64LZBYPDQ4SE7RCWRJP7J3Q6Q \
  | 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: 9fb8bc870f1c39227e22b452ffa770f4223fc82e447352543cb9502e25024a83
Canonical record JSON 
{
  "metadata": {
    "abstract_canon_sha256": "59022c9732b39dae29c8404680c1952b14c84bab2bed30330c9e03dc7546f5df",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-12-22T18:51:48Z",
    "title_canon_sha256": "91e1005430805add82b33ced7dda6029f73e7743a960eb617cd373ecc8742a08"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.19673",
    "kind": "arxiv",
    "version": 3
  }
}