Pith Number

pith:BB6YAIRN

pith:2026:BB6YAIRNV7TEOSVZAORFFULTGQ

not attested not anchored not stored refs resolved

Learning POMDP World Models from Observations with Language-Model Priors

Alfonso Amayuelas, Bernhard Sch\"olkopf, David Hyland, Frederik Panse, Lancelot Da Costa, Mathis Fajeau, Mridul Sharma, Philipp Hennig, Tim Z. Xiao, Valentin Six

An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access.

arxiv:2605.13740 v1 · 2026-05-13 · 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{BB6YAIRNV7TEOSVZAORFFULTGQ}

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

Despite using strictly less information, Pinductor matches the performance and sample efficiency of LLM-based POMDP learning methods that assume privileged access to the hidden state, while significantly surpassing the sample efficiency of tabular POMDP baselines.

C2weakest assumption

That an LLM can reliably propose and iteratively refine POMDP transition and observation models whose belief-based likelihood on limited trajectories corresponds to the true underlying dynamics.

C3one line summary

Pinductor leverages language-model priors to learn POMDP world models from limited trajectories, matching privileged-access methods in performance and exceeding tabular baselines in sample efficiency.

References

60 extracted · 60 resolved · 4 Pith anchors

[1] Sutton and Andrew G 2018

[2] World Models 2018 · arXiv:1803.10122

[3] Training Agents Inside of Scalable World Models 2025 · arXiv:2509.24527

[4] Aggregate: count rows whereCOUNTRY= Algeria. [target: Country] 1965 · doi:10.1016/0022-247x(65)90154-x

[5] Planning and acting in partially observable stochastic domains 1998 · doi:10.1016/s0004-3702(98)00023-x

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:16.468229Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41

Aliases

arxiv: 2605.13740 · arxiv_version: 2605.13740v1 · doi: 10.48550/arxiv.2605.13740 · pith_short_12: BB6YAIRNV7TE · pith_short_16: BB6YAIRNV7TEOSVZ · pith_short_8: BB6YAIRN

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/BB6YAIRNV7TEOSVZAORFFULTGQ \
  | 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: 087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "78e6322cca9170d5f72fbcd8225e80abe9f22040ec3b5cb2e64e0faaaf2a8616",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T16:18:15Z",
    "title_canon_sha256": "ad83f015af5c17608de2bbe5b5343528b73018893b8c25ece0eb63c19beacdf2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13740",
    "kind": "arxiv",
    "version": 1
  }
}