Pith Number

pith:3A3NSDLD

pith:2026:3A3NSDLDDAURSZEKB2WUDWSEKN

not attested not anchored not stored refs resolved

Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models

Anuj Sadani, Deepak Kumar

Locale-conditioned rotating few-shot prompts stop small language models from echoing demonstration examples during on-device PII substitution.

arxiv:2605.13538 v1 · 2026-05-13 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{3A3NSDLDDAURSZEKB2WUDWSEKN}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

With the fix, 482/482 unique Bonsai-1.7B calls succeed (no echoes) and produce locale-correct surrogates, although the SLM still copies from a small same-locale demonstration pool - a residual narrowness we quantify.

C2weakest assumption

That the observed NER performance gap is caused primarily by reduced variety in SLM outputs rather than by other unmeasured differences in the 160/40 subset or by the choice of XGLM-564M as the multilingual evaluator.

C3one line summary

Locale-conditioned rotating few-shot prompting eliminates demonstration regurgitation in 1.7B SLMs for PII substitution while producing more natural text than rule-based methods, though downstream NER training benefits more from synthetic variety than naturalness.

References

16 extracted · 16 resolved · 3 Pith anchors

[1] Faker: a Python package that generates fake data 2024

[2] llama.cpp: Port of LLaMA models in C/C++ 2024

[3] spaCy: Industrial-strength natural language processing in Python 2020

[4] Few-shot learning with multilingual language models 2022

[5] Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity 2022

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-18T02:44:24.088768Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d836d90d63182919648a0ead41da445340ce937cfd128a535c945fe435ff69ef

Aliases

arxiv: 2605.13538 · arxiv_version: 2605.13538v1 · doi: 10.48550/arxiv.2605.13538 · pith_short_12: 3A3NSDLDDAUR · pith_short_16: 3A3NSDLDDAURSZEK · pith_short_8: 3A3NSDLD

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/3A3NSDLDDAURSZEKB2WUDWSEKN \
  | 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: d836d90d63182919648a0ead41da445340ce937cfd128a535c945fe435ff69ef

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "08982f296d3b7011c8b7b2fdf6bec4c5c580d305c1cc7386049148fae213f8dc",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T13:47:11Z",
    "title_canon_sha256": "71ca1095213f9418fa258a120300c4beee4c761bb6f28c94731d6b266582527e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13538",
    "kind": "arxiv",
    "version": 1
  }
}