fix link to benchmarks in README

README.md

@@ -46,7 +46,7 @@ EBM is an interpretable model developed at Microsoft Research<sup>[*](#citations
 | Telecom Churn | Business| .849±.005           | .824±.004     | .828±.010       | **_.852±.006_**              |
 | Credit Fraud  | Security| .979±.002           | .950±.007     | **_.981±.003_** | **_.981±.003_**              |
 
-[*Notebook for reproducing table*](https://nbviewer.jupyter.org/github/interpretml/interpret/blob/master/benchmarks/EBM%20Classification%20Comparison.ipynb)
+[*Notebook for reproducing table*](https://nbviewer.jupyter.org/github/interpretml/interpret/blob/main/benchmarks/EBM_Classification_Comparison.ipynb)
 
 # Supported Techniques
 
@@ -604,6 +604,7 @@ We also build on top of many great packages. Please check them out!
 
 # Papers that use or compare EBMs
 
+- [LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs](https://arxiv.org/pdf/2308.01157.pdf)
 - [Model Interpretability in Credit Insurance](http://hdl.handle.net/10400.5/27507)
 - [Federated Boosted Decision Trees with Differential Privacy](https://arxiv.org/pdf/2210.02910.pdf)
 - [GAM(E) CHANGER OR NOT? AN EVALUATION OF INTERPRETABLE MACHINE LEARNING MODELS](https://arxiv.org/pdf/2204.09123.pdf)
@@ -626,6 +627,11 @@ We also build on top of many great packages. Please check them out!
 - [Exploring the Balance between Interpretability and Performance with carefully designed Constrainable Neural Additive Models](https://deliverypdf.ssrn.com/delivery.php?ID=998105006000069122073098120102102121021040051018055094125029122011041003059093125102072122106122077081069015087124028097016003127095087091028087010007035098086102086081014043013113004081117108011028041097095064071100112069081100069120077067116088100069070097093080074087115080072064086111126&EXT=pdf&INDEX=TRUE)
 - [Estimating Discontinuous Time-Varying Risk Factors and Treatment Benefits for COVID-19 with Interpretable ML](https://arxiv.org/pdf/2211.08991.pdf)
 - [StratoMod: Predicting sequencing and variant calling errors with interpretable machine learning](https://www.biorxiv.org/content/10.1101/2023.01.20.524401v1.full.pdf)
+- [Interpretable machine learning algorithms to predict leaf senescence date of deciduous trees](https://pdf.sciencedirectassets.com/271723/1-s2.0-S0168192323X00112/1-s2.0-S0168192323003143/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEOP%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJGMEQCIArPrCug2%2BpvA%2F87dfMYdbINsntWDDgNHeCOn72Yfad3AiBHzR9BvMkRvZrjQZ1DoY1YMkD6VsQw45zqo5ykkClnHSq8BQiL%2F%2F%2F%2F%2F%2F%2F%2F%2F%2F8BEAUaDDA1OTAwMzU0Njg2NSIMdV4IhgM83azwHKyjKpAFFMABPkhGjjH1i3y26weF5LN6ZuxfgcDlklmnpEZDoEntreay08vlEU7%2F3CLeNSqYgaq5txCiVztJDv2TBcxDUt0PP4faNrHUWIQdfDksvDs3EE7VEupaqhVjMNi0%2F%2ByLRw2OzjMPpz7H5sd3i4%2F%2FK2%2FJlpAWHlr4RFJ9BXMMPbLDEqhjIJIl5ZzaeLeeijXKrTtvJ6iYwTic%2FHJ23m7Fdnkh94HKkFTOWeglJzGT7FSc5Wnc7DgExrL7EBLvu9YVusMUf9rFYIU%2BKaVyxIa7WDUN48cWjwdGLjYV9XPy%2FP2lRKjeiiNMYbdknQzJfSzh0HWxx0Aq6zlXdkJUbvSgqFoDC2npaUGXjNupSLNIzcMFWr8lUvUFIBm1ZigETFDZrB4zEJFQVxXV%2Bsztpcs1tMO%2F8LAG3MNI%2BI%2Fp7lT3bj%2F%2BZg6S7d6ROGS96XMS3Am3WffiwNIxueTGrWmRWxS75EQexcJmrQ4ELU%2By3vOXxIvqftT68w6%2BnBryUB5kGE%2B6GljxUFD5y7hZFLM0tfFW9XEZF5PjDbz%2Fx%2Bi0dxEiwvN2mzNpSAWiiy6ZBT31GSRRMtTe9Sm4U%2B8DwSR0fymXmme5fKLGzkySq0xPuFhzN6LyLCoxtbob%2BRyLALNdP8E31enPu%2B1xl5Isg%2FXHINRM29SYzK0u1PlPK78ng%2Bqt4mUlLD7jlzIeBKa1vz%2BU8%2F1ZYvEofc8i6q691PqjYl%2FZK5lFQO1EEremVOv4i2nEYwmGtjtCAk1WFChnamFlEdWyJIerN5pKI4YvsGF%2FwXG8aHuYBg41CfGftl%2FwlJ77dPOQ8QHgp5BZFheyeYwEMijnbz4terE7kVpdvBKOk5lBxtiJILI0ftU%2F4F0k825M%2Ft4w%2FqzIpgY6sgFspzJ6vfwqmIKbmprTCY6NBr4uAZU%2FPUWraWxu3hCydMZTVOjlrab%2Bv5NSdCqWKHvK7Yn89JtE9um3P8Gyev9BFPXT6LykCtjNOulKUQnywvl8ngKdbujNjLAyZb4D0p4dFRFsE2sUTUWNvs%2BVwA%2BYdn4%2BwPkMN5PU0KR78myJ7LyYJGodNLOXcBSV%2FXa396TmeXagW3ihm2U7H%2FvXm1IZmOz%2FflT5y6CEy%2FegChXEVpb6&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Date=20230808T111525Z&X-Amz-SignedHeaders=host&X-Amz-Expires=300&X-Amz-Credential=ASIAQ3PHCVTY64PTFOFS%2F20230808%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Signature=e35040e1985923b74081dbdac33f7250949695d95e631d68a8fe20684b3746bc&hash=59ce65176ba4b931ecc905ef2a0bb80561947d73205e8ad2561d63a95552a4fb&host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&pii=S0168192323003143&tid=spdf-41137a89-2992-4585-8512-4303f8dedb0c&sid=b0b6f2a791aeb640d1897e968c8092375869gxrqa&type=client&tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t&ua=10145807525053555255&rr=7f375764f8ea2338&cc=us)
+- [Comparing Explainable Machine Learning Approaches With Traditional Statistical Methods for Evaluating Stroke Risk Models: Retrospective Cohort Study](https://cardio.jmir.org/2023/1/e47736/PDF)
+- [Cross Feature Selection to Eliminate Spurious Interactions and Single Feature Dominance Explainable Boosting Machines](https://arxiv.org/ftp/arxiv/papers/2307/2307.08485.pdf)
+- [Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Models](https://arxiv.org/pdf/2307.08175v1.pdf)
+- [An explainable model to support the decision about the therapy protocol for AML](https://arxiv.org/pdf/2307.02631.pdf)
 - [Assessing wind field characteristics along the airport runway glide slope: an explainable boosting machine-assisted wind tunnel study](https://www.nature.com/articles/s41598-023-36495-5)
 - [Diagnosis uncertain models for medical risk prediction](https://arxiv.org/pdf/2306.17337.pdf)
 - [Extending Explainable Boosting Machines to Scientific Image Data](https://arxiv.org/pdf/2305.16526.pdf)

scripts/release_process.txt

@@ -151,7 +151,7 @@ set_visualize_provider(InlineProvider())
     - wait for the merged code to build. conda-forge will publish it to conda.org if the build completes successfully
     - check that the package was uploaded at: https://anaconda.org/conda-forge/interpret-core
     - wait a bit longer (30 minutes seems to sometimes work) for the CDN to have an updated copy. If a rebuild is needed use: @conda-forge-admin, please restart ci
-  - interpret:
+  - interpret (consider waiting to publish interpret until interpret-core is tested):
     - fork into a new github username repo from (if not already forked): https://github.com/conda-forge/interpret-feedstock
     - sync the fork, if not already synced
     - edit the local repo in github: https://github.com/<USERNAME>/interpret-feedstock/blob/main/recipe/meta.yaml
@@ -186,7 +186,7 @@ from interpret.provider import InlineProvider
 set_visualize_provider(InlineProvider())
   - re-run all the notebooks and check the visualizations again
 
-- publish on PyPI:
+- publish on PyPI (consider waiting to publish interpret until interpret-core is tested):
   - upload the sdist and bdist together:
     - cd <PACKAGE_DOWNLOAD_DIRECTORY>
     - pip install twine