% References for the IETF AI/agent landscape survey.
% Real, verifiable entries only. Agent-added entries must be checked.

% ── IETF / Standards quantitative analysis ────────────────────────────────

@inproceedings{mcquistin2021characterising,
  author    = {McQuistin, Stephen and Karan, Mladen and Khare, Prashant and
               Perkins, Colin and Tyson, Gareth and Purver, Matthew and
               Healey, Patrick and Iqbal, Waleed and Qadir, Junaid and
               Castro, Ignacio},
  title     = {Characterising the {IETF} Through the Lens of {RFC} Deployment},
  booktitle = {Proceedings of the 21st ACM Internet Measurement Conference
               ({IMC} '21)},
  year      = {2021},
  pages     = {137--149},
  doi       = {10.1145/3487552.3487821},
  isbn      = {9781450391290},
}

@inproceedings{zhang2025affiliations,
  author    = {Zhang, Yangjun and McQuistin, Stephen and Karan, Mladen and
               Ramirez-Centeno, Hugo Enrique and Perkins, Colin and
               Tyson, Gareth and Castro, Ignacio},
  title     = {Two Decades of {IETF} Affiliations: Evolution and Impact},
  booktitle = {Proceedings of the 2025 Applied Networking Research Workshop
               ({ANRW} '25)},
  year      = {2025},
  doi       = {10.1145/3744200.3744757},
}

@techreport{tenoever2022aid,
  author      = {ten Oever, Niels and Cath, Corinne and K{\"u}hlewind, Mirja
                 and Perkins, Colin S.},
  title       = {Report from the {IAB} Workshop on Analyzing {IETF} Data
                 ({AID}) 2021},
  institution = {Internet Architecture Board},
  type        = {RFC},
  number      = {9307},
  year        = {2022},
  month       = sep,
  issn        = {2070-1721},
  note        = {Informational},
  doi         = {10.17487/RFC9307},
}

@misc{jimenez2024automating,
  author        = {Jim{\'e}nez, Jaime},
  title         = {Automating {IETF} Insights Generation with {AI}},
  year          = {2024},
  eprint        = {2410.13301},
  archivePrefix = {arXiv},
  primaryClass  = {cs.NI},
}

% ── LLM-assisted annotation / classification ──────────────────────────────

@article{gilardi2023chatgpt,
  author  = {Gilardi, Fabrizio and Alizadeh, Meysam and Kubli, Ma{\"e}l},
  title   = {{ChatGPT} Outperforms Crowd-Workers for Text-Annotation Tasks},
  journal = {Proceedings of the National Academy of Sciences},
  year    = {2023},
  volume  = {120},
  number  = {30},
  pages   = {e2305016120},
  doi     = {10.1073/pnas.2305016120},
}

@inproceedings{tan2024survey,
  author    = {Tan, Zhen and Li, Dawei and Wang, Song and Beigi, Alimohammad
               and Jiang, Bohan and Bhattacharjee, Amrita and Karami,
               Mansooreh and Li, Jundong and Cheng, Lu and Liu, Huan},
  title     = {Large Language Models for Data Annotation and Synthesis:
               {A} Survey},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in
               Natural Language Processing ({EMNLP} 2024)},
  year      = {2024},
  pages     = {930--957},
  address   = {Miami, Florida, USA},
  doi       = {10.18653/v1/2024.emnlp-main.54},
}

@misc{yang2025agentprotocols,
  author        = {Yang, Yingxuan and Chai, Huacan and Song, Yuanyi and
                   Qi, Siyuan and Wen, Muning and Li, Ning and Liao, Junwei
                   and Hu, Haoyi and Lin, Jianghao and Chang, Gaowei and
                   Liu, Weiwen and Wen, Ying and Yu, Yong and Zhang, Weinan},
  title         = {A Survey of {AI} Agent Protocols},
  year          = {2025},
  eprint        = {2504.16736},
  archivePrefix = {arXiv},
  primaryClass  = {cs.AI},
}

% ── Inter-rater reliability of LLM labels ─────────────────────────────────

@misc{reiss2023reliability,
  author        = {Reiss, Michael V.},
  title         = {Testing the Reliability of {ChatGPT} for Text Annotation
                   and Classification: {A} Cautionary Remark},
  year          = {2023},
  eprint        = {2304.11085},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
}

@inproceedings{wang2023nlgeval,
  author    = {Wang, Jiaan and Liang, Yunlong and Meng, Fandong and
               Sun, Zengkui and Shi, Haoxiang and Li, Zhixu and Xu, Jinan
               and Qu, Jianfeng and Zhou, Jie},
  title     = {Is {ChatGPT} a Good {NLG} Evaluator? {A} Preliminary Study},
  booktitle = {Proceedings of the 4th Workshop on New Frontiers in
               Summarization ({NewSumm@EMNLP} 2023)},
  year      = {2023},
  note      = {arXiv:2303.04048},
}

% ── Cohen's kappa / Landis-Koch (methodological) ──────────────────────────

@article{cohen1960kappa,
  author  = {Cohen, Jacob},
  title   = {A Coefficient of Agreement for Nominal Scales},
  journal = {Educational and Psychological Measurement},
  year    = {1960},
  volume  = {20},
  number  = {1},
  pages   = {37--46},
  doi     = {10.1177/001316446002000104},
}

@article{landis1977kappa,
  author  = {Landis, J. Richard and Koch, Gary G.},
  title   = {The Measurement of Observer Agreement for Categorical Data},
  journal = {Biometrics},
  year    = {1977},
  volume  = {33},
  number  = {1},
  pages   = {159--174},
  doi     = {10.2307/2529310},
}

% ── Text embeddings / semantic similarity ─────────────────────────────────

@inproceedings{reimers2019sbert,
  author    = {Reimers, Nils and Gurevych, Iryna},
  title     = {Sentence-{BERT}: Sentence Embeddings using Siamese {BERT}-Networks},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in
               Natural Language Processing and the 9th International Joint
               Conference on Natural Language Processing
               ({EMNLP-IJCNLP} 2019)},
  year      = {2019},
  pages     = {3982--3992},
  doi       = {10.18653/v1/D19-1410},
}

@misc{nussbaum2024nomic,
  author        = {Nussbaum, Zach and Morris, John X. and Duderstadt, Brandon
                   and Mulyar, Andriy},
  title         = {Nomic Embed: Training a Reproducible Long Context Text
                   Embedder},
  year          = {2024},
  eprint        = {2402.01613},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
}