Minor paper adjustments

* Affiliation
* PDBL citation
* DOIs and ArXiv format

paper.bib

@@ -1,16 +1,18 @@
-@article{rauber2020eagerpy,
-  title={{EagerPy}: Writing Code That Works Natively with {PyTorch}, {TensorFlow}, {JAX}, and {NumPy}},
-  author={Rauber, Jonas and Bethge, Matthias and Brendel, Wieland},
-  journal={arXiv preprint arXiv:2008.04175},
+
+@misc{rauber2020eagerpy,
+  title={EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy},
+  author={Jonas Rauber and Matthias Bethge and Wieland Brendel},
   year={2020},
-  url={https://eagerpy.jonasrauber.de},
+  eprint={2008.04175},
+  archivePrefix={arXiv},
+  primaryClass={cs.LG}
 }
 
-@article{phiflow,
-  title={Learning to control pdes with differentiable physics},
-  author={Holl, Philipp and Koltun, Vladlen and Thuerey, Nils},
-  journal={arXiv preprint arXiv:2001.07457},
-  year={2020}
+@inproceedings{phiflow,
+  title={Learning to Control PDEs with Differentiable Physics},
+  author={Holl, Philipp and Thuerey, Nils and Koltun, Vladlen},
+  booktitle={International Conference on Learning Representations},
+  year={2019}
 }
 
 @book{Python3,
@@ -244,10 +246,11 @@ @book{HFDPatterns2004
 
 @inproceedings{TensorFlow2016,
   title={Tensorflow: A system for large-scale machine learning},
-  author={Abadi, Mart{\'\i}n and Barham, Paul and Chen, Jianmin and Chen, Zhifeng and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and Ghemawat, Sanjay and Irving, Geoffrey and Isard, Michael and others},
+  author={Abadi, Martin and Barham, Paul and Chen, Jianmin and Chen, Zhifeng and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and Ghemawat, Sanjay and Irving, Geoffrey and Isard, Michael and others},
   booktitle={12th $\{$USENIX$\}$ symposium on operating systems design and implementation ($\{$OSDI$\}$ 16)},
   pages={265--283},
-  year={2016}
+  year={2016},
+  doi={}
 }
 
 @article{PyTorch2019,
@@ -328,18 +331,20 @@ @article{ScaleInvariant2022
   year={2022}
 }
 
-@article{HalfInverse2022,
-  title={Half-inverse gradients for physical deep learning},
+@inproceedings{HalfInverse2022,
+  title={Half-Inverse Gradients for Physical Deep Learning},
   author={Schnell, Patrick and Holl, Philipp and Thuerey, Nils},
-  journal={arXiv preprint arXiv:2203.10131},
-  year={2022}
+  booktitle={International Conference on Learning Representations},
+  year={2021}
 }
 
-@article{PBDL2021,
-  title={Physics-based deep learning},
-  author={Thuerey, Nils and Holl, Philipp and Mueller, Maximilian and Schnell, Patrick and Trost, Felix and Um, Kiwon},
-  journal={arXiv preprint arXiv:2109.05237},
-  year={2021}
+@misc{PBDL2021,
+  title={Physics-based Deep Learning},
+  author={Nils Thuerey and Philipp Holl and Maximilian Mueller and Patrick Schnell and Felix Trost and Kiwon Um},
+  year={2022},
+  eprint={2109.05237},
+  archivePrefix={arXiv},
+  primaryClass={cs.LG}
 }
 
 
@@ -352,11 +357,13 @@ @article{PDEBench
   year={2022}
 }
 
-@article{PDEArena,
+@misc{PDEArena,
   title={Towards Multi-spatiotemporal-scale Generalized PDE Modeling},
-  author={Gupta, Jayesh K and Brandstetter, Johannes},
-  journal={arXiv preprint arXiv:2209.15616},
-  year={2022}
+  author={Jayesh K. Gupta and Johannes Brandstetter},
+  year={2022},
+  eprint={2209.15616},
+  archivePrefix={arXiv},
+  primaryClass={cs.LG}
 }
 
 
@@ -374,13 +381,15 @@ @article{wandel2021teaching
   volume={33},
   number={4},
   year={2021},
-  publisher={AIP Publishing}
+  publisher={AIP Publishing},
+  doi={DOI: 10.1063/5.0047428}
 }
 @inproceedings{brandstetter2022clifford,
   title={Clifford Neural Layers for PDE Modeling},
   author={Brandstetter, Johannes and van den Berg, Rianne and Welling, Max and Gupta, Jayesh K},
   booktitle={The Eleventh International Conference on Learning Representations},
-  year={2022}
+  year={2022},
+  doi={10.48550/arXiv.2209.04934}
 }
 @inproceedings{wandel2020learning,
   title={Learning Incompressible Fluid Dynamics from Scratch-Towards Fast, Differentiable Fluid Models that Generalize},
@@ -393,7 +402,8 @@ @inproceedings{sengar2021multi
   author={Sengar, Vartika and Seemakurthy, Karthik and Gubbi, Jayavardhana and P, Balamuralidhar},
   booktitle={Proceedings of the twelfth Indian conference on computer vision, graphics and image processing},
   pages={1--9},
-  year={2021}
+  year={2021},
+  doi={10.1145/3490035.3490283}
 }
 @article{parekh1993sex,
   title={Sex differences in control of renal outer medullary circulation in rats: role of prostaglandins},
@@ -403,13 +413,15 @@ @article{parekh1993sex
   number={4},
   pages={F629--F636},
   year={1993},
-  publisher={American Physiological Society Bethesda, MD}
+  publisher={American Physiological Society Bethesda, MD},
+  doi={10.1152/ajprenal.1993.264.4.F629}
 }
 @inproceedings{ramos2022control,
   title={Control of Two-way Coupled Fluid Systems with Differentiable Solvers},
   author={Ramos, Brener and Trost, Felix and Thuerey, Nils},
   booktitle={ICLR 2022 Workshop on Generalizable Policy Learning in Physical World},
-  year={2022}
+  year={2022},
+  doi={10.48550/arXiv.2206.00342}
 }
 @inproceedings{wang2022approximately,
   title={Approximately equivariant networks for imperfectly symmetric dynamics},
@@ -434,7 +446,8 @@ @inproceedings{wang2023applications
   volume={12509},
   pages={300--305},
   year={2023},
-  organization={SPIE}
+  organization={SPIE},
+  doi={10.1117/12.2656026}
 }
 @article{wu2022learning,
   title={Learning to accelerate partial differential equations via latent global evolution},

paper.md

@@ -18,7 +18,7 @@ authors:
     orcid: 0000-0001-6647-8910
     affiliation: 1
 affiliations:
-  - name: Technical University of Munich
+  - name: School of Computation, Information and Technology, Technical University of Munich, Germany
     index: 1
 date: 01 August 2023
 bibliography: paper.bib
@@ -95,7 +95,7 @@ $\Phi_\textrm{Flow}$ includes geometry, physics, and visualization modules, all
 
 It was first used to show that differentiable PDE simulations can be used to train neural networks that steer the dynamics towards desired outcomes [@phiflow].
 Differentiable PDEs, implemented against $\Phi_\textrm{ML}$'s API, were later shown to benefit learning corrections for low-resolution or incomplete physics models [@SolverInTheLoop2020].
-These findings were summarized and formalized in [@PBDL2021], along with many additional examples.
+These findings were summarized and formalized in @PBDL2021, along with many additional examples.
 
 The library was also used in network optimization publications, such as showing that inverted simulations can be used to train networks [@ScaleInvariant2022] and that gradient inversion benefits learning the solutions to inverse problems [@HalfInverse2022].