CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs | Paper Citation Record

Observation 65788c0f-6182-4abf-b3a8-2ea9b74c138c · outbound

This paper cites GPT-4 Technical Report.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:46.476756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75df5980-73d5-411e-8495-bbdb621b2640 · outbound

This paper cites An Empirical Study of AI Generated Text Detection Tools.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs An Empirical Study of AI Generated Text Detection Tools

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:46.570106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 908da8b7-9eeb-4478-9439-254c9cab0d7e · outbound

This paper cites Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku, 2024

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:46.633741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7846d60-9b79-475a-9822-16282d44c1d2 · outbound

This paper cites Claude 3.7 Sonnet and Claude Code, 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Claude 3.7 Sonnet and Claude Code, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:46.720560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a100e3-a86e-4296-89d1-260fca603978 · outbound

This paper cites Is github’s copilot as bad as humans at introducing vulnerabilities in code?Empirical Software Engineering, 28(6):129, 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Is github’s copilot as bad as humans at introducing vulnerabilities in code?Empirical Software Engineering, 28(6):129, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:46.811473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a0349f-1f09-4419-bb99-36ab95a46fc6 · outbound

This paper cites Random forests.Machine learning, 45:5–32, 2001.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Random forests.Machine learning, 45:5–32, 2001

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:46.895270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f391913e-6860-425b-8fa2-3debfa1511e7 · outbound

This paper cites Membership inference attacks from first principles.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Membership inference attacks from first principles

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:46.976947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e3022a3-1094-44a2-af28-e5090a1fb735 · outbound

This paper cites R package version 3.0.1.1.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs R package version 3.0.1.1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.063202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 553cb2d9-df04-4555-913c-b75ef7780dab · outbound

This paper cites Github code clean dataset, 2022.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Github code clean dataset, 2022

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.129620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02afa950-9b55-48b6-b04f-744abf07e8c5 · outbound

This paper cites Github code dataset, 2022.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Github code dataset, 2022

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.200058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f25dda91-c58c-43df-8202-91a4e16cfd1a · outbound

This paper cites Vulnerabilities in ai code generators: Exploring targeted data poisoning attacks.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Vulnerabilities in ai code generators: Exploring targeted data poisoning attacks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.294524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29e82846-deea-4d38-bd2e-2d9edfe7f36b · outbound

This paper cites Cursor: The AI Code Editor, 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Cursor: The AI Code Editor, 2023

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.393332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b0a11d0-a7f0-462f-8638-6c5988df77d1 · outbound

This paper cites Plagiarism in the age of massive generative pre-trained transformers (gpt-3).Ethics in Science and Environmental Politics, 21:17–23, 2021.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Plagiarism in the age of massive generative pre-trained transformers (gpt-3).Ethics in Science and Environmental Politics, 21:17–23, 2021

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.467782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9338dc5a-b143-4bc3-821b-57e1450a2458 · outbound

This paper cites AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.550790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7d6f9c8-d5dd-4eab-8e0f-659fe2ae56a6 · outbound

This paper cites The DeepFake Detection Challenge (DFDC) Dataset.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs The DeepFake Detection Challenge (DFDC) Dataset

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.640002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d87665b-4f0b-46c3-8a0e-7128c09be92f · outbound

This paper cites Codep: grammatical seq2seq model for general-purpose code generation.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Codep: grammatical seq2seq model for general-purpose code generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.701676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08fb92ab-8479-4797-be7c-5184de1e9f47 · outbound

This paper cites JaCoText: A Pretrained Model for Java Code-Text Generation.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs JaCoText: A Pretrained Model for Java Code-Text Generation

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:55:17.120274Z

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 cc471623-5e94-487d-a09f-a0dd57b31ff3 · outbound

This paper cites Out of the bleu: how should we assess quality of the code generation models?Journal of Systems and Software, 203:111741, 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Out of the bleu: how should we assess quality of the code generation models?Journal of Systems and Software, 203:111741, 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.862883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11467041-3d7d-44fc-acf8-15269374ff63 · outbound

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

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs CodeBERT: A Pre-Trained Model for Programming and Natural Languages

