Paper Citation Record · LEDGER

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems

As of 18 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 5 inbound Pith citation observations for arXiv:2505.13546.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.13546 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:35:09.898417Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:26:27.695830Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-22T00:40:51.097386Z

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy12
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c697badb-72c8-47df-a2cc-4420684a0b8e · outbound

This paper cites LLM-AutoDiff: Auto-Differentiate Any LLM Workflow.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems LLM-AutoDiff: Auto-Differentiate Any LLM Workflow

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.771169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc6489c-72a6-4789-806a-3377495c30af · outbound

This paper cites Efficient multi-prompt evaluation of LLMs.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Efficient multi-prompt evaluation of LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.779264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1ed9ba4-16bb-4231-b6f8-117de28f23ba · outbound

This paper cites Concentration Inequalities: A Nonasymptotic Theory of Independence.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Concentration Inequalities: A Nonasymptotic Theory of Independence

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.267674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 20b32132-251e-481d-83f8-b0a8db913791 · outbound

This paper cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.256046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e91246e0-2bb3-46dd-879c-c8d65d7c9fce · outbound

This paper cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.790633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb9dd25a-877e-42ed-b689-abfbb54239e4 · outbound

This paper cites Generative Agents: Interactive Simulacra of Human Behavior.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Generative Agents: Interactive Simulacra of Human Behavior

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.244813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f15d743f-8d84-4215-845e-c75b19d56866 · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversa- tions.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversa- tions

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.232912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 76022750-cdac-4aca-a471-b031e8010743 · outbound

This paper cites Language Models are Few-Shot Learners.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Language Models are Few-Shot Learners

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.222047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a12b8a66-eae0-4a93-a281-764ce15165d1 · outbound

This paper cites Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.805168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc637efd-1499-44a6-be07-8b1219fbc4b0 · outbound

This paper cites Cross-Task Generalization via Natural Language Crowdsourcing Instructions.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Cross-Task Generalization via Natural Language Crowdsourcing Instructions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.808913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2e8aae8-5035-479a-9873-90518bac8511 · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.812646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e43520a-9e14-40f0-b0f0-9367b6ddb3f7 · outbound

This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems The Power of Scale for Parameter-Efficient Prompt Tuning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.816199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3214cee0-406f-4d75-a880-32d2a7a46216 · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Prefix-Tuning: Optimizing Continuous Prompts for Generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.819523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56ce45e0-a765-44b4-bf90-8e2368fca8c8 · outbound

This paper cites RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.822959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b486d3-9fde-4d80-8c8a-af868126f49a · outbound

This paper cites Large Language Models Are Human-Level Prompt Engineers.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Large Language Models Are Human-Level Prompt Engineers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.826580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bca9ce95-38b6-40b6-8229-c76562f9b215 · outbound

This paper cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.211847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 533d78ec-c8a0-4e07-b2dd-5ef81a2b117e · outbound

This paper cites Kullback and R.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Kullback and R

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.201694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 95731e7f-666a-4f52-bf4b-7b74ae1aa365 · outbound

This paper cites BERTScore: Evaluating Text Generation with BERT.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems BERTScore: Evaluating Text Generation with BERT

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.190889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0365e017-ddbf-446f-b3b4-0710dd3e3afe · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT- Networks.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Sentence-BERT: Sentence Embeddings using Siamese BERT- Networks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.180174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation eadf666d-721f-4c3f-96e8-54c37315dbeb · outbound

This paper cites Universal Sentence Encoder for English.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Universal Sentence Encoder for English

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.167922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fb94a454-ee5a-4405-b260-2a913a344ca2 · outbound

This paper cites Non-Determinism of "Deterministic" LLM Settings.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Non-Determinism of "Deterministic" LLM Settings

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.847839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 561a50ee-e1fc-4ab2-ab3f-3f3af366bbda · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.155503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 18609012-e8fb-4cd0-8dd2-25bb696bdd85 · outbound

This paper cites Are Large Language Models Consistent over Value-laden Questions?.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Are Large Language Models Consistent over Value-laden Questions?

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.854644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff87c08f-2265-441b-a084-6faa22a7c303 · outbound

This paper cites Beyond Accuracy: Behavioral Testing of NLP Models with CheckList.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Beyond Accuracy: Behavioral Testing of NLP Models with CheckList

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:35:10.143308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c9602a3a-3515-46ef-9855-5baab69a7af7 · outbound

This paper cites Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.861088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06305638-1c26-4d0b-9f9d-439bcd62a37f · outbound

This paper cites Data Interpreter: An LLM Agent For Data Science.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Data Interpreter: An LLM Agent For Data Science

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.865157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47239252-dd1a-4cad-92d8-9872b0894fcf · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.868777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22b345db-2f41-4855-a51a-ec92ef626598 · outbound

This paper cites Self-Evolving Multi-Agent Collaboration Networks for Software Development.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Self-Evolving Multi-Agent Collaboration Networks for Software Development

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.872460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa2b6d2b-96e6-40ee-994d-989ba15e8a2c · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Evaluating Large Language Models Trained on Code

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.876103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b30973ca-36d1-4fee-8ab2-5a959560b561 · outbound

This paper cites DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.880399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 671fd378-cb34-4757-8c2c-4c0b6310715d · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Measuring Mathematical Problem Solving With the MATH Dataset

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.884066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0804f88e-e849-480f-8acd-9ef3f452df19 · outbound

This paper cites InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.887686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb89272f-b359-44ef-9c7b-8ba0aa52b632 · outbound

This paper cites CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.891455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c311e2b2-7b34-47bd-b4be-832b6515aa67 · outbound

This paper cites A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.895038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a078fce0-5191-4245-ab95-3ffa43c90b28 · outbound

This paper cites ChemLLM: A Chemical Large Language Model.

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems ChemLLM: A Chemical Large Language Model

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:35:09.898417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b4f2e7ee-463c-497a-b3a0-43119574eb64 · inbound

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models cites this paper.

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T04:26:27.695830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8541d78-6217-4e5f-a137-fa8d260877a7 · inbound

Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing cites this paper.

Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:33:03.079044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72c8c0cc-ca66-467e-97f5-ca387eab47cd · inbound

GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis cites this paper.

GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:40:51.100834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d92a3d6c-5eba-4411-b26d-8f6d47172579 · inbound

Knowing How to Edit: Reliable Evaluation Signals for Diagnosing and Optimizing Prompts at Query Level cites this paper.

Knowing How to Edit: Reliable Evaluation Signals for Diagnosing and Optimizing Prompts at Query Level Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T20:29:13.400955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 226d97fc-a631-467a-a820-6e0c50f09089 · inbound

PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses cites this paper.

PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:00:02.944684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.