ref.bib

% Populate this with your references. See examples/demo.bib for an example.
@article{Avasthi2024Early,
	author = {Avasthi, Prachee and Hochstrasser, Megan L. and Roth, Robert},
	journal = {Arcadia Science},
	year = {2024},
	month = {dec 19},
	note = {https://research.arcadiascience.com/pub/result-early-publishing-v2-assessment},
	publisher = {Arcadia Science},
	title = {Early update on {Arcadia} publishing 2.0: Scientists are in charge, speed is an issue},
}

@article{kadkhodaie_generalization_2024,
        title = {Generalization in diffusion models arises from geometry-adaptive harmonic representations},
        url = {http://arxiv.org/abs/2310.02557},
        doi = {10.48550/arXiv.2310.02557},
        urldate = {2025-10-14},
        publisher = {arXiv},
        author = {Kadkhodaie, Zahra and Guth, Florentin and Simoncelli, Eero P. and Mallat, Stéphane},
        month = apr,
        year = {2024},
        note = {arXiv:2310.02557 [cs]},
        keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning},
        annote = {Comment: Accepted for oral presentation at ICLR, Vienna, May 2024}
}


@article{golden_equivalent_2025,
  author  = {James Robert Golden},
  title   = {Equivalent Linear Mappings of Large Language Models},
  journal = {Transactions on Machine Learning Research},
  year    = {2025},
  month   = {Oct},
  url     = {https://openreview.net/forum?id=oDWbJsIuEp},
}

@article{adams_mechanistic_2025,
        title = {From {Mechanistic} {Interpretability} to {Mechanistic} {Biology}: {Training}, {Evaluating}, and {Interpreting} {Sparse} {Autoencoders} on {Protein} {Language} {Models}},
        shorttitle = {From {Mechanistic} {Interpretability} to {Mechanistic} {Biology}},
        url = {https://www.biorxiv.org/content/10.1101/2025.02.06.636901v2},
        doi = {10.1101/2025.02.06.636901},
        language = {en},
        urldate = {2025-10-14},
        publisher = {bioRxiv},
        author = {Adams, Etowah and Bai, Liam and Lee, Minji and Yu, Yiyang and AlQuraishi, Mohammed},
        month = jun,
        year = {2025},
        note = {Pages: 2025.02.06.636901}
}

@article{cheveralls_epistasis_2025,
        title = {Epistasis and deep learning in quantitative genetics},
        issn = {2998-4084},
        url = {https://research.arcadiascience.com/pub/result-gp-deep-learning-scaling/release/1/},
        doi = {10.57844/arcadia-25nt-guw3},
        language = {en},
        urldate = {2025-10-14},
        author = {Cheveralls, Keith and Sandler, George and York, Ryan and Bell, Audrey},
        month = may,
        year = {2025},
        note = {Publisher: Arcadia Science},
        file = {Snapshot:/Users/georgy/Zotero/storage/JFQLRFBQ/1.html:text/html}
}

@article{sigurdsson_deep_2023,
	title = {Deep integrative models for large-scale human genomics},
	volume = {51},
	issn = {0305-1048},
	url = {https://doi.org/10.1093/nar/gkad373},
	doi = {10.1093/nar/gkad373},
	abstract = {Polygenic risk scores (PRSs) are expected to play a critical role in precision medicine. Currently, PRS predictors are generally based on linear models using summary statistics, and more recently individual-level data. However, these predictors mainly capture additive relationships and are limited in data modalities they can use. We developed a deep learning framework (EIR) for PRS prediction which includes a model, genome-local-net (GLN), specifically designed for large-scale genomics data. The framework supports multi-task learning, automatic integration of other clinical and biochemical data, and model explainability. When applied to individual-level data from the UK Biobank, the GLN model demonstrated a competitive performance compared to established neural network architectures, particularly for certain traits, showcasing its potential in modeling complex genetic relationships. Furthermore, the GLN model outperformed linear PRS methods for Type 1 Diabetes, likely due to modeling non-additive genetic effects and epistasis. This was supported by our identification of widespread non-additive genetic effects and epistasis in the context of T1D. Finally, we constructed PRS models that integrated genotype, blood, urine, and anthropometric data and found that this improved performance for 93\% of the 290 diseases and disorders considered. EIR is available at https://github.com/arnor-sigurdsson/EIR.},
	number = {12},
	urldate = {2025-01-15},
	journal = {Nucleic Acids Research},
	author = {Sigurdsson, Arnór I and Louloudis, Ioannis and Banasik, Karina and Westergaard, David and Winther, Ole and Lund, Ole and Ostrowski, Sisse Rye and Erikstrup, Christian and Pedersen, Ole Birger Vesterager and Nyegaard, Mette and {DBDS Genomic Consortium} and Brunak, Søren and Vilhjálmsson, Bjarni J and Rasmussen, Simon},
	month = jul,
	year = {2023},
	keywords = {good ML in UKBB},
	pages = {e67},
	file = {Full Text PDF:/Users/georgy/Zotero/storage/8DSASFY6/Sigurdsson et al. - 2023 - Deep integrative models for large-scale human geno.pdf:application/pdf;Snapshot:/Users/georgy/Zotero/storage/IK9RYEMG/7177885.html:text/html},
}