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:47.920730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21847269-8275-48a4-b353-0e7bb165121f · outbound

This paper cites Introducing GitHub Copilot: your AI pair programmer, 2022.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Introducing GitHub Copilot: your AI pair programmer, 2022

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.011427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e6ddef-b792-4499-8ca8-05d7ac0df019 · outbound

This paper cites What makes good in-context demonstrations for code intelligence tasks with llms? InIEEE/ACM International Conference on Automated Software Engineering (ASE), pages 761–773, 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs What makes good in-context demonstrations for code intelligence tasks with llms? InIEEE/ACM International Conference on Automated Software Engineering (ASE), pages 761–773, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.070030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1528c165-1662-4f98-a82a-3165eaa55899 · outbound

This paper cites Gltr: Statistical detection and visualization of generated text.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Gltr: Statistical detection and visualization of generated text

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.124138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 314297cd-8c44-4ef9-b4a0-4a1e554b2176 · outbound

This paper cites A survey on the possibilities & impossibilities of ai-generated text detection.Transactions on Machine Learning Research (TMLR), 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs A survey on the possibilities & impossibilities of ai-generated text detection.Transactions on Machine Learning Research (TMLR), 2023

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.246520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5aac917-e193-4767-ad10-2fbec12deecd · outbound

This paper cites Deepfake video detection using recurrent neural networks.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Deepfake video detection using recurrent neural networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.359564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13457b0-5431-42a2-b472-218cb58cd458 · outbound

This paper cites Graphcodebert: Pre-training code representations with data flow.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Graphcodebert: Pre-training code representations with data flow

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.449654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05003157-91eb-4798-8360-04d2c36081b1 · outbound

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

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.545437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb20765c-9e15-4507-8edc-b618ad05b088 · outbound

This paper cites Biscope: Ai-generated text detection by checking memorization of preceding tokens.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Biscope: Ai-generated text detection by checking memorization of preceding tokens

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.665601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c66b5304-5d20-4b43-abe3-3212d8cf7a90 · outbound

This paper cites Spotting llms with binoculars: Zero-shot detection of machine-generated text.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Spotting llms with binoculars: Zero-shot detection of machine-generated text

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.809631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5195c632-aa5c-4485-855a-96398f705a7d · outbound

This paper cites Denoising diffusion probabilistic models.Advances in Neural Information Processing Systems (NeurIPS), 33:6840–6851, 2020.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Denoising diffusion probabilistic models.Advances in Neural Information Processing Systems (NeurIPS), 33:6840–6851, 2020

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.908202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83737ca2-14d0-46cf-85c5-01beb47d2d14 · outbound

This paper cites Qwen2.5-Coder Technical Report.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Qwen2.5-Coder Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:48.989561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77d0cb4e-9f09-4066-ab9d-84f237151c12 · outbound

This paper cites Rethinking plagiarism in the era of generative ai.Journal of Intelligent Communication, 3(2):20–31, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Rethinking plagiarism in the era of generative ai.Journal of Intelligent Communication, 3(2):20–31, 2024

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:49.120454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3207f12b-4c39-4ebc-951d-9d6ed0e8ceb6 · outbound

This paper cites Whodunit: Classifying code as human authored or gpt-4 generated-a case study on codechef problems.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Whodunit: Classifying code as human authored or gpt-4 generated-a case study on codechef problems

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:49.242525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc477be6-3ca6-452d-a785-58be0314634a · outbound

This paper cites Automatic detection of generated text is easiest when humans are fooled.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Automatic detection of generated text is easiest when humans are fooled

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:49.340671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4238f08-8892-4f25-8231-5600621c9da7 · outbound

This paper cites Swe-bench: Can language models resolve real-world github issues? InInternational Conference on Learning Representations (ICLR), 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Swe-bench: Can language models resolve real-world github issues? InInternational Conference on Learning Representations (ICLR), 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:49.537272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bae908c6-127e-4bda-a198-82489ae72e37 · outbound

This paper cites Access the latest 2.0 experimental models in the gemini app., 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Access the latest 2.0 experimental models in the gemini app., 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:49.661149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 605bc256-bacb-4710-8e72-c6021ee8bb78 · outbound

