1"""Build paper/references.bib from the verified sources CSV + curated core entries (fields only from the audit files)."""2from __future__ import annotations3import csv, re, yaml4from pathlib import Path5from .util import ROOT67CORE_BIB = r"""8@misc{alabdulkareem2026swat, title={SwaT: Cross-Family KV Cache Transfer between Language Models}, author={Alabdulkareem, Abdulrahman and Tenison, Isabel and Zhang, Jun and Zhu, Yiyang and Katz, Boris and Gutfreund, Dan}, year={2026}, eprint={2610.15095}, archivePrefix={arXiv}, note={arXiv preprint, v1 (October 2026); repository Ar-Kareem/SwaT, no released checkpoint or licence (verified 2026-10-29)}}9@misc{zweiger2026compaction, title={Fast KV Compaction via Attention Matching}, author={Zweiger, Adam and Fu, Yilun and Guo, Han and Kim, Yoon}, year={2026}, eprint={2602.16284}, archivePrefix={arXiv}, note={arXiv preprint, v2 (May 2026); code adamzweiger/compaction, MIT}}10@inproceedings{fu2026c2c, title={Cache-to-Cache: Direct Semantic Communication Between Large Language Models}, author={Fu, Tianyu and others}, booktitle={International Conference on Learning Representations (ICLR)}, year={2026}, note={arXiv:2510.03215; code thu-nics/C2C, Apache-2.0; fuser checkpoints nics-efc/C2C\_Fuser}}11@inproceedings{zou2026latentmas, title={LatentMAS: Latent Collaboration in Multi-Agent Systems}, author={Zou, Jiaru and others}, booktitle={International Conference on Machine Learning (ICML)}, year={2026}, note={arXiv:2511.20639; code Gen-Verse/LatentMAS, Apache-2.0}}12@inproceedings{liu2024kivi, title={KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache}, author={Liu, Zirui and Yuan, Jiayi and Jin, Hongye and Zhong, Shaochen and Xu, Zhaozhuo and Braverman, Vladimir and Chen, Beidi and Hu, Xia}, booktitle={International Conference on Machine Learning (ICML)}, year={2024}, note={arXiv:2402.02750}}13@inproceedings{li2024snapkv, title={SnapKV: LLM Knows What You are Looking for Before Generation}, author={Li, Yuhong and Huang, Yingbing and Yang, Bowen and Venkitesh, Bharat and Locatelli, Acyr and Ye, Hanchen and Cai, Tianle and Lewis, Patrick and Chen, Deming}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2024}, note={arXiv:2404.14469; code FasterDecoding/SnapKV}}14@misc{cai2024pyramidkv, title={PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling}, author={Cai, Zefan and Zhang, Yichi and Gao, Bofei and Liu, Yuliang and Li, Yucheng and Liu, Tianyu and Lu, Keming and Xiong, Wayne and Dong, Yue and Hu, Junjie and Xiao, Wen}, year={2024}, eprint={2406.02069}, archivePrefix={arXiv}, note={v4 (May 2025); code Zefan-Cai/KVCache-Factory, MIT}}15@inproceedings{zhang2023h2o, title={H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models}, author={Zhang, Zhenyu and Sheng, Ying and Zhou, Tianyi and Chen, Tianlong and Zheng, Lianmin and Cai, Ruisi and Song, Zhao and Tian, Yuandong and R{\'e}, Christopher and Barrett, Clark and Wang, Zhangyang and Chen, Beidi}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2023}, note={arXiv:2306.14048}}16@inproceedings{xiao2024streamingllm, title={Efficient Streaming Language Models with Attention Sinks}, author={Xiao, Guangxuan and Tian, Yuandong and Chen, Beidi and Han, Song and Lewis, Mike}, booktitle={International Conference on Learning Representations (ICLR)}, year={2024}, note={arXiv:2309.17453}}17@inproceedings{pan2024llmlingua2, title={LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression}, author={Pan, Zhuoshi and Wu, Qianhui and Jiang, Huiqiang and Xia, Menglin and Luo, Xufang and Zhang, Jue and Lin, Qingwei and R{\"u}hle, Victor and Yang, Yuqing and Lin, Chin-Yew and Zhao, H. Vicky and Qiu, Lili and Zhang, Dongmei}, booktitle={Findings of the Association for Computational Linguistics: ACL 2024}, year={2024}, note={arXiv:2403.12968}}18@inproceedings{bai2024longbench, title={LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding}, author={Bai, Yushi and Lv, Xin and Zhang, Jiajie and Lyu, Hongchang and Tang, Jiankai and Huang, Zhidian and Du, Zhengxiao and Liu, Xiao and Zeng, Aohan and Hou, Lei and Dong, Yuxiao and Tang, Jie and Li, Juanzi}, booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, pages={3119--3137}, year={2024}, doi={10.18653/v1/2024.acl-long.172}}19@inproceedings{hsieh2024ruler, title={RULER: What's the Real Context Size of Your Long-Context Language Models?