References

Literature underwriting the framework's claims. 25 entries, grouped by theme, with stable anchors for cross-page citation.

Bibliography

Cited from the architecture, methodology, validation, evidence, fusion, and limitations pages. Entries within a group are alphabetical by first author.

25 entries
How to read and cite this page

Scope and citation convention

The bibliography is the literature actually invoked elsewhere on the site. It is not a survey of the field and does not attempt to cover every related result. Each group corresponds to a recurring concern in the framework — reproducibility, design, uncertainty, causality, graphs, fusion, and biomedical grounding — in roughly the order those concerns appear across the pages.

Each entry has a stable anchor of the form #ref-author-year. Other pages may link to a specific reference directly, e.g. references.html#ref-zitnik-2018. Where a DOI or arXiv identifier is available it is linked inline.

Reproducibility & scientific method

3 entries

Grounding for the framework's emphasis on declared interfaces, persisted artifacts, and explicit deployment scope.

  1. Baker, M. (2016). 1,500 scientists lift the lid on reproducibility. Nature, 533, 452–454. doi:10.1038/533452a
  2. Hutson, M. (2018). Artificial intelligence faces reproducibility crisis. Science, 359(6377), 725–726. doi:10.1126/science.359.6377.725
  3. Peirce, C. S. (1903). Pragmatism as a Principle and Method of Right Thinking. SUNY Press (1997 ed.).

Experimental design & optimization

5 entries

Bayesian design, bandit theory, multi-objective search, and the algorithm-selection framing that motivate SNPTX's experimentation surface.

  1. Agrawal, S. & Goyal, N. (2012). Analysis of Thompson Sampling for the Multi-armed Bandit Problem. COLT. arXiv:1111.1797
  2. Chaloner, K. & Verdinelli, I. (1995). Bayesian experimental design: A review. Statistical Science, 10(3), 273–304. doi:10.1214/ss/1177009939
  3. Deb, K., Pratap, A., Agarwal, S. & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197. doi:10.1109/4235.996017
  4. Rice, J. R. (1976). The algorithm selection problem. Advances in Computers, 15, 65–118. doi:10.1016/S0065-2458(08)60520-3
  5. Snoek, J., Larochelle, H. & Adams, R. P. (2012). Practical Bayesian Optimization of Machine Learning Algorithms. NeurIPS. arXiv:1206.2944

Uncertainty & calibration

3 entries

Sources used where the framework discusses calibrated outputs, evidential confidence, and information-theoretic bounds on representation.

  1. Benavoli, A., Corani, G., Demšar, J. & Zaffalon, M. (2017). Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis. Journal of Machine Learning Research, 18(77), 1–36. jmlr:v18/16-305
  2. Sensoy, M., Kaplan, L. & Kandemir, M. (2018). Evidential Deep Learning to Quantify Classification Uncertainty. NeurIPS. arXiv:1806.01768
  3. Vovk, V., Gammerman, A. & Shafer, G. (2005). Algorithmic Learning in a Random World. Springer. doi:10.1007/b106715

Causal & logical inference

3 entries

Foundational references for causal reasoning, inductive logic programming, and the information-bottleneck view of representation learning.

  1. Cover, T. M. & Thomas, J. A. (2006). Elements of Information Theory (2nd ed.). Wiley. doi:10.1002/047174882X
  2. Muggleton, S. & De Raedt, L. (1994). Inductive logic programming: Theory and methods. Journal of Logic Programming, 19–20, 629–679. doi:10.1016/0743-1066(94)90035-3
  3. Pearl, J. (2009). Causality: Models, Reasoning, and Inference (2nd ed.). Cambridge University Press. doi:10.1017/CBO9780511803161

Graph learning & equivariance

3 entries

Methods relevant to the molecular and network-level representations used in the biomedical workloads.

  1. Satorras, V. G., Hoogeboom, E. & Welling, M. (2021). E(n) Equivariant Graph Neural Networks. ICML. arXiv:2102.09844
  2. Thomas, N., Smidt, T., Kearnes, S., Yang, L., Li, L., Kohlhoff, K. & Riley, P. (2018). Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds. arXiv preprint. arXiv:1802.08219
  3. Tishby, N., Pereira, F. C. & Bialek, W. (2000). The Information Bottleneck method. arXiv preprint. arXiv:physics/0004057

Multimodal representation & fusion

3 entries

Background for the fusion page: tensor-based multimodal combination, masked self-supervision, and continual-learning constraints.

  1. He, K., Chen, X., Xie, S., Li, Y., Dollár, P. & Girshick, R. (2022). Masked Autoencoders Are Scalable Vision Learners. CVPR. arXiv:2111.06377
  2. Kirkpatrick, J. et al. (2017). Overcoming catastrophic forgetting in neural networks. PNAS, 114(13), 3521–3526. doi:10.1073/pnas.1611835114
  3. Zadeh, A., Chen, M., Poria, S., Cambria, E. & Morency, L.-P. (2017). Tensor Fusion Network for Multimodal Sentiment Analysis. EMNLP. arXiv:1707.07250

Biomedical foundation models & network medicine

5 entries

Domain literature on pre-trained biomedical models, network-level disease representation, and zero-shot therapeutic prediction.

  1. Barabási, A.-L., Gulbahce, N. & Loscalzo, J. (2011). Network medicine: a network-based approach to human disease. Nature Reviews Genetics, 12(1), 56–68. doi:10.1038/nrg2918
  2. Huang, K. et al. (2023). A foundation model for clinician-centered drug repurposing (zero-shot prediction of therapeutic use with geometric deep learning). Nature Medicine. doi:10.1038/s41591-024-03233-x
  3. Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H. & Kang, J. (2020). BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics, 36(4), 1234–1240. doi:10.1093/bioinformatics/btz682
  4. Zitnik, M. & Leskovec, J. (2017). Predicting multicellular function through multi-layer tissue networks. Bioinformatics, 33(14), i190–i198. doi:10.1093/bioinformatics/btx252
  5. Zitnik, M., Agrawal, M. & Leskovec, J. (2018). Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13), i457–i466. doi:10.1093/bioinformatics/bty294