Pith Number

pith:XIZ37DTT

pith:2026:XIZ37DTT3E5YHYZF22DHZDQLJA

not attested not anchored not stored refs resolved

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

DongHeun Han, HyeongYeop Kang, SeongRae Noh, SeungWon Seo

Alice learns executable world models by refining failed candidate updates into hypothesis classes

arxiv:2605.16725 v1 · 2026-05-16 · 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{XIZ37DTT3E5YHYZF22DHZDQLJA}

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 Alice substantially improves executable world-model learning under prior misalignment, and ablations show that both class refinement and class-aware exploration contribute.

C2weakest assumption

That failed candidate updates provide structural signal revealing dynamics the current program had conflated, and that refining these into hypothesis classes yields compact preservation counterexamples sufficient for effective updates.

C3one line summary

Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.

References

37 extracted · 37 resolved · 6 Pith anchors

[1] Never give up: Learning directed exploration strategies.arXiv preprint arXiv:2002.06038, 2020 2002

[2] Exploration by random network distillation 2018 · arXiv:1810.12894

[3] Generating code world models with large language models guided by monte carlo tree search.Advances in Neural Information Processing Systems, 37:60429–60474, 2024 2024

[4] Stanley, and Jeff Clune 1901

[5] Diversity is All You Need: Learning Skills without a Reward Function 2018 · arXiv:1802.06070

Receipt and verification

First computed	2026-05-20T00:02:38.600366Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ba33bf8e73d93b83e325d6867c8e0b4817ff7a952183762f9e7bc9064a708d70

Aliases

arxiv: 2605.16725 · arxiv_version: 2605.16725v1 · doi: 10.48550/arxiv.2605.16725 · pith_short_12: XIZ37DTT3E5Y · pith_short_16: XIZ37DTT3E5YHYZF · pith_short_8: XIZ37DTT

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/XIZ37DTT3E5YHYZF22DHZDQLJA \
  | 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: ba33bf8e73d93b83e325d6867c8e0b4817ff7a952183762f9e7bc9064a708d70

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3bec55d75d813f3e7e727aab2bb3529e600a70edf771acacf2fe5d5ef4021952",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-16T00:18:22Z",
    "title_canon_sha256": "384c1aa69880624b23ac84fb58fd13d016a63bf9595c8bb40287786018492ac3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16725",
    "kind": "arxiv",
    "version": 1
  }
}