Pith Number

pith:JMJJNPZB

pith:2023:JMJJNPZBO6PRVNC2QRNEBSWN33

not attested not anchored not stored refs resolved

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, Tim Rockt\"aschel

An LLM can improve prompting by evolving both the task prompts and the mutation rules that generate them.

arxiv:2309.16797 v1 · 2023-09-28 · cs.CL · cs.AI · cs.LG · cs.NE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JMJJNPZBO6PRVNC2QRNEBSWN33}

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

Promptbreeder outperforms state-of-the-art prompt strategies such as Chain-of-Thought and Plan-and-Solve Prompting on commonly used arithmetic and commonsense reasoning benchmarks. Furthermore, Promptbreeder is able to evolve intricate task-prompts for the challenging problem of hate speech classification.

C2weakest assumption

That the LLM can generate useful mutations and provide reliable fitness evaluations on a training set without systematic biases or errors that would derail the evolutionary process.

C3one line summary

Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.

References

296 extracted · 296 resolved · 67 Pith anchors

[1] Show Your Work: Scratchpads for Intermediate Computation with Language Models 2021 · arXiv:2112.00114

[2] The Hitchhiker's Guide to the Galaxy , author=. 1995 , publisher= 1995

[3] NeurIPS , year =

[5] The Eleventh International Conference on Learning Representations, 2023

[6] gradient descent

Formal links

2 machine-checked theorem links

Cited by

32 papers in Pith

Residual Skill Optimization for Text-to-SQL Ensembles

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

Harnesses for Inference-Time Alignment over Execution Trajectories

TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization

PRISM: Prompt Reliability via Iterative Simulation and Monitoring for Enterprise Conversational AI

Receipt and verification

First computed	2026-05-17T23:38:48.545777Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4b1296bf21779f1ab45a845a40cacddeff4d6a06eb4c42057b7fc3ddd4e5c667

Aliases

arxiv: 2309.16797 · arxiv_version: 2309.16797v1 · doi: 10.48550/arxiv.2309.16797 · pith_short_12: JMJJNPZBO6PR · pith_short_16: JMJJNPZBO6PRVNC2 · pith_short_8: JMJJNPZB

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/JMJJNPZBO6PRVNC2QRNEBSWN33 \
  | 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: 4b1296bf21779f1ab45a845a40cacddeff4d6a06eb4c42057b7fc3ddd4e5c667

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "72442a4596cb224cd8ca06a06d4d596f0073c6c055ab633d35e6e856a0f40a39",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG",
      "cs.NE"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-09-28T19:01:07Z",
    "title_canon_sha256": "4244f6eb42bf5cfaa0a8ca2bc7803a3815d151f208b15816561832a5396f68b0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2309.16797",
    "kind": "arxiv",
    "version": 1
  }
}