This paper cites Vulnerability handling of ai- generated code-existing solutions and open challenges.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Vulnerability handling of ai- generated code-existing solutions and open challenges

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:49.780282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d508cc1b-25f4-4f13-bd1b-d3a77ffe37be · outbound

This paper cites Gemini 2.0 is now available to everyone, 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Gemini 2.0 is now available to everyone, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:49.898415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbda737d-454c-453b-ba59-b83e84ff4e8e · outbound

This paper cites Does attitude towards plagiarism predict aigiarism using chatgpt?AI and Ethics, 5(1):677–688, 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Does attitude towards plagiarism predict aigiarism using chatgpt?AI and Ethics, 5(1):677–688, 2025

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:50.058627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef0bb54f-4125-47f8-89f4-f384d8462faf · outbound

This paper cites Will chatgpt g et you caught? rethinking of plagiarism detection.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Will chatgpt g et you caught? rethinking of plagiarism detection

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:50.183926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64ffc721-c503-4bb6-a5a5-533ecc3ba99f · outbound

This paper cites How secure is code generated by chatgpt? InIEEE international conference on systems, man, and cybernetics (SMC), pages 2445–2451.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs How secure is code generated by chatgpt? InIEEE international conference on systems, man, and cybernetics (SMC), pages 2445–2451

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:26.240995Z

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 03f30dd7-d73a-47ee-bd15-91d0063106e0 · outbound

This paper cites Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense.Advances in Neural Information Processing Systems (NeurIPS), 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense.Advances in Neural Information Processing Systems (NeurIPS), 2023

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:26.074964Z

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 4271435f-c3b5-455a-8867-637eaf646188 · outbound

This paper cites Detecting fake content with relative entropy scoring.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Detecting fake content with relative entropy scoring

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:25.908463Z

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 50499960-1047-4a1f-b5a3-ade3debd7f65 · outbound

This paper cites Protecting intellectual property of large language model-based code generation apis via watermarks.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Protecting intellectual property of large language model-based code generation apis via watermarks

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:25.821311Z

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 cabc3883-4bb6-4818-80ea-24f5fff2cfc9 · outbound

This paper cites DeepSeek-V3 Technical Report.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs DeepSeek-V3 Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:50.744812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da2f7b4-1105-407c-a195-1bc12dcf90ad · outbound

This paper cites an unresolved cited work.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:55:25.697427Z

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 04279a04-6e3d-4f41-8e20-d41d409b3ac1 · outbound

This paper cites CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:51.004303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce6caf2-b835-4f6e-80a1-10112003ecd9 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:51.120028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6f9638a-d993-4bd4-bf4d-944c3afec798 · outbound

This paper cites Raidar: generative ai detection via rewriting.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Raidar: generative ai detection via rewriting

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:25.537792Z

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 db5bea98-ac35-408c-8e6a-9907e16e7a86 · outbound

This paper cites On the robustness of code generation techniques: An empirical study on github copilot.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs On the robustness of code generation techniques: An empirical study on github copilot

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:25.415448Z

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 47c2b334-6ec8-4be7-84ef-3bb770d4ba7f · outbound

This paper cites Llama 3.3: Model cards & prompt formats, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Llama 3.3: Model cards & prompt formats, 2024

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:25.275821Z

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 a1845f18-307f-48db-99d2-ef1065386dff · outbound

This paper cites Detectgpt: Zero-shot machine-generated text detection using probability curvature.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Detectgpt: Zero-shot machine-generated text detection using probability curvature

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:25.167755Z

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 369ee951-331b-4b17-a544-0fc92734f160 · outbound

This paper cites Is this Snippet Written by ChatGPT? An Empirical Study with a CodeBERT-Based Classifier.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Is this Snippet Written by ChatGPT? An Empirical Study with a CodeBERT-Based Classifier

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:51.700600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e054e314-9f13-4178-bf36-13dc638c012a · outbound

This paper cites Gptsniffer: A codebert-based classifier to detect source code written by chatgpt.Journal of Systems and Software, 214:112059, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Gptsniffer: A codebert-based classifier to detect source code written by chatgpt.Journal of Systems and Software, 214:112059, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.981311Z