}, author={Hsieh, Cheng-Ping and Sun, Simeng and Kriman, Samuel and Acharya, Shantanu and Rekesh, Dima and Jia, Fei and Zhang, Yang and Ginsburg, Boris}, booktitle={First Conference on Language Modeling (COLM)}, year={2024}, note={arXiv:2404.06654}}20@misc{mlxlm2026, title={mlx-lm: Run LLMs with MLX}, author={{Apple ML Explore contributors}}, year={2026}, howpublished={\url{https://github.com/ml-explore/mlx-lm}}, note={v0.32.2 (16 October 2026), MIT}}21@misc{anthropic2026caching, title={Prompt caching}, author={{Anthropic}}, year={2026}, howpublished={\url{https://platform.claude.com/docs/en/build-with-claude/prompt-caching}}, note={accessed 2026-10-29}}22@misc{hf2026kvcache, title={KV cache strategies}, author={{Hugging Face}}, year={2026}, howpublished={\url{https://huggingface.co/docs/transformers/en/kv_cache}}, note={Transformers v5 documentation, accessed 2026-10-29}}23@misc{dasigi2021qasper, title={A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers}, author={Dasigi, Pradeep and Lo, Kyle and Beltagy, Iz and Cohan, Arman and Smith, Noah A. and Gardner, Matt}, year={2021}, note={NAACL 2021; QASPER, CC BY 4.0}}24@inproceedings{ho2020twowiki, title={Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps}, author={Ho, Xanh and Nguyen, Anh-Khoa Duong and Sugawara, Saku and Aizawa, Akiko}, booktitle={Proceedings of the 28th International Conference on Computational Linguistics (COLING)}, year={2020}}25@inproceedings{yang2018hotpotqa, title={HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering}, author={Yang, Zhilin and Qi, Peng and Zhang, Saizheng and Bengio, Yoshua and Cohen, William W. and Salakhutdinov, Ruslan and Manning, Christopher D.}, booktitle={EMNLP}, year={2018}}26@misc{qwen2.5, title={Qwen2.5 Technical Report}, author={{Qwen Team}}, year={2024}, eprint={2412.15115}, archivePrefix={arXiv}}27@misc{llama3, title={The Llama 3 Herd of Models}, author={{Llama Team, AI @ Meta}}, year={2024}, eprint={2407.21783}, archivePrefix={arXiv}}28"""2930def _bibkey(row):31 first = re.split(r"[,; ]+", row["authors"].strip())[0].lower() if row["authors"] and row["authors"] != "unverified" else row["source_id"]32 first = re.sub(r"[^a-z]", "", first) or row["source_id"]33 return f"{first}{row['year']}_{row['source_id']}"3435def audit(config_path: str) -> int:36 cfg = yaml.safe_load(open(config_path))37 rows = list(csv.DictReader(open(ROOT / cfg["sources_csv"], newline="")))38 core_ids = {"swat2026", "compaction2026", "c2c2025", "latentmas2025", "kivi2024", "snapkv2024", "pyramidkv2024", "h2o2023", "streamingllm2023", "llmlingua2_2024", "longbench2024", "ruler2024", "mlxlm2026", "hf_kvcache_docs", "anthropic_prompt_caching"}39 extra = []40 for r in rows:41 if r["source_id"] in core_ids or r["verification"].startswith("unverified"):42 continue43 m = re.search(r"(\d{4}\.\d{5})", r["url"] or "")44 if not m: continue45 title = r["title"].replace("{", "").replace("}", "")46 extra.append(f"@misc{{{_bibkey(r)}, title={{{title}}}, author={{{r['authors'] if r['authors'] != 'unverified' else 'unverified'}}}, year={{{r['year']}}}, eprint={{{m.group(1)}}}, archivePrefix={{arXiv}}, note={{{r['venue_status']}; verification: {r['verification'][:80]}}}}}")47 out = "% Generated by `python -m wp30 sources audit` from literature/sources.csv (verified 2026-10-29) + curated core entries.\n" + CORE_BIB + "\n" + "\n".join(extra) + "\n"48 (ROOT / cfg["bib_out"]).parent.mkdir(parents=True, exist_ok=True)49 (ROOT / cfg["bib_out"]).write_text(out)50 n_ver = sum(1 for r in rows if not r["verification"].startswith("unverified"))51 print(f"sources: {len(rows)} rows, {n_ver} verified; bib entries: {out.count('@')}")52 return 053