Paper Citation Record · LEDGER

Training Language Models to Generate Quality Code with Program Analysis Feedback

As of 16 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 2 inbound Pith citation observations for arXiv:2505.22704.

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

pith.paper-citation-record.v1
2505.22704 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:05:02.006644Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-19T04:07:31.283348Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-19T04:12:02.886089Z

Reference resolution

32 of 32 outbound references displayed

verified exact1
verified fuzzy11
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5ca62695-c2c7-49af-af31-a005b60b6fbe · outbound

This paper cites Aho, Monica S.

Training Language Models to Generate Quality Code with Program Analysis Feedback Aho, Monica S

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:06.135389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b69e37c0-b0bc-478a-8ea9-9238ac7f9355 · outbound

This paper cites Bearer: Static application security testing (sast) tool.

Training Language Models to Generate Quality Code with Program Analysis Feedback Bearer: Static application security testing (sast) tool

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:05.974106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 259fba11-9ee5-4183-a195-facc5c07f03b · outbound

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

Training Language Models to Generate Quality Code with Program Analysis Feedback Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:58.231629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c67cf41f-8374-4792-b9ef-b4b90f6662ca · outbound

This paper cites A comprehensive study of llm secure code generation.

Training Language Models to Generate Quality Code with Program Analysis Feedback A comprehensive study of llm secure code generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:58.343500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb10acb-174c-40f0-81d2-ae3bcbc23691 · outbound

This paper cites StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback.

Training Language Models to Generate Quality Code with Program Analysis Feedback StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:58.439514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ed72c20-080e-4360-8174-a9e84ef6a0c4 · outbound

This paper cites Constrained Decoding for Secure Code Generation.

Training Language Models to Generate Quality Code with Program Analysis Feedback Constrained Decoding for Secure Code Generation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:58.524594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 484deb15-1a48-4b08-a34d-273bc18125e1 · outbound

This paper cites RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning.

Training Language Models to Generate Quality Code with Program Analysis Feedback RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:58.623446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c760b4cb-24b6-4e47-adc0-f6671a768ad6 · outbound

This paper cites Codeql: Semantic code analysis engine.

Training Language Models to Generate Quality Code with Program Analysis Feedback Codeql: Semantic code analysis engine

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:05.839474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c01c0d31-96ab-4fb5-ad76-efd1edc1618d · outbound

This paper cites Github copilot: Your ai pair programmer.

Training Language Models to Generate Quality Code with Program Analysis Feedback Github copilot: Your ai pair programmer

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:05.640188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ccf1f684-fabe-4cc6-98fd-f76d8f882da2 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Training Language Models to Generate Quality Code with Program Analysis Feedback DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:58.947933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7655e32-eedf-490d-90d1-9155d4608bb0 · outbound

This paper cites Large Language Models for Code: Security Hardening and Adversarial Testing.

Training Language Models to Generate Quality Code with Program Analysis Feedback Large Language Models for Code: Security Hardening and Adversarial Testing

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:05:02.921764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e175f7dc-7824-4f4e-af12-5670abf44ec7 · outbound

This paper cites an unresolved cited work.

Training Language Models to Generate Quality Code with Program Analysis Feedback Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:05.334653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 24aff923-53cf-46a3-b8b4-43f160115736 · outbound

This paper cites Measuring coding challenge competence with apps.

Training Language Models to Generate Quality Code with Program Analysis Feedback Measuring coding challenge competence with apps

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:05.021846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a900045f-3d70-4a91-b01d-04a5edd5e3d5 · outbound

This paper cites Qwen2.5-Coder Technical Report.

Training Language Models to Generate Quality Code with Program Analysis Feedback Qwen2.5-Coder Technical Report

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:59.498911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b43a0e2-45b5-4b95-bba7-5573f982563b · outbound

This paper cites Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models.

Training Language Models to Generate Quality Code with Program Analysis Feedback Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:59.596935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b5f7da6-277d-4d51-b69c-e4a193a199e5 · outbound

This paper cites CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning.

Training Language Models to Generate Quality Code with Program Analysis Feedback CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:59.720250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e969e35b-834f-40e2-bd3c-c8713d522bd4 · outbound

This paper cites Mypy: Optional static typing for python.

Training Language Models to Generate Quality Code with Program Analysis Feedback Mypy: Optional static typing for python

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:04.753026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8063a31e-e586-473a-9b7c-fce21ef5feb3 · outbound

This paper cites Acecoder: An effective prompting technique specialized in code generation.

