Pith Number

pith:PWAJHOCC

pith:2026:PWAJHOCC3S65JQR64UQPXVBOGU

not attested not anchored not stored refs resolved

State-Centric Decision Process

Mahdi Imani, Mohsen Imani, Ryozo Masukawa, Sanggeon Yun, Sungheon Jeong

The State-Centric Decision Process lets agents build their own certified state spaces from raw language observations using natural-language predicates.

arxiv:2605.12755 v1 · 2026-05-12 · 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{PWAJHOCC3S65JQR64UQPXVBOGU}

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

SDP achieves the best training-free results on all five benchmarks, with the advantage widening as the horizon grows. The certified trajectories additionally support analyses unavailable to reactive agents, including per-predicate credit assignment, failure localization, partial-progress measurement, and modular operator replacement.

C2weakest assumption

That an agent can reliably commit to a natural-language predicate describing the desired world state and accurately verify whether the subsequent observation satisfies that predicate without external supervision or error.

C3one line summary

SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.

References

63 extracted · 63 resolved · 13 Pith anchors

[1] State abstractions for lifelong rein- forcement learning 2018

[2] GPT-4 Technical Report 2023 · arXiv:2303.08774

[3] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances 2022 · arXiv:2204.01691

[4] Hindsight experience replay.Advances in neural information processing systems, 30, 2017 2017

[5] Agent context protocols enhance collective in- ference.arXiv preprint arXiv:2505.14569, 2025 2025

Receipt and verification

First computed	2026-05-18T03:09:48.601076Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7d8093b842dcbdd4c23ee520fbd42e352aec45be011ebcabd7901c51ecc8519f

Aliases

arxiv: 2605.12755 · arxiv_version: 2605.12755v1 · doi: 10.48550/arxiv.2605.12755 · pith_short_12: PWAJHOCC3S65 · pith_short_16: PWAJHOCC3S65JQR6 · pith_short_8: PWAJHOCC

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/PWAJHOCC3S65JQR64UQPXVBOGU \
  | 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: 7d8093b842dcbdd4c23ee520fbd42e352aec45be011ebcabd7901c51ecc8519f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8dc8427e4292fb9771a26336d81959a93468d1aa1b21b855e278fbe4a49f0975",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-12T21:09:43Z",
    "title_canon_sha256": "c386154661080f376a7a0b3da60ff880ad94b0af8237e8ce84ed7a240f65d2f6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12755",
    "kind": "arxiv",
    "version": 1
  }
}