@misc{rijal_2025,
      title={Inferring genotype-phenotype maps using attention models},
      author={Krishna Rijal and Caroline M. Holmes and Samantha Petti and Gautam Reddy and Michael M. Desai and Pankaj Mehta},
      year={2025},
      eprint={2504.10388},
      archivePrefix={arXiv},
      primaryClass={q-bio.GN},
      url={https://arxiv.org/abs/2504.10388},
}

 @article{Sandler2025Epistasis,
	author = {Sandler, George and York, Ryan},
	journal = {Arcadia Science},
	doi = {10.57844/arcadia-25nt-guw3},
	issn = {2998-4084},
	year = {2025},
	month = {jun 16},
	publisher = {Arcadia Science},
	title = {Epistasis and deep learning in quantitative genetics},
	url = {https://research.arcadiascience.com/pub/result-gp-deep-learning-scaling/release/1},
}

 @article{York2025Cross,
	author = {York, Ryan and Kiefl, Evan and Bigge, Brae M. and McGeever, Erin},
	journal = {Arcadia Science},
	doi = {10.57844/arcadia-bmb9-fzxd},
	issn = {2998-4084},
	year = {2025},
	month = {may 1},
	publisher = {Arcadia Science},
	title = {Cross-trait learning with a canonical transformer tops custom attention in genotype--phenotype mapping},
	url = {https://research.arcadiascience.com/pub/observation-geno-pheno-attention/release/1},
}

@article{York2025GP,
	author = {York, Ryan and Mets, David G.},
	journal = {Arcadia Science},
	doi = {10.57844/arcadia-d316-721f},
	issn = {2998-4084},
	year = {2025},
	month = {aug 8},
	publisher = {Arcadia Science},
	title = {G--{P} {Atlas}: A neural network framework for mapping genotypes to many phenotypes},
	url = {https://research.arcadiascience.com/pub/result-g-p-atlas/release/1},
}

@article{zeng_g2pdeep_2021,
	title = {{G2PDeep}: a web-based deep-learning framework for quantitative phenotype prediction and discovery of genomic markers},
	volume = {49},
	issn = {0305-1048},
	shorttitle = {{G2PDeep}},
	url = {https://doi.org/10.1093/nar/gkab407},
	doi = {10.1093/nar/gkab407},
	abstract = {G2PDeep is an open-access web server, which provides a deep-learning framework for quantitative phenotype prediction and discovery of genomics markers. It uses zygosity or single nucleotide polymorphism (SNP) information from plants and animals as the input to predict quantitative phenotype of interest and genomic markers associated with phenotype. It provides a one-stop-shop platform for researchers to create deep-learning models through an interactive web interface and train these models with uploaded data, using high-performance computing resources plugged at the backend. G2PDeep also provides a series of informative interfaces to monitor the training process and compare the performance among the trained models. The trained models can then be deployed automatically. The quantitative phenotype and genomic markers are predicted using a user-selected trained model and the results are visualized. Our state-of-the-art model has been benchmarked and demonstrated competitive performance in quantitative phenotype predictions by other researchers. In addition, the server integrates the soybean nested association mapping (SoyNAM) dataset with five phenotypes, including grain yield, height, moisture, oil, and protein. A publicly available dataset for seed protein and oil content has also been integrated into the server. The G2PDeep server is publicly available at http://g2pdeep.org. The Python-based deep-learning model is available at https://github.com/shuaizengMU/G2PDeep\_model.},
	number = {W1},
	urldate = {2025-05-19},
	journal = {Nucleic Acids Research},
	author = {Zeng, Shuai and Mao, Ziting and Ren, Yijie and Wang, Duolin and Xu, Dong and Joshi, Trupti},
	month = jul,
	year = {2021},
	pages = {W228--W236}
}

@article{bricken2023monosemanticity,
       title={Towards Monosemanticity: Decomposing Language Models With Dictionary Learning},
       author={Bricken, Trenton and Templeton, Adly and Batson, Joshua and Chen, Brian and Jermyn, Adam and Conerly, Tom and Turner, Nick and Anil, Cem and Denison, Carson and Askell, Amanda and Lasenby, Robert and Wu, Yifan and Kravec, Shauna and Schiefer, Nicholas and Maxwell, Tim and Joseph, Nicholas and Hatfield-Dodds, Zac and Tamkin, Alex and Nguyen, Karina and McLean, Brayden and Burke, Josiah E and Hume, Tristan and Carter, Shan and Henighan, Tom and Olah, Christopher},
       year={2023},
       journal={Transformer Circuits Thread},
       note={https://transformer-circuits.pub/2023/monosemantic-features/index.html}
}

