Paper Citation Record · LEDGER

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models

As of 9 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 2 inbound Pith citation observations for arXiv:2502.06039.

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

pith.paper-citation-record.v1
2502.06039 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:00:30.502504Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T18:41:18.266271Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

23 of 23 outbound references displayed

verified exact0
verified fuzzy14
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a3a855af-b95d-4b38-bbb6-fa99390cd2ed · outbound

This paper cites Do users write more insecure code with ai assistants?.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Do users write more insecure code with ai assistants?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T17:00:30.424474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6817bca-ce47-40cd-a6b9-bbac6c595fc6 · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T17:00:30.428292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94da71c1-07be-4b2e-8c93-73439d4d942c · outbound

This paper cites Llmseceval: A dataset of natural language prompts for security evaluations,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Llmseceval: A dataset of natural language prompts for security evaluations,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.903664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0195563c-8341-4d13-a7fe-67b9a87a9060 · outbound

This paper cites Securityeval dataset: mining vulnerability examples to evaluate machine learning-based code generation techniques,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Securityeval dataset: mining vulnerability examples to evaluate machine learning-based code generation techniques,

Reference 4

Resolution: malformed identifier; doi_truncated, observed 2026-08-08T17:00:30.533448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 61cd14df-9602-4338-9e02-688cc7c10dff · outbound

This paper cites find bug variants with patterns that look like source code.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models find bug variants with patterns that look like source code

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.894366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e44c594f-6f4d-4a7d-82db-ca8dc16d0851 · outbound

This paper cites an unresolved cited work.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:00:30.884908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8d6dd596-0f46-4873-b478-2d286e71d9e6 · outbound

This paper cites Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T17:00:30.448721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e527895d-dd42-4076-83d5-c76061acfa99 · outbound

This paper cites Asleep at the keyboard? assessing the security of github copilot’s code contributions,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Asleep at the keyboard? assessing the security of github copilot’s code contributions,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.875332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 40fc6567-0669-4cad-8e63-d286c876512b · outbound

This paper cites How secure is code generated by chatgpt?.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models How secure is code generated by chatgpt?

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.865601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad637ca4-12c8-44a0-b4aa-c4921128ea8a · outbound

This paper cites [Online].

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models [Online]

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.856238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e89f275-13dc-49a2-8358-52d8b34ab118 · outbound

This paper cites Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T17:00:30.464049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf89ba3a-87da-4c2c-983b-1add75420d1e · outbound

This paper cites Original-date: 2021-09-30T16:06:12Z.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Original-date: 2021-09-30T16:06:12Z

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.846712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 848f49fe-884f-49cc-b185-3f1c7d932551 · outbound

This paper cites Time to separate from stackoverflow and match with chatgpt for encryption,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Time to separate from stackoverflow and match with chatgpt for encryption,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.837505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4a62ff18-4144-4c7f-83d2-93a00c91306b · outbound

This paper cites Chatgpt’s potential in cryptography misuse detection: A compara- tive analysis with static analysis tools,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Chatgpt’s potential in cryptography misuse detection: A compara- tive analysis with static analysis tools,

Reference 14

Resolution: metadata mismatch; raw_fallback, observed 2026-08-08T17:00:30.659880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6b4bbb02-05f1-4d65-a38b-885ee715680a · outbound

This paper cites Prompting Techniques for Secure Code Generation: A Systematic Investigation.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Prompting Techniques for Secure Code Generation: A Systematic Investigation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T17:00:30.480022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a851e3c6-22a2-4084-8903-793b80e2fb8f · outbound

This paper cites Purplellama codeshield,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Purplellama codeshield,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.817234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fc6f1deb-a487-4314-acbc-b6c798abfd91 · outbound

This paper cites Llm security guard for code,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Llm security guard for code,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.806053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dc357e86-6ef7-406e-8759-94dda40dc5d7 · outbound

This paper cites GitHub Copilot Chat and pull request summaries are now powered by GPT-4o · GitHub Changelog,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models GitHub Copilot Chat and pull request summaries are now powered by GPT-4o · GitHub Changelog,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.782871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8407446b-5ffd-4074-8534-5cb6d257f681 · outbound

This paper cites Available: https://api.semanticscholar.or g/CorpusID:269502004.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Available: https://api.semanticscholar.or g/CorpusID:269502004

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.794592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 34acae99-0fca-4852-9386-4adb322ccafd · outbound

This paper cites Betterchatgpt,.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Betterchatgpt,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.759530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f8018117-2623-4ea0-abfa-17d93060d32b · outbound

This paper cites Available: https://github.blog/changelo g/2024-07-31-github-copilot-chat-and-pull-request-sum maries-are-now-powered-by-gpt-4o/.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Available: https://github.blog/changelo g/2024-07-31-github-copilot-chat-and-pull-request-sum maries-are-now-powered-by-gpt-4o/

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.772147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f09206d3-a19c-45a9-aa1f-f86038d13837 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Evaluating Large Language Models Trained on Code

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T17:00:30.498975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffca8383-e35a-4c57-a6a6-d28c8b9a6d1e · outbound

This paper cites Available: https://arxiv.org/abs/2406.061 64.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models Available: https://arxiv.org/abs/2406.061 64

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:00:30.827903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 2f3baa25-29d5-4bc0-863f-78f3f5d84b53 · inbound

WildCode Revisited: A Comprehensive Empirical Study on the Security of LLM-Generated Code cites this paper.

WildCode Revisited: A Comprehensive Empirical Study on the Security of LLM-Generated Code Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:18.266271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd1eae40-6734-4481-9eed-29c9891ec775 · inbound

The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting cites this paper.

The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-30T15:13:30.346665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.