% SocioLens, LD-06 version v0.1: https://sociolens-web.pages.dev/debates/ld-06/v0.1/
% Generated from SocioLens source labels. Authors and years are not stored as separate fields,
% so they are not filled in here, and a title is given only where the label states one;
% the full label is in each note. For complete records, import the identifiers file into
% Zotero (Add Item by Identifier). "SocioLens synthesis" entries are the project's own
% synthesis documents, not primary evidence or scholarship.

@misc{src_sl_truong_et_al_arxiv_2511_16842,
  title = {Fantastic Bugs and Where to Find Them in AI Benchmarks},
  eprint = {2511.16842},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2511.16842},
  howpublished = {Source type: preprint},
  note = {Truong, Tu, Hardy, Reuel, Tang, Burapacheep, Perera, Uwakwe, Domingue, Haber \& Koyejo, “Fantastic Bugs and Where to Find Them in AI Benchmarks,” arXiv:2511.16842, November 2025},
  annote = {SocioLens source SRC-SL-TRUONG-ET-AL-ARXIV-2511-16842: https://sociolens-web.pages.dev/sources/src-sl-truong-et-al-arxiv-2511-16842/v1.0/}
}

@misc{src_sl_ai_index_2026_annual_report,
  title = {The AI Index 2026 Annual Report},
  howpublished = {Source type: independent research report},
  note = {Sajadieh, Fattorini, Perrault, Gil, Parli et al., “The AI Index 2026 Annual Report,” AI Index Steering Committee, Institute for Human-Centered AI, Stanford University, April 2026},
  annote = {SocioLens source SRC-SL-AI-INDEX-2026-ANNUAL-REPORT: https://sociolens-web.pages.dev/sources/src-sl-ai-index-2026-annual-report/v1.0/}
}

@misc{src_sl_vendrow_et_al_arxiv_2502_03461,
  title = {Do Large Language Model Benchmarks Test Reliability?},
  eprint = {2502.03461},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2502.03461},
  howpublished = {Source type: preprint},
  note = {Vendrow, Vendrow, Beery \& Madry, “Do Large Language Model Benchmarks Test Reliability?,” arXiv:2502.03461, February 2025},
  annote = {SocioLens source SRC-SL-VENDROW-ET-AL-ARXIV-2502-03461: https://sociolens-web.pages.dev/sources/src-sl-vendrow-et-al-arxiv-2502-03461/v1.0/}
}

@misc{src_sl_gema_et_al_arxiv_2406_04127,
  title = {Are We Done with MMLU?},
  eprint = {2406.04127},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2406.04127v3},
  howpublished = {Source type: preprint},
  note = {Gema, Leang, Hong et al., “Are We Done with MMLU?,” arXiv:2406.04127 (v3), January 2025},
  annote = {SocioLens source SRC-SL-GEMA-ET-AL-ARXIV-2406-04127: https://sociolens-web.pages.dev/sources/src-sl-gema-et-al-arxiv-2406-04127/v1.0/}
}

@misc{src_sl_bean_et_al_neurips_2025_arxiv_2511_04703,
  title = {Measuring what Matters: Construct Validity in Large Language Model Benchmarks},
  eprint = {2511.04703},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2511.04703},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Bean, Kearns, Romanou, Hafner, Mayne, Batzner et al., “Measuring what Matters: Construct Validity in Large Language Model Benchmarks,” NeurIPS 2025 Datasets and Benchmarks Track, arXiv:2511.04703},
  annote = {SocioLens source SRC-SL-BEAN-ET-AL-NEURIPS-2025-ARXIV-2511-04703: https://sociolens-web.pages.dev/sources/src-sl-bean-et-al-neurips-2025-arxiv-2511-04703/v1.0/}
}

@misc{src_sl_reuel_et_al_betterbench_arxiv_2411_12990,
  title = {BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices},
  eprint = {2411.12990},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2411.12990},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Reuel, Hardy, Smith, Lamparth, Hardy \& Kochenderfer, “BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices,” NeurIPS 2024, arXiv:2411.12990},
  annote = {SocioLens source SRC-SL-REUEL-ET-AL-BETTERBENCH-ARXIV-2411-12990: https://sociolens-web.pages.dev/sources/src-sl-reuel-et-al-betterbench-arxiv-2411-12990/v1.0/}
}

