構造経路から逆算する理解の定義

Ainsworth, S. K., Hayase, J., & Srinivasa, S. (2023). Git Re-Basin: Merging models modulo permutation symmetries. ICLR 2023.

ALIGN Intelligence Symbiosis Chapter (2026). AI免疫系（AI Immune System）. https://intelligence-symbiosis.net/ja/ais（2026-10-14閲覧、暫定版）

Alvarez-Melis, D., & Jaakkola, T. (2018). Gromov-Wasserstein alignment of word embedding spaces. EMNLP 2018, 1881–1890.

Arimichi, S., Doya, K., Endo, T., et al. (2026). Humanity-in-the-Circle: A position paper. Zenodo. doi:10.5281/zenodo.20176233

Artetxe, M., Labaka, G., & Agirre, E. (2018). A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. ACL 2018, 789–798.

Ba, J., Hinton, G. E., Mnih, V., Leibo, J. Z., & Ionescu, C. (2016). Using fast weights to attend to the recent past. NIPS 2016.

Bansal, Y., Nakkiran, P., & Barak, B. (2021). Revisiting model stitching to compare neural representations. NeurIPS 34, 225–236.

Beckmann, P., & Queloz, M. (2026, forthcoming). Mechanistic indicators of understanding in large language models. Philosophical Studies. arXiv:2507.08017

Behrouz, A., Zhong, P., & Mirrokni, V. (2025). Titans: Learning to memorize at test time. NeurIPS 2025.

Berglund, L., Tong, M., Kaufmann, M., et al. (2024). The reversal curse: LLMs trained on “A is B” fail to learn “B is A”. ICLR 2024. arXiv:2309.12288

Bommasani, R., Creel, K. A., Kumar, A., Jurafsky, D., & Liang, P. (2022). Picking on the same person: Does algorithmic monoculture lead to outcome homogenization? NeurIPS 35, 3663–3678.

Caramazza, A. (1986). On drawing inferences about the structure of normal cognitive systems from the analysis of patterns of impaired performance: The case for single-patient studies. Brain and Cognition, 5(1), 41–66.

Chater, N., & Vitányi, P. (2003). Simplicity: A unifying principle in cognitive science? Trends in Cognitive Sciences, 7(1), 19–22. doi:10.1016/S1364-6613(02)00005-0

Conneau, A., Lample, G., Ranzato, M., Denoyer, L., & Jégou, H. (2018). Word translation without parallel data. ICLR 2018.

Elgin, C. Z. (2017). True Enough. MIT Press.

von Frisch, K. (1967). The Dance Language and Orientation of Bees. Harvard University Press.

Fu, T., Min, Z., Zhang, H., et al. (2025). Cache-to-cache: Direct semantic communication between large language models. arXiv:2510.03215.

Gärdenfors, P. (2000). Conceptual Spaces: The Geometry of Thought. MIT Press.

Geiping, J., McLeish, S., Jain, N., et al. (2025). Scaling up test-time compute with latent reasoning: A recurrent depth approach. NeurIPS 38.

Gentner, D. (1983). Structure-mapping: A theoretical framework for analogy. Cognitive Science, 7(2), 155–170.

Grave, E., Joulin, A., & Berthet, Q. (2019). Unsupervised alignment of embeddings with Wasserstein Procrustes. AISTATS 2019, PMLR 89, 1880–1890.

Grimm, S. R. (2006). Is understanding a species of knowledge? British Journal for the Philosophy of Science, 57(3), 515–535. doi:10.1093/bjps/axl015

Grünwald, P. D. (2007). The Minimum Description Length Principle. MIT Press.

Hao, S., Sukhbaatar, S., Su, D., et al. (2025). Training large language models to reason in a continuous latent space. COLM 2025.

Harris, Z. S. (1954). Distributional structure. Word, 10(2–3), 146–162.

Haxby, J. V., Guntupalli, J. S., Connolly, A. C., et al. (2011). A common, high-dimensional model of the representational space in human ventral temporal cortex. Neuron, 72(2), 404–416.

Henrich, J. (2015). The Secret of Our Success. Princeton University Press.

Hills, A. (2016). Understanding why. Noûs, 50(4), 661–688.

Hinton, G. (2022). The forward-forward algorithm: Some preliminary investigations. arXiv:2212.13345.

Hinton, G. (2024). Will digital intelligence replace biological intelligence? Romanes Lecture, University of Oxford, 19 February 2024.

Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv:1503.02531.

Hubinger, E., van Merwijk, C., Mikulik, V., Skalse, J., & Garrabrant, S. (2019). Risks from learned optimization in advanced machine learning systems. arXiv:1906.01820.

