Paper Citation Record · LEDGER

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

As of 18 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 3 inbound Pith citation observations for arXiv:2508.10059.

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

pith.paper-citation-record.v1
2508.10059 v2

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T21:12:44.483546Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:17:49.699662Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T06:41:36.565022Z

Reference resolution

40 of 40 outbound references displayed

verified exact1
verified fuzzy19
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5f8e2d00-398e-4ff4-9739-92cd690f46ca · outbound

This paper cites Intellicode compose: Code generation using transformer,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Intellicode compose: Code generation using transformer,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:48.637666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 10cc8d13-747e-4db8-adb7-d65cd301a3e5 · outbound

This paper cites Programming is hard-or at least it used to be: Educational opportunities and challenges of ai code generation,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Programming is hard-or at least it used to be: Educational opportunities and challenges of ai code generation,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:39.947080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f89c3fd7-8380-4032-9ccd-d0ca42082086 · outbound

This paper cites Competition- level code generation with alphacode,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Competition- level code generation with alphacode,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:40.039480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b88b991e-0b19-427b-949f-0acaaccfe80a · outbound

This paper cites Llm-based code generation method for golang compiler testing,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Llm-based code generation method for golang compiler testing,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:48.427741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation da32c948-2404-40f4-a2be-17cafbe373f7 · outbound

This paper cites A review on code generation with llms: Application and evaluation,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement A review on code generation with llms: Application and evaluation,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:40.284470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a11142c6-d58a-4a2e-956a-58cbabad207d · outbound

This paper cites Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:48.266514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b7ffefdc-3b61-4c73-b19b-87e380d93875 · outbound

This paper cites Hlspilot: Llm-based high- level synthesis,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Hlspilot: Llm-based high- level synthesis,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:48.094497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 538ef311-4d17-451c-b258-615f8badb27d · outbound

This paper cites Uncovering llm-generated code: A zero-shot synthetic code detector via code rewrit- ing,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Uncovering llm-generated code: A zero-shot synthetic code detector via code rewrit- ing,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:47.949817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f6c72a80-6384-4179-a4f2-41e7cf57f354 · outbound

This paper cites Methodology for code synthesis evaluation of llms presented by a case study of chatgpt and copilot,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Methodology for code synthesis evaluation of llms presented by a case study of chatgpt and copilot,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:47.795755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b7107d50-4251-4af8-9dcc-3e9f8a8c5c06 · outbound

This paper cites Policy Filtration for RLHF to Mitigate Noise in Reward Models.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Policy Filtration for RLHF to Mitigate Noise in Reward Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-05T21:12:45.142668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9b939a93-5116-451a-b01f-0489329ea5b0 · outbound

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

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:41.213688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82c50f5a-6bb8-4537-bb03-d5df8cffdd36 · outbound

This paper cites Exploring and evaluating hallucinations in llm-powered code generation,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Exploring and evaluating hallucinations in llm-powered code generation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:41.387283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf6caa1c-c5e5-4b9c-9346-fdc20c65907e · outbound

This paper cites Llm hallucinations in practical code generation: Phenomena, mechanism, and mitigation,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Llm hallucinations in practical code generation: Phenomena, mechanism, and mitigation,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:47.595923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 03943476-6a0a-4ba5-b693-c3a6d85d0287 · outbound

This paper cites Llm is like a box of chocolates: the non-determinism of chatgpt in code generation,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Llm is like a box of chocolates: the non-determinism of chatgpt in code generation,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:47.438947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 241013d7-78e8-4257-a3e6-3e5900db6515 · outbound

This paper cites Limitations of formal methods and an approach to improvement,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Limitations of formal methods and an approach to improvement,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:47.289246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e8393f89-9ec0-4280-a3be-110cf29ccf8d · outbound

This paper cites Formal methods: Practice and experience,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Formal methods: Practice and experience,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:41.984276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7637f626-0a3c-4fc8-ade8-44c657fb06c0 · outbound

This paper cites Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:42.157612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b467118c-316d-469d-803a-92b3245d1696 · outbound

This paper cites Llm- based test-driven interactive code generation: User study and empirical evaluation,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Llm- based test-driven interactive code generation: User study and empirical evaluation,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:47.120275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 665c83b2-3cd5-498e-b72b-09e5d0450688 · outbound

This paper cites The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:42.386148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b66e05f-55a7-4e94-aae4-38f855cd5a32 · outbound

This paper cites From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:42.463310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a08b970-89ec-48d6-975a-dd371fee4d8c · outbound