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 5607cbcf-e488-48c7-945f-c638c8485b33 · outbound

This paper cites Poisoned chatgpt finds work for idle hands: Exploring developers’ coding practices with insecure suggestions from poisoned ai models.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Poisoned chatgpt finds work for idle hands: Exploring developers’ coding practices with insecure suggestions from poisoned ai models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.839371Z

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 16b5d11e-f0ca-4610-be35-b2a5a824779c · outbound

This paper cites Introducing ChatGPT, 2022.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Introducing ChatGPT, 2022

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:51.919051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e47c2de-2fd7-4582-a635-8af1d6a61da5 · outbound

This paper cites Gpt-4o mini: advancing cost-efficient intelligence, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Gpt-4o mini: advancing cost-efficient intelligence, 2024

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:51.992202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adbea689-e8b3-492f-b51e-222122821c97 · outbound

This paper cites Openai o3-mini: Pushing the frontier of cost-effective reasoning, 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Openai o3-mini: Pushing the frontier of cost-effective reasoning, 2025

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.666988Z

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 3f3a22e2-6ddf-4c0d-8dc1-a910825615d8 · outbound

This paper cites CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:52.108811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a74c8129-f622-4c8e-855d-711bc48a174f · outbound

This paper cites Assessing ai detectors in identifying ai-generated code: Implications for education.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Assessing ai detectors in identifying ai-generated code: Implications for education

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.515159Z

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 1b147bce-2743-4336-be30-1d54c61c8701 · outbound

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

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Bleu: A method for automatic evaluation of machine translation

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.371342Z

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 68814478-2094-4fa8-9715-03362c8d9dfa · outbound

This paper cites Asleep at the keyboard? assessing the security of github copilot’s code contributions.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Asleep at the keyboard? assessing the security of github copilot’s code contributions

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.265456Z

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 b8253700-57d5-448a-87ba-54f616a19d6b · outbound

This paper cites Magecode: Machine- generated code detection method using large language models.IEEE Access, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Magecode: Machine- generated code detection method using large language models.IEEE Access, 2024

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.178275Z

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 b9be9d4a-a780-403d-b1ff-d1c738eadafe · outbound

This paper cites Introducing gemini 2.0: our new ai model for the agentic era, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Introducing gemini 2.0: our new ai model for the agentic era, 2024

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:24.021607Z

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 353bcb8a-68f2-4f89-85f2-ebea9ed390cf · outbound

This paper cites Using tf-idf to determine word relevance in document queries.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Using tf-idf to determine word relevance in document queries

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:23.877765Z

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 77607fbd-f9cc-4b54-9e84-827390f386e8 · outbound

This paper cites CodeBLEU: a Method for Automatic Evaluation of Code Synthesis.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs CodeBLEU: a Method for Automatic Evaluation of Code Synthesis

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:52.586166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aea7182-b91b-4944-a0e6-0b80e6e140b3 · outbound

This paper cites The perceptron: a probabilistic model for information storage and organization in the brain.Psychological review, 65(6):386, 1958.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs The perceptron: a probabilistic model for information storage and organization in the brain.Psychological review, 65(6):386, 1958

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:52.664974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01af329a-b3ef-47a6-bfcf-632bd019bb96 · outbound

This paper cites FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:52.729191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc0d9a15-6988-4450-9b53-7e21e5f7b7c4 · outbound

This paper cites Can AI-Generated Text be Reliably Detected?.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Can AI-Generated Text be Reliably Detected?

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T13:54:52.803803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f655c91-4889-4576-9e70-790a4b834762 · outbound

This paper cites Automated detection of ai-obfuscated plagiarism in modeling assignments.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Automated detection of ai-obfuscated plagiarism in modeling assignments

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:23.647131Z

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 7c3dd540-98d5-48df-8e2d-9f9244f49fba · outbound

This paper cites Between lines of code: Unraveling the distinct patterns of machine and human programmers.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Between lines of code: Unraveling the distinct patterns of machine and human programmers

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:23.470078Z

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 0c1ca927-6b1f-407a-a316-2911d4455c3b · outbound

