Pith Number

pith:MFKKA2JM

pith:2026:MFKKA2JMUS7QF4QRBF7EVD6ZN6

not attested not anchored not stored refs pending

How Can Reinforcement Learning Achieve Expert-level Placement?

Chao Qian, Chengrui Gao, Ke Xue, Mingxuan Yuan, Peng Xie, Ruo-Tong Chen, Siyuan Xu, Tian Xu, Yunqi Shi, Zhi-Hua Zhou

Reinforcement learning reaches expert chip placement quality by learning a reward model directly from final expert layouts.

arxiv:2604.25191 v2 · 2026-04-28 · cs.AR · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{MFKKA2JMUS7QF4QRBF7EVD6ZN6}

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

Experiments show that our framework can efficiently learn from even a single design and generalize well to unseen cases.

C2weakest assumption

That step-by-step expert trajectories can be reliably inferred from final layouts alone without additional information about the expert's intermediate decisions or constraints.

C3one line summary

RL chip placement learns an implicit reward model from expert trajectories inferred from final layouts, closing the gap to human experts even from a single design.

Receipt and verification

First computed	2026-06-02T03:04:41.575556Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6154a0692ca4bf02f211097e4a8fd96f9ea2f7eda94c0114c86982752914caee

Aliases

arxiv: 2604.25191 · arxiv_version: 2604.25191v2 · doi: 10.48550/arxiv.2604.25191 · pith_short_12: MFKKA2JMUS7Q · pith_short_16: MFKKA2JMUS7QF4QR · pith_short_8: MFKKA2JM

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/MFKKA2JMUS7QF4QRBF7EVD6ZN6 \
  | 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: 6154a0692ca4bf02f211097e4a8fd96f9ea2f7eda94c0114c86982752914caee

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "86b64e6e00286b16d4046569d3ce6097cf6e6243df04765c74f591b340f1b36d",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AR",
    "submitted_at": "2026-04-28T03:55:03Z",
    "title_canon_sha256": "5c337aab732a35bda80d51e1390f69cf053d3d93f7a6d2e100aed2bf1a5b3723"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.25191",
    "kind": "arxiv",
    "version": 2
  }
}