@misc{src_sl_zhang_et_al_gsm1k_arxiv_2405_00332,
  title = {A Careful Examination of Large Language Model Performance on Grade School Arithmetic},
  eprint = {2405.00332},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2405.00332},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Zhang, Da, Lee, Robinson, Wu, Song et al., “A Careful Examination of Large Language Model Performance on Grade School Arithmetic,” NeurIPS 2024 Datasets and Benchmarks Track, arXiv:2405.00332},
  annote = {SocioLens source SRC-SL-ZHANG-ET-AL-GSM1K-ARXIV-2405-00332: https://sociolens-web.pages.dev/sources/src-sl-zhang-et-al-gsm1k-arxiv-2405-00332/v1.0/}
}

@misc{src_sl_zhu_et_al_agentic_benchmark_checklist_arxiv_2507_02825,
  title = {Establishing Best Practices for Building Rigorous Agentic Benchmarks},
  eprint = {2507.02825},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2507.02825v5},
  howpublished = {Source type: preprint},
  note = {Zhu, Jin, Pruksachatkun, Zhang, Liu, Cui et al., “Establishing Best Practices for Building Rigorous Agentic Benchmarks,” arXiv:2507.02825 (v5), 2025},
  annote = {SocioLens source SRC-SL-ZHU-ET-AL-AGENTIC-BENCHMARK-CHECKLIST-ARXIV-2507-02825: https://sociolens-web.pages.dev/sources/src-sl-zhu-et-al-agentic-benchmark-checklist-arxiv-2507-02825/v1.0/}
}

@misc{src_sl_sclar_choi_tsvetkov_suhr_iclr_2024,
  title = {Quantifying Language Models’ Sensitivity to Spurious Features in Prompt Design},
  eprint = {2310.11324},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2310.11324},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Sclar, Choi, Tsvetkov \& Suhr, “Quantifying Language Models’ Sensitivity to Spurious Features in Prompt Design,” ICLR 2024, arXiv:2310.11324},
  annote = {SocioLens source SRC-SL-SCLAR-CHOI-TSVETKOV-SUHR-ICLR-2024: https://sociolens-web.pages.dev/sources/src-sl-sclar-choi-tsvetkov-suhr-iclr-2024/v1.0/}
}

@misc{src_sl_maia_polo_et_al_tinybenchmarks_icml_2024,
  title = {tinyBenchmarks: evaluating LLMs with fewer examples},
  eprint = {2402.14992},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2402.14992},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Maia Polo, Weber, Choshen, Sun, Xu \& Yurochkin, “tinyBenchmarks: evaluating LLMs with fewer examples,” ICML 2024, arXiv:2402.14992},
  annote = {SocioLens source SRC-SL-MAIA-POLO-ET-AL-TINYBENCHMARKS-ICML-2024: https://sociolens-web.pages.dev/sources/src-sl-maia-polo-et-al-tinybenchmarks-icml-2024/v1.0/}
}

@misc{src_sl_singh_et_al_global_mmlu_arxiv_2412_03304,
  title = {Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation},
  eprint = {2412.03304},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2412.03304v2},
  howpublished = {Source type: preprint},
  note = {Singh, Romanou, Fourrier, Adelani, Ngui, Vila-Suero et al., “Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation,” arXiv:2412.03304 (v2), 2025},
  annote = {SocioLens source SRC-SL-SINGH-ET-AL-GLOBAL-MMLU-ARXIV-2412-03304: https://sociolens-web.pages.dev/sources/src-sl-singh-et-al-global-mmlu-arxiv-2412-03304/v1.0/}
}