This paper cites Deep unsupervised learning using nonequilibrium thermodynamics.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Deep unsupervised learning using nonequilibrium thermodynamics

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:23.301606Z

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 78b2e5a4-a0c9-442b-8f13-4145bc6d8800 · outbound

This paper cites 2024 Stack Overflow Developer Survey, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs 2024 Stack Overflow Developer Survey, 2024

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:23.023700Z

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 c3bd3099-8ece-4dc6-bf6f-a010a95a4eb1 · outbound

This paper cites Developer Perspectives on Licensing and Copyright Issues Arising from Generative AI for Software Development.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Developer Perspectives on Licensing and Copyright Issues Arising from Generative AI for Software Development

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:14.040744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1c00e4-1d96-44f0-bb43-aa7ee7d7cd28 · outbound

This paper cites Plagiarism in ai empowered world.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Plagiarism in ai empowered world

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:22.748784Z

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 ee171013-724e-4eb6-a7ac-0ff12e27303b · outbound

This paper cites An empirical study on automatically detecting ai-generated source code: How far are we? InInternational Conference on Software Engineering (ICSE), 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs An empirical study on automatically detecting ai-generated source code: How far are we? InInternational Conference on Software Engineering (ICSE), 2025

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:22.569105Z

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 0fa2b0ba-a5c4-4881-8712-9fa7925527eb · outbound

This paper cites Bugs in large language models generated code: An empirical study.Empirical Software Engineering, 30(3):1–48, 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Bugs in large language models generated code: An empirical study.Empirical Software Engineering, 30(3):1–48, 2025

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:22.322393Z

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 ff6127b3-03dc-40ee-8637-e058f3d68f20 · outbound

This paper cites How secure is ai-generated code: a large-scale comparison of large language models.Empirical Software Engineering, 30(2):1–42, 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs How secure is ai-generated code: a large-scale comparison of large language models.Empirical Software Engineering, 30(2):1–42, 2025

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:22.045275Z

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 6587dbf4-3410-4e7e-8012-c34f119d7781 · outbound

This paper cites Llms in web development: Evaluating llm-generated php code unveiling vulnerabilities and limitations.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Llms in web development: Evaluating llm-generated php code unveiling vulnerabilities and limitations

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:21.795506Z

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 281323d5-087a-459e-a11e-f0f9bc864f63 · outbound

This paper cites Turingbench: A benchmark environ- ment for turing test in the age of neural text generation.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Turingbench: A benchmark environ- ment for turing test in the age of neural text generation

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:21.551090Z

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 be9e6b2a-63ed-4c8d-abd5-81e52907e025 · outbound

This paper cites A critical look at ai-generate software: Coding with the new ai tools is both irresistible and dangerous.IEEE Spectrum, 60(7):34–39, 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs A critical look at ai-generate software: Coding with the new ai tools is both irresistible and dangerous.IEEE Spectrum, 60(7):34–39, 2023

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:21.423137Z

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 b88f5d05-c87f-4528-b0b1-f8c8780fe4c7 · outbound

This paper cites Attention is all you need.Advances in Neural Information Processing Systems (NeurIPS), 30, 2017.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Attention is all you need.Advances in Neural Information Processing Systems (NeurIPS), 30, 2017

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:21.314436Z

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 9d273f42-c329-43ba-bd73-61fc2f03955b · outbound

This paper cites Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:14.361719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a4c4378-4bcb-4f06-b2ce-31c15e7b716b · outbound

This paper cites Openhands: An open platform for ai software developers as generalist agents.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Openhands: An open platform for ai software developers as generalist agents

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:21.222402Z

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 d7b5277a-0773-4316-95da-07206b479896 · outbound

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

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Codet5+: Open code large language models for code understanding and generation

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:21.117660Z

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 75d1735f-1810-49cb-ab70-67083d7d1190 · outbound

This paper cites A new era of plagiarism the danger of cheating using ai.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs A new era of plagiarism the danger of cheating using ai

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:21.003759Z

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 17920c00-40ea-4080-908b-2bac02b2510b · outbound