Huh, M., Cheung, B., Wang, T., & Isola, P. (2024). Position: The Platonic representation hypothesis. ICML 2024, PMLR 235, 20617–20642.

Ilharco, G., Ribeiro, M. T., Wortsman, M., et al. (2023). Editing models with task arithmetic. ICLR 2023.

Jha, R., Zhang, C., Shmatikov, V., & Morris, J. X. (2025). Harnessing the universal geometry of embeddings. NeurIPS 38, 45963–45987.

Jiang, L., Stocco, A., Losey, D. M., et al. (2019). BrainNet: A multi-person brain-to-brain interface for direct collaboration between brains. Scientific Reports, 9, 6115.

Kakaes, K. (2026). AI has solved one of math’s $1 million Millennium Prize problems. Quanta Magazine, September 8, 2026.

Kleinberg, J., & Raghavan, M. (2021). Algorithmic monoculture and social welfare. PNAS, 118(22), e2018340118.

Korbak, T., Balesni, M., et al. (2025). Chain of thought monitorability: A new and fragile opportunity for AI safety. arXiv:2507.11473.

Kornblith, S., Norouzi, M., Lee, H., & Hinton, G. (2019). Similarity of neural network representations revisited. ICML 2019, PMLR 97, 3519–3529.

Krenn, M., Pollice, R., Guo, S. Y., et al. (2022). On scientific understanding with artificial intelligence. Nature Reviews Physics, 4(12), 761–769.

Kriegeskorte, N., Mur, M., & Bandettini, P. (2008). Representational similarity analysis – connecting the branches of systems neuroscience. Frontiers in Systems Neuroscience, 2, 4.

Ladyman, J., & Ross, D. (2007). Every Thing Must Go: Metaphysics Naturalized. Oxford University Press.

Landymore, F. (2026). Mathematicians can’t make sense of how OpenAI’s agents solved one of the toughest math problems. Futurism, September 23, 2026.

Lewis, H. M., & Laland, K. N. (2012). Transmission fidelity is the key to the build-up of cumulative culture. Phil. Trans. R. Soc. B, 367(1599), 2171–2180.

Leyton-Brown, K., & Shoham, Y. (2024). Understanding understanding: A pragmatic framework motivated by large language models. arXiv:2406.10937

Li, K., Hopkins, A., Bau, D., Viégas, F., Pfister, H., & Wattenberg, M. (2023). Emergent world representations: Exploring a sequence model trained on a synthetic task. ICLR 2023. arXiv:2210.13382

Lipton, Z. C. (2018). The mythos of model interpretability. Communications of the ACM, 61(10), 36–43. arXiv:1606.03490

Liu, Y. (2026). Beyond tokens: A unified framework for latent communication in LLM-based multi-agent systems. arXiv:2606.05711.

Mancoridis, M., Weeks, B., Vafa, K., & Mullainathan, S. (2025). Potemkin understanding in large language models. ICML 2025. arXiv:2506.21521

McClelland, J. L., McNaughton, B. L., & O'Reilly, R. C. (1995). Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory. Psychological Review, 102(3), 419–457. doi:10.1037/0033-295X.102.3.419

Mikolov, T., Le, Q. V., & Sutskever, I. (2013). Exploiting similarities among languages for machine translation. arXiv:1309.4168.

Mitchell, M., & Krakauer, D. C. (2023). The debate over understanding in AI’s large language models. PNAS, 120(13), e2215907120. doi:10.1073/pnas.2215907120

Moschella, L., Maiorca, V., Fumero, M., et al. (2023). Relative representations enable zero-shot latent space communication. ICLR 2023.

Newman, M. H. A. (1928). Mr. Russell's “Causal Theory of Perception”. Mind, 37(146), 137–148.

OpenAI (2026). On the Navier–Stokes Millennium Prize Problem. https://openai.com/index/navier-stokes-solution/ （2026年9月8日公開）

Pham, C., Liu, B., Yang, Y., et al. (2024). Let models speak ciphers: Multiagent debate through embeddings. ICLR 2024.

Polanyi, M. (1966). The Tacit Dimension. Doubleday.

Queloz, M., & Beckmann, P. (2026). Why we care about understanding: Competence through predictive compression. arXiv:2609.04962

Rao, R. P. N., Stocco, A., Bryan, M., et al. (2014). A direct brain-to-brain interface in humans. PLoS ONE, 9(11), e111332.

de Regt, H. W. (2017). Understanding Scientific Understanding. Oxford University Press.

Saussure, F. de (1916). Cours de linguistique générale. Payot.