@misc{src_sl_whitfill_wu_becker_rush_metr_2026_03_10,
  title = {Many SWE-bench-Passing PRs Would Not Be Merged into Main},
  url = {https://metr.org/notes/2026-03-10-many-swe-bench-passing-prs-would-not-be-merged-into-main/},
  howpublished = {Source type: independent research report},
  note = {Whitfill, Wu, Becker \& Rush, “Many SWE-bench-Passing PRs Would Not Be Merged into Main,” METR research note, 10 March 2026},
  annote = {SocioLens source SRC-SL-WHITFILL-WU-BECKER-RUSH-METR-2026-03-10: https://sociolens-web.pages.dev/sources/src-sl-whitfill-wu-becker-rush-metr-2026-03-10/v1.0/}
}

@misc{src_sl_hardy_et_al_more_than_marketing_arxiv_2412_05520,
  title = {More than Marketing? On the Information Value of AI Benchmarks for Practitioners},
  eprint = {2412.05520},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2412.05520},
  howpublished = {Source type: preprint},
  note = {Hardy, Reuel, Jafari Meimandi, Soder, Griffith, Asmar, Koyejo, Bernstein \& Kochenderfer, “More than Marketing? On the Information Value of AI Benchmarks for Practitioners,” arXiv:2412.05520, December 2024},
  annote = {SocioLens source SRC-SL-HARDY-ET-AL-MORE-THAN-MARKETING-ARXIV-2412-05520: https://sociolens-web.pages.dev/sources/src-sl-hardy-et-al-more-than-marketing-arxiv-2412-05520/v1.0/}
}

@misc{src_sl_international_ai_safety_report_2026,
  title = {International AI Safety Report 2026},
  eprint = {2602.21012},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2602.21012},
  howpublished = {Source type: policy research or monitoring},
  note = {Bengio, Clare, Prunkl, Andriushchenko, Bucknall, Murray et al., “International AI Safety Report 2026,” arXiv:2602.21012, February 2026},
  annote = {SocioLens source SRC-SL-INTERNATIONAL-AI-SAFETY-REPORT-2026: https://sociolens-web.pages.dev/sources/src-sl-international-ai-safety-report-2026/v1.0/}
}

@misc{src_sl_singh_et_al_leaderboard_illusion_arxiv_2504_20879,
  title = {The Leaderboard Illusion},
  eprint = {2504.20879},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2504.20879v2},
  howpublished = {Source type: preprint},
  note = {Singh, Nan, Wang, D’Souza, Kapoor, Üstün, Koyejo, Deng, Longpre, Smith, Ermis, Fadaee \& Hooker, “The Leaderboard Illusion,” arXiv:2504.20879 (v2), May 2025},
  annote = {SocioLens source SRC-SL-SINGH-ET-AL-LEADERBOARD-ILLUSION-ARXIV-2504-20879: https://sociolens-web.pages.dev/sources/src-sl-singh-et-al-leaderboard-illusion-arxiv-2504-20879/v1.0/}
}

@misc{src_sl_lmarena_response_leaderboard_illusion_2025_05_09,
  title = {Our Response to ‘The Leaderboard Illusion’ Writeup},
  url = {https://arena.ai/blog/our-response},
  howpublished = {Source type: vendor primary},
  note = {LMArena, “Our Response to ‘The Leaderboard Illusion’ Writeup,” Arena blog, 9 May 2025 (updated 13 June 2025)},
  annote = {SocioLens source SRC-SL-LMARENA-RESPONSE-LEADERBOARD-ILLUSION-2025-05-09: https://sociolens-web.pages.dev/sources/src-sl-lmarena-response-leaderboard-illusion-2025-05-09/v1.0/}
}

@misc{src_sl_wan_et_al_fmti_2025_arxiv_2512_10169,
  title = {The 2025 Foundation Model Transparency Index},
  eprint = {2512.10169},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2512.10169},
  howpublished = {Source type: preprint},
  note = {Wan, Klyman, Kapoor, Maslej, Longpre, Xiong, Liang \& Bommasani, “The 2025 Foundation Model Transparency Index,” arXiv:2512.10169, December 2025},
  annote = {SocioLens source SRC-SL-WAN-ET-AL-FMTI-2025-ARXIV-2512-10169: https://sociolens-web.pages.dev/sources/src-sl-wan-et-al-fmti-2025-arxiv-2512-10169/v1.0/}
}