This paper cites Do llms know to respect copyright notice? InConference on Empirical Methods in Natural Language Processing (EMNLP), pages 20604–20619, 2024.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Do llms know to respect copyright notice? InConference on Empirical Methods in Natural Language Processing (EMNLP), pages 20604–20619, 2024

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:20.853496Z

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 4dbac241-c745-401e-a5f6-e9b4a06dcd99 · outbound

This paper cites One Size Does Not Fit All: Investigating Efficacy of Perplexity in Detecting LLM-Generated Code.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs One Size Does Not Fit All: Investigating Efficacy of Perplexity in Detecting LLM-Generated Code

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:14.798043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ac7c31-4310-47fd-85cb-983ba9055911 · outbound

This paper cites LiCoEval: Evaluating LLMs on License Compliance in Code Generation.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs LiCoEval: Evaluating LLMs on License Compliance in Code Generation

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:14.880420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e66fc8d-f6ad-4b95-b5bb-5793c48afe27 · outbound

This paper cites Distin- guishing llm-generated from human-written code by contrastive learning.ACM Transactions on Software Engineering and Methodology, 34(4):1–31, 2025.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Distin- guishing llm-generated from human-written code by contrastive learning.ACM Transactions on Software Engineering and Methodology, 34(4):1–31, 2025

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:20.760397Z

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 559512f9-8e72-460e-8ef4-c0308bf77398 · outbound

This paper cites Detecting ai-generated code assignments using perplexity of large language models.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Detecting ai-generated code assignments using perplexity of large language models

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:20.608036Z

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 1a0ffe97-c900-4d1d-a030-c9b766ecbe73 · outbound

This paper cites An {LLM-Assisted}{Easy-to-Trigger} backdoor attack on code completion models: Injecting disguised vulnerabilities against strong detection.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs An {LLM-Assisted}{Easy-to-Trigger} backdoor attack on code completion models: Injecting disguised vulnerabilities against strong detection

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:20.428612Z

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 646f7d6b-37ce-431e-8a7a-e7e6bf2dcc18 · outbound

This paper cites Zero-Shot Detection of Machine-Generated Codes.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Zero-Shot Detection of Machine-Generated Codes

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:15.071294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98df593a-6b3d-46a5-be04-6eb4eac9b636 · outbound

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

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Uncovering llm-generated code: A zero-shot synthetic code detector via code rewriting

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:20.249361Z

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 6b711f23-85f8-44f8-929f-41adc1564bf7 · outbound

This paper cites Codeipprompt: intellectual property infringement assessment of code language models.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Codeipprompt: intellectual property infringement assessment of code language models

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:20.053757Z

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 16b48c01-9f40-41ff-888e-384a39c9a208 · outbound

This paper cites Inducing Vulnerable Code Generation in LLM Coding Assistants.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Inducing Vulnerable Code Generation in LLM Coding Assistants

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:15.340847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c76f7210-55c6-4567-aaf4-cb8d912ee442 · outbound

This paper cites How well does llm generate security tests?arXiv preprint arXiv:2310.00710, 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs How well does llm generate security tests?arXiv preprint arXiv:2310.00710, 2023

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:15.407231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31be87fc-8af6-437f-815a-8d84cee8a050 · outbound

This paper cites Genimage: A million-scale benchmark for detecting ai-generated image.Advances in Neural Information Processing Systems (NeurIPS), 36:77771–77782, 2023.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Genimage: A million-scale benchmark for detecting ai-generated image.Advances in Neural Information Processing Systems (NeurIPS), 36:77771–77782, 2023

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:19.823765Z

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 fa6ba879-fa02-4f20-a6f2-f0e7caf8aec1 · outbound

This paper cites Wilddeepfake: A challenging real-world dataset for deepfake detection.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Wilddeepfake: A challenging real-world dataset for deepfake detection

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:55:19.529874Z

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 3b4e48ee-263b-4fa0-ba3e-0eda070ab4b1 · outbound

This paper cites an unresolved cited work.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Unresolved cited work

Reference 99

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:55:19.259887Z

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 83acb047-23d9-4acc-b227-7eb9507bc60f · outbound

This paper cites an unresolved cited work.

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs Unresolved cited work

Reference 100

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:55:19.095212Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers