Paper Citation Record · LEDGER

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach

As of 7 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2505.23953.

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

pith.paper-citation-record.v1
2505.23953 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:42:49.380605Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T12:28:04.662036Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T20:26:12.312629Z

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy16
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2d1d413a-cfde-4218-8e67-a108ba5800ef · outbound

This paper cites No Man is an Island: Towards Fully Automatic Programming by Code Search, Code Generation and Program Repair.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach No Man is an Island: Towards Fully Automatic Programming by Code Search, Code Generation and Program Repair

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.266982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf27e45-5821-4b0a-abf3-72d96962fd46 · outbound

This paper cites GPT-4 Technical Report.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.301532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c597eb55-f80a-413c-bfe7-e8d94f4ddcd1 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Chain-of-thought prompting elicits reasoning in large language models,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.399613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca7c204f-bb87-42c0-919e-75cc28bd74a8 · outbound

This paper cites Reflex- ion: Language agents with verbal reinforcement learning,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Reflex- ion: Language agents with verbal reinforcement learning,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.489296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7538d63-9f61-4f7a-a4be-3a284c70d6bf · outbound

This paper cites Cyclomatic complexity,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Cyclomatic complexity,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:52.347125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eff05077-bdf4-4797-a461-b66d3eb9981a · outbound

This paper cites Software complexity analysis using halstead metrics,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Software complexity analysis using halstead metrics,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:52.107139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a54ee7bc-c2a9-4800-8493-f81cc38ad761 · outbound

This paper cites an unresolved cited work.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:51.970786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc4b5b42-8b38-4b00-b62c-b926372ff371 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Evaluating Large Language Models Trained on Code

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.707195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8da40589-7982-481c-a1a6-af257376fc47 · outbound

This paper cites Logistic regression,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Logistic regression,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.745640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1492496d-7328-45a2-86c2-bb1931a9ee8b · outbound

This paper cites Gpt-3.5-turbo,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Gpt-3.5-turbo,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:51.754048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 82e6b995-8548-454b-954b-262c4aee58aa · outbound

This paper cites The Llama 3 Herd of Models.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.844950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec3497aa-42b8-4687-9535-00a18fd6a349 · outbound

This paper cites Program Synthesis with Large Language Models.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Program Synthesis with Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.884835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28fd7036-9151-4c9e-8d6d-786dd1e43b5f · outbound

This paper cites Leetcode dataset,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Leetcode dataset,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:51.576495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9d0603c5-dbf5-4981-8e85-c8684cdfcc6f · outbound

This paper cites Introduction to the shapley value,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Introduction to the shapley value,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:51.499699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 93263ceb-5838-459e-aa0e-6fbd614f96ef · outbound

This paper cites BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:47.989730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b64ace2c-b152-405f-86e2-9ca9929c968f · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Code Llama: Open Foundation Models for Code

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:48.021836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 906bae7e-5d62-4d27-b5a8-569c83fd7569 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:48.052643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4355666-d183-4f00-ae0c-a92f4165f873 · outbound

This paper cites Gpt-o3-mini,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Gpt-o3-mini,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:51.411825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 281931f0-19f6-45a7-8144-e57f288e0805 · outbound

This paper cites Parsel: Algorithmic reasoning with language models by composing decompositions,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Parsel: Algorithmic reasoning with language models by composing decompositions,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:51.273873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 953d045a-dbd6-40b1-a877-2de29bcb9a02 · outbound

This paper cites Anpl: towards natural programming with interactive decomposition,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Anpl: towards natural programming with interactive decomposition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:51.126668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ca285ce8-5ec6-45db-9b4f-e1da5d77c7e6 · outbound

This paper cites A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:48.283041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a02b37f-f55b-4716-ae10-2eb43e116c62 · outbound

This paper cites AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:48.318234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e48c0abb-38b3-46e7-a054-709324835ec9 · outbound

This paper cites Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:48.385369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7797ed5c-8f72-47d5-8ceb-9483a04ecb80 · outbound

This paper cites Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:48.458168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff59a357-265e-48f6-a87e-d5e16b697141 · outbound

This paper cites A survey on metric of software complexity,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach A survey on metric of software complexity,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:50.990468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9ec0a775-57bd-472c-b842-d1579a8404bd · outbound

This paper cites A pragmatic approach for hyper-parameter tuning in search-based test case generation,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach A pragmatic approach for hyper-parameter tuning in search-based test case generation,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:50.839308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 673717ef-94b6-46bf-b2c2-6d97721eb6df · outbound

This paper cites An empirical study on bug severity estimation using source code metrics and static analysis,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach An empirical study on bug severity estimation using source code metrics and static analysis,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:50.694054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ddfa489d-6048-4707-9dd4-5cec615d4a90 · outbound

This paper cites Analysis and modeling conditional mutual dependency of metrics in software defect prediction using latent variables,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Analysis and modeling conditional mutual dependency of metrics in software defect prediction using latent variables,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:50.513519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 459817a3-daf6-4175-bf9a-2f21768c9b4a · outbound

This paper cites Automatically learning semantic features for defect prediction,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Automatically learning semantic features for defect prediction,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:50.326852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a289458-ded9-4002-8664-1cd0659948e7 · outbound

This paper cites Continuous software bug prediction,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Continuous software bug prediction,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:50.193140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8f402f69-8672-4bb9-b03e-1491686418ac · outbound

This paper cites Feature selection, l 1 vs. l 2 regularization, and rotational invariance,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Feature selection, l 1 vs. l 2 regularization, and rotational invariance,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:50.010422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0e59e6a2-15b4-48ff-828a-257c8bc737b9 · outbound

This paper cites Gene selection for cancer classification using support vector machines,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Gene selection for cancer classification using support vector machines,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:49.826918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 82f7346e-64af-492f-8e2b-43b5bc6fdbab · outbound

This paper cites Correlation-based feature selection for machine learning,.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach Correlation-based feature selection for machine learning,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:49.263703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad89ffdc-a058-4693-8f79-c2b736181a4f · outbound

This paper cites A Unified Approach to Interpreting Model Predictions.

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach A Unified Approach to Interpreting Model Predictions

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:49.380605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 405a92cd-5fca-4046-aff2-35c4a4fa2a0a · inbound

Throttling Web Agents Using Reasoning Gates cites this paper.

Throttling Web Agents Using Reasoning Gates Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-05T12:28:04.662036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 003f8466-7227-4149-919d-d3db5316f2e2 · inbound

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval cites this paper.

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:26:12.314142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.