Paper Citation Record · LEDGER

Detecting Stealthy Data Poisoning Attacks in AI Code Generators

As of 17 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2508.21636.

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

pith.paper-citation-record.v1
2508.21636 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:09:30.625352Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy22
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c8f418f8-4737-49cc-a0dd-901aabed5db5 · outbound

This paper cites Quality in, quality out: Investigating training data’s role in ai code generation,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Quality in, quality out: Investigating training data’s role in ai code generation,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:35.803895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 648542f5-0987-4214-b599-3b1bcc0e033d · outbound

This paper cites Poisoning programs by un-repairing code: Security con- cerns of ai-generated code,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Poisoning programs by un-repairing code: Security con- cerns of ai-generated code,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:35.603093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 786753b8-3a4f-4459-8fcf-1975a8d66cca · outbound

This paper cites Backdooring neural code search,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Backdooring neural code search,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:35.395646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 93f7f206-dd2e-4052-9356-4d70bb809268 · outbound

This paper cites Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:35.247758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 072de786-d8e8-441e-ab38-eb98abfbbcd2 · outbound

This paper cites Backdoors in neural models of source code,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Backdoors in neural models of source code,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:35.070321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 63e674d0-7d29-4182-ab4f-d55dd4fd6652 · outbound

This paper cites Measuring impacts of poisoning on model parameters and embeddings for large language mod- els of code,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Measuring impacts of poisoning on model parameters and embeddings for large language mod- els of code,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:34.914363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c059c1e0-c25a-46b1-9820-bf79ce79e251 · outbound

This paper cites Stealthy backdoor attack for code models,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Stealthy backdoor attack for code models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:34.730323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation caeddfe9-433f-44f7-8614-6b560639ed0d · outbound

This paper cites Poison attack and poison detection on deep source code processing models,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Poison attack and poison detection on deep source code processing models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:34.591309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a6d6b428-cda7-4727-af52-d732cacc4f42 · outbound

This paper cites Trojanpuzzle: Covertly poisoning code-suggestion models,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Trojanpuzzle: Covertly poisoning code-suggestion models,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:34.407471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a8adbaf5-897d-4a2f-b3f3-d9314c38965b · outbound

This paper cites Spectral signatures in backdoor attacks,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Spectral signatures in backdoor attacks,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:34.280296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bfa1db9c-a730-4dbf-b7eb-986c0a627e47 · outbound

This paper cites Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T14:09:28.716206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a467f79-71e3-46cb-8761-72db5ddaeda2 · outbound

This paper cites Poison forensics: Traceback of data poisoning attacks in neural networks,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Poison forensics: Traceback of data poisoning attacks in neural networks,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:34.201104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4db8208c-b10f-4e93-b524-5b71dba9f02d · outbound

This paper cites Spectre: Defending against backdoor attacks using robust statistics,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Spectre: Defending against backdoor attacks using robust statistics,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:34.035884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1f41c4c9-58db-489d-87f0-2e5d5edb1800 · outbound

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

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Securityeval dataset: mining vulner- ability examples to evaluate machine learning-based code generation techniques,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:33.820368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 78eb0c3c-ecc5-4f64-985a-91b2c84d6994 · outbound

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

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Llmseceval: A dataset of natural language prompts for security evaluations,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:33.644275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f54d7848-a1ca-4104-a414-b21d6371ed34 · outbound

This paper cites CodeBERT: A Pre-Trained Model for Programming and Natural Languages.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators CodeBERT: A Pre-Trained Model for Programming and Natural Languages

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T14:09:29.240553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0cbe5df-e730-4afa-8005-baa65d241abe · outbound

This paper cites Codet5+: Open code large language models for code understanding and generation,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Codet5+: Open code large language models for code understanding and generation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:33.448653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e59e5976-1131-4366-b0a3-bcaa2b79c1e8 · outbound

This paper cites Ast-t5: structure-aware pretrain- ing for code generation and understanding,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Ast-t5: structure-aware pretrain- ing for code generation and understanding,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:33.224721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6a29736c-577f-4d08-8617-4da822ca37f7 · outbound

This paper cites Principal component analysis,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Principal component analysis,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:32.905480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e835cd7c-c73b-440b-ba51-e7352971d830 · outbound

This paper cites Visualizing data using t-sne.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Visualizing data using t-sne

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T14:09:29.721692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad74de08-109d-4874-bc18-c7f4c5ae11ba · outbound

This paper cites The k-means algorithm: A comprehensive survey and performance evaluation,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators The k-means algorithm: A comprehensive survey and performance evaluation,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:32.707617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 14c54feb-dbd4-4abc-a646-f6502d098261 · outbound

This paper cites Analysis of agglomerative clustering,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Analysis of agglomerative clustering,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:32.550340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 03abcd30-0aea-4042-a5db-ed27b123152c · outbound

This paper cites Static Code Analyzer,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Static Code Analyzer,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:32.289017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2f14b636-f980-460c-8587-8a0a372f9365 · outbound

This paper cites an unresolved cited work.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:09:32.036380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cd3e6c4d-7139-4465-bb16-941bf00f61b9 · outbound

This paper cites an unresolved cited work.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:09:31.815585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f1045bc-9152-4f44-bc99-6470e498185a · outbound

This paper cites 2021 OW ASP Top 10,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators 2021 OW ASP Top 10,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:31.512170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 35f7dccc-06b6-4dde-bec5-3e23bdb7438d · outbound

This paper cites an unresolved cited work.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:09:31.267517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 82dfc076-203d-4ed1-bc92-29f5d89968c9 · outbound

This paper cites Who evaluates the evaluators? on automatic metrics for assessing ai-based offensive code generators,.

Detecting Stealthy Data Poisoning Attacks in AI Code Generators Who evaluates the evaluators? on automatic metrics for assessing ai-based offensive code generators,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:09:31.004772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.