Schmidhuber, J. (1992). Learning to control fast-weight memories: An alternative to dynamic recurrent networks. Neural Computation, 4(1), 131–139.

Schönemann, P. H. (1966). A generalized solution of the orthogonal Procrustes problem. Psychometrika, 31(1), 1–10.

Schut, L., Tomasev, N., McGrath, T., Hassabis, D., Paquet, U., & Kim, B. (2025). Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero. PNAS, 122(13), e2406675122.

Seyfarth, R. M., Cheney, D. L., & Marler, P. (1980). Monkey responses to three different alarm calls. Science, 210(4471), 801–803.

Shallice, T. (1988). From Neuropsychology to Mental Structure. Cambridge University Press.

Shibata, K., Watanabe, T., Sasaki, Y., & Kawato, M. (2011). Perceptual learning incepted by decoded fMRI neurofeedback without stimulus presentation. Science, 334(6061), 1413–1415.

Shumailov, I., Shumaylov, Z., Zhao, Y., et al. (2024). AI models collapse when trained on recursively generated data. Nature, 631(8022), 755–759.

Smith, S. L., Turban, D. H. P., Hamblin, S., & Hammerla, N. Y. (2017). Offline bilingual word vectors, orthogonal transformations and the inverted softmax. ICLR 2017.

Søgaard, A., Ruder, S., & Vulić, I. (2018). On the limitations of unsupervised bilingual dictionary induction. ACL 2018, 778–788.

Sun, Y., Li, X., Dalal, K., et al. (2025). Learning to (learn at test time): RNNs with expressive hidden states. ICML 2025, PMLR 267, 57503–57522.

Taschereau-Dumouchel, V., Cortese, A., Chiba, T., Knotts, J. D., Kawato, M., & Lau, H. (2018). Towards an unconscious neural reinforcement intervention for common fears. PNAS, 115(13), 3470–3475.

Tomasello, M. (1999). The Cultural Origins of Human Cognition. Harvard University Press.

Tse, D., Langston, R. F., Kakeyama, M., et al. (2007). Schemas and memory consolidation. Science, 316(5821), 76–82.

Wilkenfeld, D. A. (2013). Understanding as representation manipulability. Synthese, 190(6), 997–1016. doi:10.1007/s11229-011-0055-x

Wilkenfeld, D. A. (2019). Understanding as compression. Philosophical Studies, 176(10), 2807–2831. doi:10.1007/s11098-018-1152-1

Woodward, J. (2003). Making Things Happen: A Theory of Causal Explanation. Oxford University Press.

Wortsman, M., Ilharco, G., Gadre, S. Y., et al. (2022). Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. ICML 2022, PMLR 162, 23965–23998.

Wu, Z., Qiu, L., Ross, A., et al. (2024). Reasoning or reciting? Exploring the capabilities and limitations of language models through counterfactual tasks. NAACL 2024, 1819–1862. doi:10.18653/v1/2024.naacl-long.102

Xing, C., Wang, D., Liu, C., & Lin, Y. (2015). Normalized word embedding and orthogonal transform for bilingual word translation. NAACL-HLT 2015, 1006–1011.

Yadav, P., Tam, D., Choshen, L., Raffel, C., & Bansal, M. (2023). TIES-Merging: Resolving interference when merging models. NeurIPS 36.

Yamakawa, H. (2021). The whole brain architecture approach: Accelerating the development of artificial general intelligence by referring to the brain. Neural Networks, 144, 478–495. doi:10.1016/j.neunet.2021.09.004

Yoon, P. H., Athukoralage, J. S., Ameisen, E., Kauderer-Abrams, E., Perry, N. T., Durrant, M. G., et al. (2026). Autonomous AI agents discover reverse transcriptases with tandem repeat arrays. bioRxiv. doi:10.64898/2026.10.05.755809

Yu, X., Chen, Z., He, Y., et al. (2026). The latent space: Foundation, evolution, mechanism, ability, and outlook. arXiv:2604.02029.

Zhang, M., Liu, Y., Luan, H., & Sun, M. (2017). Adversarial training for unsupervised bilingual lexicon induction. ACL 2017, 1959–1970.

Zou, A., Phan, L., Chen, S., et al. (2023). Representation engineering: A top-down approach to AI transparency. arXiv:2310.01405.

山川宏, 市瀬龍太郎, 遠藤太一郎, 加藤洋平, ジェプカラファウ, 林祐輔 (2025). 創発機械倫理に向けて. 人工知能学会第二種研究会資料, 2025(AGI-030), 05. doi:10.11517/jsaisigtwo.2025.AGI-030_05