@misc{src_sl_bavaresco_et_al_judge_bench_acl_2025,
  title = {LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks},
  eprint = {2406.18403},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2406.18403},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Bavaresco, Bernardi, Bertolazzi, Elliott, Fernández, Gatt et al., “LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks,” ACL 2025, arXiv:2406.18403},
  annote = {SocioLens source SRC-SL-BAVARESCO-ET-AL-JUDGE-BENCH-ACL-2025: https://sociolens-web.pages.dev/sources/src-sl-bavaresco-et-al-judge-bench-acl-2025/v1.0/}
}

@misc{src_sl_zheng_et_al_mt_bench_neurips_2023,
  title = {Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena},
  eprint = {2306.05685},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2306.05685},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Zheng, Chiang, Sheng et al., “Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena,” NeurIPS 2023 Datasets and Benchmarks Track, arXiv:2306.05685},
  annote = {SocioLens source SRC-SL-ZHENG-ET-AL-MT-BENCH-NEURIPS-2023: https://sociolens-web.pages.dev/sources/src-sl-zheng-et-al-mt-bench-neurips-2023/v1.0/}
}

@misc{src_sl_needham_et_al_evaluation_awareness_arxiv_2505_23836,
  title = {Large Language Models Often Know When They Are Being Evaluated},
  eprint = {2505.23836},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2505.23836v3},
  howpublished = {Source type: preprint},
  note = {Needham, Edkins, Pimpale, Bartsch \& Hobbhahn, “Large Language Models Often Know When They Are Being Evaluated,” arXiv:2505.23836 (v3), July 2025},
  annote = {SocioLens source SRC-SL-NEEDHAM-ET-AL-EVALUATION-AWARENESS-ARXIV-2505-23836: https://sociolens-web.pages.dev/sources/src-sl-needham-et-al-evaluation-awareness-arxiv-2505-23836/v1.0/}
}

@misc{src_sl_schoen_et_al_anti_scheming_arxiv_2509_15541,
  title = {Stress Testing Deliberative Alignment for Anti-Scheming Training},
  eprint = {2509.15541},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2509.15541},
  howpublished = {Source type: preprint},
  note = {Schoen, Nitishinskaya, Balesni, Højmark, Hofstätter, Scheurer et al., “Stress Testing Deliberative Alignment for Anti-Scheming Training,” arXiv:2509.15541, September 2025},
  annote = {SocioLens source SRC-SL-SCHOEN-ET-AL-ANTI-SCHEMING-ARXIV-2509-15541: https://sociolens-web.pages.dev/sources/src-sl-schoen-et-al-anti-scheming-arxiv-2509-15541/v1.0/}
}

@misc{src_sl_taylor_et_al_sandbagging_auditing_games_arxiv_2512_07810,
  title = {Auditing Games for Sandbagging},
  eprint = {2512.07810},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2512.07810},
  howpublished = {Source type: preprint},
  note = {Taylor, Black, Bowen, Read, Golechha et al., “Auditing Games for Sandbagging,” arXiv:2512.07810, December 2025},
  annote = {SocioLens source SRC-SL-TAYLOR-ET-AL-SANDBAGGING-AUDITING-GAMES-ARXIV-2512-07810: https://sociolens-web.pages.dev/sources/src-sl-taylor-et-al-sandbagging-auditing-games-arxiv-2512-07810/v1.0/}
}

@misc{src_sl_us_uk_aisi_o1_predeployment_evaluation_2024_12,
  title = {US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1},
  url = {https://www.nist.gov/document/aisi-pre-deployment-evaluation-openai-o1-december-2024},
  howpublished = {Source type: government audit or evaluation},
  note = {US AI Safety Institute \& UK AI Safety Institute, “US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1,” December 2024},
  annote = {SocioLens source SRC-SL-US-UK-AISI-O1-PREDEPLOYMENT-EVALUATION-2024-12: https://sociolens-web.pages.dev/sources/src-sl-us-uk-aisi-o1-predeployment-evaluation-2024-12/v1.0/}
}

