@article{ff-2022,
  title = {The Forward-Forward Algorithm: Some Preliminary Investigations},
  author = {Geoffrey Hinton},
  year = {2022},
  journal = {arXiv},
  url = {https://arxiv.org/abs/2212.13345},
  note = {已对工作区内原始 16 页 PDF 完成深读，并与 arXiv 一手入口记录核对；2026-08-13 无法重新打开 arXiv，未确认正式同行评议版本。证据仅覆盖原文实验与作者限定语。}
}

@article{bicovg-2026,
  title = {Covariance-Aware Goodness for Scalable Forward-Forward Learning},
  year = {2026},
  journal = {arXiv},
  url = {https://arxiv.org/abs/2605.04346},
  note = {arXiv:2605.04346 预印本；使用本地独立审计的正文/附录记录，正式出版状态截至截止日未确认。纯局部与 Hybrid Goodness Blocks 的证据分别记录。}
}

@article{scff-2025,
  title = {Self-Contrastive Forward-Forward algorithm},
  year = {2025},
  journal = {Nature Communications},
  url = {https://doi.org/10.1038/s41467-025-61037-0},
  note = {Nature Communications 2025 正式 DOI 版本；本地专项审计核验结果与讨论边界已写入 claim ledger。},
  doi = {10.1038/s41467-025-61037-0}
}

@article{layer-collaboration-2024,
  title = {Layer Collaboration in the Forward-Forward Algorithm},
  year = {2024},
  journal = {AAAI},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29324},
  note = {正式 AAAI 2024 论文，DOI 10.1609/aaai.v38i13.29324；来自本地独立审计的摘要/方法核验，当前环境无法重新打开 AAAI 页面。},
  doi = {10.1609/aaai.v38i13.29324}
}

@article{trifecta-2024,
  title = {The Trifecta: Three simple techniques for training deeper Forward-Forward networks},
  year = {2024},
  journal = {Transactions on Machine Learning Research},
  url = {https://openreview.net/forum?id=a7KP5uo0Fp},
  note = {使用 OpenReview/TMLR 版本族和本地 2026-08-12 逐条审计记录；机制、深度和 OLU 边界按正文/附录核验，未把 OLU 结果写成纯 FF 结果。}
}

@article{advancing-ff-2026,
  title = {Advancing the forward-forward algorithm towards high-performance deep local learning},
  year = {2026},
  journal = {Neural Networks},
  url = {https://www.sciencedirect.com/science/article/pii/S0893608026002273},
  note = {正式 DOI 10.1016/j.neunet.2026.108765；本地独立审计已核验出版状态与摘要级主张，因当前页面访问限制，机制细节保守降为 V2。},
  doi = {10.1016/j.neunet.2026.108765}
}

@article{hcl-ff-2026,
  title = {HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithm},
  year = {2026},
  journal = {CVPR},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Yao\_HCL-FF\_Hierarchical\_and\_Contrastive\_Learning\_for\_Forward-Forward\_Algorithm\_CVPR\_2026\_paper.html},
  note = {CVPR 2026 正式开放论文页与本地版本族核验；数值来自正文结果表，作者预印本作为版本补充但不替代正式入口。}
}

@article{cff-vit-2025,
  title = {Contrastive Forward-Forward: A Training Algorithm of Vision Transformer},
  year = {2025},
  journal = {Neural Networks},
  url = {https://doi.org/10.1016/j.neunet.2025.107867},
  note = {使用 Neural Networks 正式 DOI 版本和本地审计记录；对应作者预印本入口为 arXiv:2502.00571，正式版本优先。},
  doi = {10.1016/j.neunet.2025.107867}
}

@article{forwardgnn-2024,
  title = {Forward Learning of Graph Neural Networks},
  year = {2024},
  journal = {ICLR},
  url = {https://openreview.net/forum?id=Abr7dU98ME},
  note = {ICLR 2024 OpenReview 正式入口；被纳为桥接条目，未把标题中的 forward learning 改写为原始 FF 算法。}
}

@misc{dtg-ff-2026,
  title = {Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training},
  year = {2026},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2606.06539},
  note = {arXiv:2606.06539 预印本；数值来自本地独立审计的正文和系统附录记录，正式出版状态截至截止日未确认。}
}

@article{ff-cnn-2025,
  title = {Training convolutional neural networks with the Forward–Forward Algorithm},
  year = {2025},
  journal = {Scientific Reports},
  url = {https://doi.org/10.1038/s41598-025-26235-2},
  note = {Scientific Reports 2025 正式 DOI 版本；数值来自本地专项审计记录的同架构主实验，未把负面结果扩大到未测试的 FF 变体。},
  doi = {10.1038/s41598-025-26235-2}
}

@article{memristor-ff-2026,
  title = {Forward-only learning in memristor arrays with month-scale stability},
  year = {2026},
  journal = {arXiv},
  url = {https://arxiv.org/abs/2601.09903},
  note = {arXiv:2601.09903v2 预印本；本地硬件分支候选包核验了器件、任务和保持性边界，未确认正式期刊版本。}
}

@article{forward-projection-2026,
  title = {Closed-form feedback-free learning with forward projection},
  year = {2026},
  journal = {Nature Communications},
  url = {https://www.nature.com/articles/s41467-026-69161-1},
  note = {Nature Communications 2026 正式论文；作为桥接条目纳入，依据正式方法、比较表和本地独立审计记录，不把它归入严格 FF 变体。},
  doi = {10.1038/s41467-026-69161-1}
}

@article{noprop-2026,
  title = {NoProp: Training Neural Networks without Back-propagation or Forward-propagation},
  year = {2026},
  journal = {Conference on Lifelong Learning Agents},
  url = {https://proceedings.mlr.press/v330/li26a.html},
  note = {PMLR 2026 正式入口；作为邻接桥接条目纳入，依据正式摘要/方法记录，未把块内 BP 隐去。}
}