Pith Number

pith:YODX455Z

pith:2026:YODX455ZHPRD4VKF6V4QOVFS3U

not attested not anchored not stored refs resolved

Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations

Anjin Liu, Anna Leontjeva, Coco Wu, Devika Prasad, Henry Xiao, Luiz Pizzato, Luke Gerschwitz, Tong Li

Optimised segment-level annotations on decomposed prompts improve LLM responses while preserving the original to avoid degradation.

arxiv:2605.14561 v1 · 2026-05-14 · 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{YODX455ZHPRD4VKF6V4QOVFS3U}

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

optimised segment-level annotations can lead to improved LLM responses, with the original prompt retained as a candidate in the optimisation space to prevent performance degradation. Empirical evaluations indicate that PSAO benefits from annotations in terms of improved reasoning accuracy and self-consistency.

C2weakest assumption

That human-readable annotations such as {important} or {not important} can reliably guide LLMs in allocating focus and clarifying confusion during response generation without distorting the original intent.

C3one line summary

PSAO decomposes prompts into annotated segments to improve LLM reasoning accuracy and self-consistency as a proof-of-concept framework.

References

37 extracted · 37 resolved · 2 Pith anchors

[1] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning 2025 · arXiv:2507.19457

[2] Xcoop: Explainable prompt learning for computer-aided diagnosis via concept-guided context optimization 2024

[3] Evoprompting: Language models for code-level neu- ral architecture search 2023

[4] Instructzero: Effi- cient instruction optimization for black-box large language models 2024

[5] Training Verifiers to Solve Math Word Problems 2021 · arXiv:2110.14168

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:05.593273Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c3877e77b93be23e5545f5790754b2dd37723b083ba6c403ca7f58ec7c05e48e

Aliases

arxiv: 2605.14561 · arxiv_version: 2605.14561v1 · doi: 10.48550/arxiv.2605.14561 · pith_short_12: YODX455ZHPRD · pith_short_16: YODX455ZHPRD4VKF · pith_short_8: YODX455Z

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/YODX455ZHPRD4VKF6V4QOVFS3U \
  | 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: c3877e77b93be23e5545f5790754b2dd37723b083ba6c403ca7f58ec7c05e48e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d386dcca8e0a550f9a3907ccc549005c96ce5e8ba10c17631676c53ed2b7b3fe",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T08:33:47Z",
    "title_canon_sha256": "a0d8d703ed097db5ad5a57480c82d197c3ecc01fb858761dacd5d4cd285ae2e7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14561",
    "kind": "arxiv",
    "version": 1
  }
}