Pith Number

pith:GD7XVMZU

pith:2026:GD7XVMZUXZJUKCX5TLTQ7JGSIH

not attested not anchored not stored refs resolved

Learning Local Constraints for Reinforcement-Learned Content Generators

Ahmed Khalifa, Debosmita Bhaumik, Georgios N. Yannakakis, Julian Togelius

Constraining an RL content generator with local patterns learned by Wave Function Collapse produces playable and visually satisfying puzzle-platform levels.

arxiv:2605.13570 v1 · 2026-05-13 · 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{GD7XVMZUXZJUKCX5TLTQ7JGSIH}

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

the best of our trained generators produce visually satisfying and playable puzzle-platform game levels -- such as Lode Runner levels -- with desired global properties.

C2weakest assumption

That WFC-learned local constraints remain compatible with the RL reward signal and do not overly restrict the policy to the point where global properties cannot be achieved during training.

C3one line summary

Constraining a PCGRL generator's action space with locally learned WFC constraints yields visually satisfying and playable puzzle-platform levels with desired global properties.

References

40 extracted · 40 resolved · 2 Pith anchors

[1] Hierarchical semantic wave function collapse 2023

[2] Leveraging reinforcement learn- ing and wavefunctioncollapse for improved procedural level generation 2021

[3] Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. Openai gym, 2016 2016

[4] Tile-based map generation using wave function col- lapse in ’caves of qud’, 2022 2022

[5] Sturgeon-graph: Constrained graph generation from examples 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:23.379528Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

30ff7ab334be53450afd9ae70fa4d241d9b214c512bd3a054ec4a2dbd0ea6093

Aliases

arxiv: 2605.13570 · arxiv_version: 2605.13570v1 · doi: 10.48550/arxiv.2605.13570 · pith_short_12: GD7XVMZUXZJU · pith_short_16: GD7XVMZUXZJUKCX5 · pith_short_8: GD7XVMZU

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/GD7XVMZUXZJUKCX5TLTQ7JGSIH \
  | 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: 30ff7ab334be53450afd9ae70fa4d241d9b214c512bd3a054ec4a2dbd0ea6093

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "de20f2527edf952771ca2ecd8823de3ff1adfcb0ef1c9905fc186554e3d6a570",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T14:07:10Z",
    "title_canon_sha256": "5d5d41614467562af644e939666e1efeb26e05eb63c4c938de155d8448196d04"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13570",
    "kind": "arxiv",
    "version": 1
  }
}