Pith Number

pith:LZJMXACJ

pith:2026:LZJMXACJ2QOP7HZXTFKINNIWCF

not attested not anchored not stored refs pending

Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding Agents

Bing Zhu, Guanghui Wang, Peiyang He, Wei Qiu, Xing Zhang, Yanwei Cui, Ziyuan Li

Negative constraints raise AI coding agent success rates while positive instructions lower them, and random rules match expert ones.

arxiv:2604.11088 v2 · 2026-04-13 · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LZJMXACJ2QOP7HZXTFKINNIWCF}

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

Rules improve performance by 7--14 percentage points, but random rules help as much as expert-curated ones -- suggesting rules work through context priming rather than specific instruction. Negative constraints are the only individually beneficial rule type, while positive directives actively hurt.

C2weakest assumption

That differences in agent success rates are caused by the rule types themselves rather than unmeasured factors in how rules are inserted into prompts or variations across agent runs.

C3one line summary

Negative constraints in agent rules improve coding performance via context priming while positive directives degrade it, with collective rules remaining helpful up to 50 rules.

Cited by

2 papers in Pith

Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

Receipt and verification

First computed	2026-05-29T01:05:09.360267Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5e52cb8049d41cff9f37995486b516115c78fdf867d1b9c76f5964c7ca721b64

Aliases

arxiv: 2604.11088 · arxiv_version: 2604.11088v2 · doi: 10.48550/arxiv.2604.11088 · pith_short_12: LZJMXACJ2QOP · pith_short_16: LZJMXACJ2QOP7HZX · pith_short_8: LZJMXACJ

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/LZJMXACJ2QOP7HZXTFKINNIWCF \
  | 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: 5e52cb8049d41cff9f37995486b516115c78fdf867d1b9c76f5964c7ca721b64

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9ddbe9ead40d1e75fbf7d5c1bd1d2688dc8c2b4a350c36f98988ecc1294a6228",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-13T07:10:01Z",
    "title_canon_sha256": "9e767301e3cdcde0e6a2b375adcccddcc3020265586dd650c38257304c39e7ca"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.11088",
    "kind": "arxiv",
    "version": 2
  }
}