@article{elhage2021mathematical,
   title={A Mathematical Framework for Transformer Circuits},
   author={Elhage, Nelson and Nanda, Neel and Olsson, Catherine and Henighan, Tom and Joseph, Nicholas and Mann, Ben and Askell, Amanda and Bai, Yuntao and Chen, Anna and Conerly, Tom and DasSarma, Nova and Drain, Dawn and Ganguli, Deep and Hatfield-Dodds, Zac and Hernandez, Danny and Jones, Andy and Kernion, Jackson and Lovitt, Liane and Ndousse, Kamal and Amodei, Dario and Brown, Tom and Clark, Jack and Kaplan, Jared and McCandlish, Sam and Olah, Chris},
   year={2021},
   journal={Transformer Circuits Thread},
   note={https://transformer-circuits.pub/2021/framework/index.html}
}

@inproceedings{wang_edjm,
author = {Wang, Shengjie and Mohamed, Abdel-Rahman and Caruana, Rich and Bilmes, Jeff and Plilipose, Matthai and Richardson, Matthew and Geras, Krzysztof and Urban, Gregor and Aslan, Ozlem},
title = {Analysis of deep neural networks with the extended data Jacobian matrix},
year = {2016},
publisher = {JMLR.org},
abstract = {Deep neural networks have achieved great success on a variety of machine learning tasks. There are many fundamental and open questions yet to be answered, however. We introduce the Extended Data Jacobian Matrix (EDJM) as an architecture-independent tool to analyze neural networks at the manifold of interest. The spectrum of the EDJM is found to be highly correlated with the complexity of the learned functions. After studying the effect of dropout, ensembles, and model distillation using EDJM, we propose a novel spectral regularization method, which improves network performance.},
booktitle = {Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48},
pages = {718–727},
numpages = {10},
location = {New York, NY, USA},
series = {ICML'16}
}

@misc{mohan2020biasfree,
      title={Robust and interpretable blind image denoising via bias-free convolutional neural networks},
      author={Sreyas Mohan and Zahra Kadkhodaie and Eero P. Simoncelli and Carlos Fernandez-Granda},
      year={2020},
      eprint={1906.05478},
      archivePrefix={arXiv},
      primaryClass={eess.IV},
      url={https://arxiv.org/abs/1906.05478},
}


@article{gaynor_alphasimr_2021,
	title = {{AlphaSimR}: an {R} package for breeding program simulations},
	volume = {11},
	issn = {2160-1836},
	shorttitle = {{AlphaSimR}},
	url = {https://doi.org/10.1093/g3journal/jkaa017},
	doi = {10.1093/g3journal/jkaa017},
	abstract = {This paper introduces AlphaSimR, an R package for stochastic simulations of plant and animal breeding programs. AlphaSimR is a highly flexible software package able to simulate a wide range of plant and animal breeding programs for diploid and autopolyploid species. AlphaSimR is ideal for testing the overall strategy and detailed design of breeding programs. AlphaSimR utilizes a scripting approach to building simulations that is particularly well suited for modeling highly complex breeding programs, such as commercial breeding programs. The primary benefit of this scripting approach is that it frees users from preset breeding program designs and allows them to model nearly any breeding program design. This paper lists the main features of AlphaSimR and provides a brief example simulation to show how to use the software.},
	number = {2},
	urldate = {2025-10-14},
	journal = {G3 Genes{\textbar}Genomes{\textbar}Genetics},
	author = {Gaynor, R Chris and Gorjanc, Gregor and Hickey, John M},
	month = feb,
	year = {2021},
}


@article{mackay_epistasis_2014,
	title = {Epistasis and quantitative traits: using model organisms to study gene–gene interactions},
	volume = {15},
	copyright = {2013 Springer Nature Limited},
	issn = {1471-0064},
	shorttitle = {Epistasis and quantitative traits},
	url = {https://www.nature.com/articles/nrg3627},
	doi = {10.1038/nrg3627},
	language = {en},
	number = {1},
	urldate = {2025-10-14},
	journal = {Nature Reviews Genetics},
	author = {Mackay, Trudy F. C.},
	month = jan,
	year = {2014},
	note = {Publisher: Nature Publishing Group},
}


@article{tucker_cropherit_2020,
	title = {Evaluating maize phenotypic variance, heritability, and yield relationships at multiple biological scales across agronomically relevant environments},
	volume = {43},
	issn = {1365-3040},
	url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/pce.13681},
	doi = {10.1111/pce.13681},
	number = {4},
	urldate = {2025-10-14},
	journal = {Plant, Cell \& Environment},
	author = {Tucker, Sarah L. and Dohleman, Frank G. and Grapov, Dmitry and Flagel, Lex and Yang, Sean and Wegener, Kimberly M. and Kosola, Kevin and Swarup, Shilpa and Rapp, Ryan A. and Bedair, Mohamed and Halls, Steven C. and Glenn, Kevin C. and Hall, Michael A. and Allen, Edwards and Rice, Elena A.},
	year = {2020},
	keywords = {drought, field conditions, genetic variation, growth, maize yield},
	pages = {880--902},
}