Paper Citation Record · LEDGER

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis

As of 9 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2509.00038.

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

pith.paper-citation-record.v1
2509.00038 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:13:54.245487Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

21 of 21 outbound references displayed

verified exact2
verified fuzzy11
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3dfc7eb0-8626-4c33-a378-f95dd56e10d7 · outbound

This paper cites Meerpohl, and Angelika Eisele-Metzger.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Meerpohl, and Angelika Eisele-Metzger

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:13:52.850546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fafb3077-301b-40ef-b0a3-d0d3aa841120 · outbound

This paper cites an unresolved cited work.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T17:13:52.895439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6230737b-69d8-4d1e-8bf6-a0bf9e508377 · outbound

This paper cites Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T17:13:52.950973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10d2e2ae-f6ec-48f1-a8fa-6aa090174121 · outbound

This paper cites What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:13:54.709479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0c6303c6-b9a1-4eed-92bc-a1f4cdcedac0 · outbound

This paper cites Responsible ai in the generative era, May 2023.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Responsible ai in the generative era, May 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:57.298017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f56ea301-a87b-46da-bb90-e2d936763424 · outbound

This paper cites Benchmarking prompt sensitivity in large language models.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Benchmarking prompt sensitivity in large language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T17:13:53.183804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 097947dc-6052-4c9c-b302-820f9bad615b · outbound

This paper cites A reproducibility and generalizability study of large language models for query generation.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis A reproducibility and generalizability study of large language models for query generation

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:57.104768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8658831c-e12f-4bb9-8584-55cdcbe96541 · outbound

This paper cites Efficacy of large language models for systematic reviews.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Efficacy of large language models for systematic reviews

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:56.946683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ca059ba3-419f-4b90-a92a-2d9465acd318 · outbound

This paper cites Title and abstract screening for literature reviews using large language models: an exploratory study in the biomedical domain.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Title and abstract screening for literature reviews using large language models: an exploratory study in the biomedical domain

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:56.653269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6586d2f4-9fd3-4e3a-85bf-44936f9ef893 · outbound

This paper cites Prompting is all you need: Llms for systematic review screening.medRxiv, pages 2024–06, 2024.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Prompting is all you need: Llms for systematic review screening.medRxiv, pages 2024–06, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:56.396585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ea88254a-511b-489b-a189-3d77c427b1db · outbound

This paper cites Streamlining systematic reviews with large language models using prompt engineering and retrieval augmented generation.BMC medical research methodology, 25(1):130, 2025.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Streamlining systematic reviews with large language models using prompt engineering and retrieval augmented generation.BMC medical research methodology, 25(1):130, 2025

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:56.182303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3290ab32-c62a-427a-a799-bf54ebd88a0b · outbound

This paper cites Development of prompt templates for large language model-driven screening in systematic reviews.Annals of Internal Medicine, 178(3):389–401, 2025.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Development of prompt templates for large language model-driven screening in systematic reviews.Annals of Internal Medicine, 178(3):389–401, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:55.981401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c26f41a1-5050-4ff1-87b2-1627672780ac · outbound

This paper cites Automation of systematic reviews with large language models.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Automation of systematic reviews with large language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:55.766994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bd8e3e36-1fda-4627-9ca5-8fe7bb346c43 · outbound

This paper cites Language models for data extraction and risk of bias assessment in complementary medicine.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Language models for data extraction and risk of bias assessment in complementary medicine

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:55.532478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cd999a59-96b7-47ab-8554-dc274490cb48 · outbound

This paper cites an unresolved cited work.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-05T17:13:55.417576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 22011d5f-ef3c-46bc-87af-976e57eb0068 · outbound

This paper cites Prompt engineering in consistency and reliability with the evidence-based guideline for llms.NPJ digital medicine, 7(1):41, 2024.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Prompt engineering in consistency and reliability with the evidence-based guideline for llms.NPJ digital medicine, 7(1):41, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:55.250935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3a83cecb-d5c0-43d4-a9d9-978a19acfc71 · outbound

This paper cites Assessing the risk of bias in randomized clinical trials with large language models.JAMA Network Open, 7(5):e2412687–e2412687, 05 2024.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Assessing the risk of bias in randomized clinical trials with large language models.JAMA Network Open, 7(5):e2412687–e2412687, 05 2024

Reference 17

Resolution: verified exact; raw_fallback, observed 2026-08-05T17:13:54.553670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9d157bc7-361d-4686-8bca-bc7a51885b60 · outbound

This paper cites an unresolved cited work.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-05T17:13:55.101259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 292b7988-6bfe-439d-bf65-e6f6b131f904 · outbound

This paper cites Optimizinginstructionsanddemonstrationsformulti-stagelanguagemodelprograms.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Optimizinginstructionsanddemonstrationsformulti-stagelanguagemodelprograms

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:13:54.915574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 54fdb85b-9af6-4a64-b709-cb8bddf6105c · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T17:13:54.147437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7029828f-3886-4ae3-b3a0-a5365c0a6efc · outbound

This paper cites GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T17:13:54.245487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.