Pith Number

pith:DKZKRXDQ

pith:2026:DKZKRXDQCU3YI5Q5ZXUSFZECDX

not attested not anchored not stored refs resolved

TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints

Shuhei Tarashima, Yoshio Kato

TruncProof uses an LL(1) parser to approximate the fewest tokens still needed for a valid JSON at every decoding step, letting the model finish inside a hard token budget.

arxiv:2605.13076 v1 · 2026-05-13 · cs.CL · cs.FL · cs.SE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DKZKRXDQCU3YI5Q5ZXUSFZECDX}

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

TruncProof successfully generates syntactically correct outputs even under strict token constraints.

C2weakest assumption

That the LL(1) parser approximation of minimum completion tokens remains accurate enough across varied JSON structures and does not cause premature termination or invalid outputs when the grammar is complex.

C3one line summary

TruncProof lets LLMs generate syntactically valid JSON within strict token limits by approximating completion token counts via LL(1) parser lookahead.

References

32 extracted · 32 resolved · 2 Pith anchors

[1] MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning, 2024

[2] Visual Programming: Compositional Visual Reasoning Without Training, 2023

[3] OpenAI, “Structured model outputs,” https://platform.openai.com/docs/guides/structured-outputs/json-mode (accessed December 2025) 2025

[4] Increase output consistency (JSON mode), 2025

[5] Google, “Structured Outputs,” https://ai.google.dev/gemini- api/docs/structured-output (accessed December 2025) 2025

Receipt and verification

First computed	2026-05-18T03:08:58.767538Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1ab2a8dc70153784761dcde922e4821de68ad0f73e0cafe8c979fb61f58d9d36

Aliases

arxiv: 2605.13076 · arxiv_version: 2605.13076v1 · doi: 10.48550/arxiv.2605.13076 · pith_short_12: DKZKRXDQCU3Y · pith_short_16: DKZKRXDQCU3YI5Q5 · pith_short_8: DKZKRXDQ

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/DKZKRXDQCU3YI5Q5ZXUSFZECDX \
  | 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: 1ab2a8dc70153784761dcde922e4821de68ad0f73e0cafe8c979fb61f58d9d36

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4648a7bff61fa9140adea98f0750d0b3b6d1e1241bb53204e16b6ebca99241c9",
    "cross_cats_sorted": [
      "cs.FL",
      "cs.SE"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T06:49:08Z",
    "title_canon_sha256": "a78d613a3e23f8d7fe947dc6b4e5d00ee1ad6af9eeb7cf5128878688dfb2ee76"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13076",
    "kind": "arxiv",
    "version": 1
  }
}