Training Language Models to Generate Quality Code with Program Analysis Feedback Acecoder: An effective prompting technique specialized in code generation

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:04.479644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0fbe6af1-4e7f-4827-8a15-1378db50655c · outbound

This paper cites Wizardcoder: Empowering code large language models with evol-instruct.

Training Language Models to Generate Quality Code with Program Analysis Feedback Wizardcoder: Empowering code large language models with evol-instruct

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:04.176947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b8f14148-0272-42e1-add9-ad4236c1f2b4 · outbound

This paper cites Common weakness enumeration (cwe).

Training Language Models to Generate Quality Code with Program Analysis Feedback Common weakness enumeration (cwe)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:03.955212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5236a9fc-6890-43f9-84ad-702d29e79900 · outbound

This paper cites an unresolved cited work.

Training Language Models to Generate Quality Code with Program Analysis Feedback Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:00.254049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7d7e7de-f899-45c1-b2b4-6586bc9c59dd · outbound

This paper cites Promsec: Prompt optimization for secure generation of functional source code with large language models (llms).

Training Language Models to Generate Quality Code with Program Analysis Feedback Promsec: Prompt optimization for secure generation of functional source code with large language models (llms)

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:00.650025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb335b4-49d5-4d36-92b4-b56d3ea1f7cd · outbound

This paper cites Gpt-4.1, 2025.

Training Language Models to Generate Quality Code with Program Analysis Feedback Gpt-4.1, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:03.643099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dfae27df-cbd0-4803-b4fc-0074ef80d85e · outbound

This paper cites Bandit: Security linter for python source code.

Training Language Models to Generate Quality Code with Program Analysis Feedback Bandit: Security linter for python source code

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:03.426810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6c570066-f284-485d-974c-7c83a8259d40 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Training Language Models to Generate Quality Code with Program Analysis Feedback Proximal Policy Optimization Algorithms

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:01.474455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e9d0bcd-38ca-4b67-86c2-4108dd7f79f7 · outbound

This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.

Training Language Models to Generate Quality Code with Program Analysis Feedback CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:01.558235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad4b5ac-875a-4fbd-8816-8309f00a9f76 · outbound

This paper cites SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution.

Training Language Models to Generate Quality Code with Program Analysis Feedback SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:01.626359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37fbef5f-ad6f-407e-9dbe-aea64b4b9e05 · outbound

This paper cites Teaching language models to critique via reinforcement learning.

Training Language Models to Generate Quality Code with Program Analysis Feedback Teaching language models to critique via reinforcement learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:01.713256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7caa3c3-eb2b-4074-ba71-7ebfe9658875 · outbound

This paper cites DeepGlow: an efficient neural-network emulator of physical afterglow models for gamma-ray bursts and gravitational-wave events.

Training Language Models to Generate Quality Code with Program Analysis Feedback DeepGlow: an efficient neural-network emulator of physical afterglow models for gamma-ray bursts and gravitational-wave events

Reference 29

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T13:05:02.340963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8bb5c08d-0244-486d-968c-df316f3cdb58 · outbound

This paper cites Seccodeplt: A unified platform for evaluating the security of code genai, 2024.

Training Language Models to Generate Quality Code with Program Analysis Feedback Seccodeplt: A unified platform for evaluating the security of code genai, 2024

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:01.838728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1a162d-cc09-49fd-90a7-e166cce82c6c · outbound

This paper cites $\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis.

Training Language Models to Generate Quality Code with Program Analysis Feedback $\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:01.915820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 043a8083-a0eb-4820-80c4-e4a763ea9d35 · outbound

This paper cites SecCoder: Towards Generalizable and Robust Secure Code Generation.

Training Language Models to Generate Quality Code with Program Analysis Feedback SecCoder: Towards Generalizable and Robust Secure Code Generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:02.006644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6842ab4f-dede-4ac1-a765-d9ac3fe036b3 · inbound

MetaLint: Easy-to-Hard Generalization for Code Linting cites this paper.

MetaLint: Easy-to-Hard Generalization for Code Linting Training Language Models to Generate Quality Code with Program Analysis Feedback

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-19T04:12:02.888031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d19c9433-720e-452d-8de7-88c07d9c6459 · inbound

Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code cites this paper.

Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code Training Language Models to Generate Quality Code with Program Analysis Feedback

Reference 143

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:21:10.905622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.