This paper cites Apollo: Automated llm and lean collaboration for advanced formal reasoning,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Apollo: Automated llm and lean collaboration for advanced formal reasoning,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:42.580191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fd4ee5b-6798-4dc6-a3f1-54795930cb2d · outbound

This paper cites Llm-guided formal verification coupled with mutation testing,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Llm-guided formal verification coupled with mutation testing,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:46.952599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0bc4c367-1f9b-44eb-aeed-7b4486c39e37 · outbound

This paper cites Dehallucinating large language models using formal methods guided iterative prompting,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Dehallucinating large language models using formal methods guided iterative prompting,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:46.757300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f498ad32-15e3-473a-bcf8-366912cf6ed8 · outbound

This paper cites Enhancing reasoning capabilities of llms via principled synthetic logic corpus,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Enhancing reasoning capabilities of llms via principled synthetic logic corpus,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:46.557026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation be4baa25-070f-4361-9342-cea5481a0d48 · outbound

This paper cites LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:43.061768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4aeab6-0e39-4c5a-a469-b5feef693478 · outbound

This paper cites LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:43.176830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0de5dda0-26c9-497e-8698-f93dc6943105 · outbound

This paper cites Isr-llm: Iterative self- refined large language model for long-horizon sequential task planning,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Isr-llm: Iterative self- refined large language model for long-horizon sequential task planning,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:46.364460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ad88be47-41e0-4264-bf6a-9d51251f764c · outbound

This paper cites To believe or not to believe your llm: Iterative prompting for estimating epistemic uncertainty,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement To believe or not to believe your llm: Iterative prompting for estimating epistemic uncertainty,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:46.189240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e3268b7-a67a-416e-ac97-4af57a3e78e0 · outbound

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

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Reflex- ion: Language agents with verbal reinforcement learning,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:43.461307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f9c02fa-7964-4a66-ab86-9ab93cfa3b83 · outbound

This paper cites Coderl: Mastering code generation through pretrained models and deep reinforcement learning,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Coderl: Mastering code generation through pretrained models and deep reinforcement learning,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:46.017661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14990738-af3f-48ac-b010-6bf56f6018bb · outbound

This paper cites CodeT: Code Generation with Generated Tests.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement CodeT: Code Generation with Generated Tests

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:43.653944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25e6d507-5a1a-4194-8c27-d90ef20f99e8 · outbound

This paper cites TextGrad: Automatic "Differentiation" via Text.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement TextGrad: Automatic "Differentiation" via Text

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:43.795452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82fa2688-4cb9-4677-87c7-aa9d195e76fc · outbound

This paper cites Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:43.916068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cf5426c-7900-4f78-a8ff-4ad31f1bb174 · outbound

This paper cites Qwen2.5-Coder Technical Report.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Qwen2.5-Coder Technical Report

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:43.985545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6792afdf-8d83-4037-9d63-1e478ee55beb · outbound

This paper cites Qwen3 Technical Report.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Qwen3 Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:44.085991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c04a7bb-5415-478d-9d89-f4accc99cd82 · outbound

This paper cites Introducing GPT-4.1, GPT-4.1 Mini, and GPT-4.1 Nano,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Introducing GPT-4.1, GPT-4.1 Mini, and GPT-4.1 Nano,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:45.854346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5178fd09-aafa-44ba-bf4b-da5077207dbb · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Efficient memory management for large language model serving with pagedattention,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:44.255287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635c63a3-8f5b-4df4-ac90-5cb52b18b47f · outbound

This paper cites Evaluating large language models trained on code,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Evaluating large language models trained on code,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:44.334232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ffd127-cd8e-4f08-bfaa-48159c49c7c0 · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Livecodebench: Holistic and contamination free evaluation of large language models for code,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:45.585169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ebc00b27-b28a-4637-89b5-6553a467613a · outbound

This paper cites Problemset,.

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement Problemset,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:12:45.373299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation ffe57237-8a56-4e9d-ba26-fc5f51b0a9e7 · inbound

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair cites this paper.

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

Reference 96

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:41:36.566440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f3cba19-9de0-4813-bc49-6387983fb22e · inbound

Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination cites this paper.

Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-03T16:45:52.507347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f648a37a-8c09-49d7-ab1b-1edccfb46a98 · inbound

GraphAlignCoder: Aligning Program and Proof Graphs for Code Generation cites this paper.

GraphAlignCoder: Aligning Program and Proof Graphs for Code Generation CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:49.699662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.