Paper Citation Record · LEDGER

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

As of 12 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 2 inbound Pith citation observations for arXiv:2505.21425.

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

pith.paper-citation-record.v1
2505.21425 v3

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:34:08.351503Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:39:07.095045Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T07:10:59.734637Z

Reference resolution

17 of 17 outbound references displayed

verified exact1
verified fuzzy6
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 77e8c394-8097-4f59-8aa0-89f79891853f · outbound

This paper cites How important are good method names in neural code generation? a model robustness perspective,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation How important are good method names in neural code generation? a model robustness perspective,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:06.569986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a29b0b76-cfd5-4016-8c97-5ac09ee29fab · outbound

This paper cites A multi-modal transformer-based code summarization approach for smart contracts,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation A multi-modal transformer-based code summarization approach for smart contracts,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:06.639554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef47d936-eb7f-4211-9755-28f332c0e57a · outbound

This paper cites SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:06.749325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ac239e-3632-48be-bc5b-94e632e1e58c · outbound

This paper cites Redcode: Risky code execution and generation benchmark for code agents,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Redcode: Risky code execution and generation benchmark for code agents,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:34:09.493619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6efde41f-bcf2-4d9d-bf95-b187f4f96bec · outbound

This paper cites Onion: A simple and effective defense against textual backdoor attacks,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Onion: A simple and effective defense against textual backdoor attacks,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:06.967273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51e2ded-db8b-4205-9f2d-07aa2d074907 · outbound

This paper cites Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:07.048528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f7fa858-4e1c-44de-a2ac-b192d2d6a8ac · outbound

This paper cites Mitigating backdoor attacks in lstm-based text classification systems by backdoor keyword identification,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Mitigating backdoor attacks in lstm-based text classification systems by backdoor keyword identification,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:34:09.337076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0fa7d2fc-7cde-47e7-9250-30613634148d · outbound

This paper cites Badpre: Task-agnostic backdoor attacks to pre-trained nlp foundation models,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Badpre: Task-agnostic backdoor attacks to pre-trained nlp foundation models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:34:09.167418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 59afda3e-4be3-43a2-b404-6271f75ea40a · outbound

This paper cites Weight poisoning attacks on pretrained models,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Weight poisoning attacks on pretrained models,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:34:09.025161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 48283a21-99e7-4981-adb8-23c19d7403e9 · outbound

This paper cites Chain- of-thought in neural code generation: From and for lightweight language models,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Chain- of-thought in neural code generation: From and for lightweight language models,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:34:08.835048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 60fba37f-e81c-4507-b20f-35d6693c3b87 · outbound

This paper cites MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:34:08.487937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d89071c0-9589-4691-a7ad-114700ef3770 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Evaluating Large Language Models Trained on Code

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:07.833120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 673d9348-f5f1-47fc-9486-484d8202f960 · outbound

This paper cites Avatar: A parallel corpus for java-python program translation,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Avatar: A parallel corpus for java-python program translation,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:34:08.678505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation adcb5a05-c141-4f02-8b85-53204b1b8657 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Bleu: a method for automatic evaluation of machine translation,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:08.023037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3632ac6-b072-4fd9-8683-af0489c4a62d · outbound

This paper cites Meteor: An automatic metric for mt evalua- tion with improved correlation with human judgments,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Meteor: An automatic metric for mt evalua- tion with improved correlation with human judgments,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:08.110955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc5c8f0c-0217-40f5-b783-b2a9b4a98ae1 · outbound

This paper cites Rouge: A package for automatic evaluation of summaries,.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Rouge: A package for automatic evaluation of summaries,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:08.251152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0ee996-2aec-4992-9de1-0a1c6a966840 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:34:08.351503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 326a30d0-a3b5-4092-9455-00a264f51dd7 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

Reference 176

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:07.095045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04dded39-d3f6-41b6-9a26-434fc5d01254 · inbound

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning cites this paper.

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:10:59.738695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.