@misc{src_sl_eu_gpai_code_of_practice_safety_security_2025_07_10,
  title = {The General-Purpose AI Code of Practice: Safety and Security chapter},
  howpublished = {Source type: government primary},
  note = {European Commission, “The General-Purpose AI Code of Practice: Safety and Security chapter,” final version, 10 July 2025},
  annote = {SocioLens source SRC-SL-EU-GPAI-CODE-OF-PRACTICE-SAFETY-SECURITY-2025-07-10: https://sociolens-web.pages.dev/sources/src-sl-eu-gpai-code-of-practice-safety-security-2025-07-10/v1.0/}
}

@misc{src_sl_gb_t_45654_2025_cset_translation,
  title = {Cybersecurity Technology — Basic Safety Requirements for Generative Artificial Intelligence Services},
  url = {https://cset.georgetown.edu/wp-content/uploads/t0661_gen_ai_safety_standard_final_EN.pdf},
  howpublished = {Source type: standards body primary},
  note = {State Administration for Market Regulation \& Standardization Administration of China, GB/T 45654-2025, “Cybersecurity Technology — Basic Safety Requirements for Generative Artificial Intelligence Services,” issued 25 April 2025 (CSET English translation, 28 May 2026)},
  annote = {SocioLens source SRC-SL-GB-T-45654-2025-CSET-TRANSLATION: https://sociolens-web.pages.dev/sources/src-sl-gb-t-45654-2025-cset-translation/v1.0/}
}

@misc{src_sl_costanza_chock_et_al_facct_2022,
  title = {Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem},
  doi = {10.1145/3531146.3533213},
  url = {https://doi.org/10.1145/3531146.3533213},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Costanza-Chock, Harvey, Raji, Czernuszenko \& Buolamwini, “Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem,” FAccT 2022, arXiv:2310.02521},
  annote = {SocioLens source SRC-SL-COSTANZA-CHOCK-ET-AL-FACCT-2022: https://sociolens-web.pages.dev/sources/src-sl-costanza-chock-et-al-facct-2022/v1.0/}
}

@misc{src_sl_feffer_et_al_red_teaming_aies_2024,
  title = {Red-Teaming for Generative AI: Silver Bullet or Security Theater?},
  doi = {10.1609/aies.v7i1.31647},
  url = {https://doi.org/10.1609/aies.v7i1.31647},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Feffer, Sinha, Deng, Lipton \& Heidari, “Red-Teaming for Generative AI: Silver Bullet or Security Theater?,” AIES 2024, arXiv:2401.15897},
  annote = {SocioLens source SRC-SL-FEFFER-ET-AL-RED-TEAMING-AIES-2024: https://sociolens-web.pages.dev/sources/src-sl-feffer-et-al-red-teaming-aies-2024/v1.0/}
}

@misc{src_sl_birhane_et_al_ai_auditing_satml_2024,
  title = {AI auditing: The Broken Bus on the Road to AI Accountability},
  eprint = {2401.14462},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2401.14462},
  howpublished = {Source type: peer reviewed conference paper},
  note = {Birhane, Steed, Ojewale, Vecchione \& Raji, “AI auditing: The Broken Bus on the Road to AI Accountability,” IEEE SaTML 2024, arXiv:2401.14462},
  annote = {SocioLens source SRC-SL-BIRHANE-ET-AL-AI-AUDITING-SATML-2024: https://sociolens-web.pages.dev/sources/src-sl-birhane-et-al-ai-auditing-satml-2024/v1.0/}
}

@misc{src_sl_wolfrath_et_al_model_retirement_arxiv_2609_04699,
  title = {Model Retirement Creates Reproducibility Risk in Biomedical AI Publications},
  eprint = {2609.04699},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2609.04699},
  howpublished = {Source type: preprint},
  note = {Wolfrath, Conroy, Kosten, Bell, Neupane, Kindel et al., “Model Retirement Creates Reproducibility Risk in Biomedical AI Publications,” arXiv:2609.04699, September 2026},
  annote = {SocioLens source SRC-SL-WOLFRATH-ET-AL-MODEL-RETIREMENT-ARXIV-2609-04699: https://sociolens-web.pages.dev/sources/src-sl-wolfrath-et-al-model-retirement-arxiv-2609-04699/v1.0/}
}