Merge pull request #14 from LengerichLab/context-invariant

[ci skip]

This build is based on
2528d57.

This commit was created by the following CI build and job:
https://github.com/LengerichLab/context-review/commit/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/checks
https://github.com/LengerichLab/context-review/actions/runs/11487083986

manuscript.html

@@ -6,7 +6,7 @@
   <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" />
   <meta name="author" content="Ben Lengerich" />
   <meta name="author" content="Caleb N. Ellington" />
-  <meta name="dcterms.date" content="2024-10-11" />
+  <meta name="dcterms.date" content="2024-10-23" />
   <meta name="keywords" content="markdown, publishing, manubot" />
   <title>Context-Adaptive Statistical Inference: Recent Progress, Open Problems, and Opportunities for Foundation Models</title>
   <style>
@@ -51,11 +51,11 @@
   <meta name="citation_title" content="Context-Adaptive Statistical Inference: Recent Progress, Open Problems, and Opportunities for Foundation Models" />
   <meta property="og:title" content="Context-Adaptive Statistical Inference: Recent Progress, Open Problems, and Opportunities for Foundation Models" />
   <meta property="twitter:title" content="Context-Adaptive Statistical Inference: Recent Progress, Open Problems, and Opportunities for Foundation Models" />
-  <meta name="dc.date" content="2024-10-11" />
-  <meta name="citation_publication_date" content="2024-10-11" />
-  <meta property="article:published_time" content="2024-10-11" />
-  <meta name="dc.modified" content="2024-10-11T19:49:14+00:00" />
-  <meta property="article:modified_time" content="2024-10-11T19:49:14+00:00" />
+  <meta name="dc.date" content="2024-10-23" />
+  <meta name="citation_publication_date" content="2024-10-23" />
+  <meta property="article:published_time" content="2024-10-23" />
+  <meta name="dc.modified" content="2024-10-23T19:50:33+00:00" />
+  <meta property="article:modified_time" content="2024-10-23T19:50:33+00:00" />
   <meta name="dc.language" content="en-US" />
   <meta name="citation_language" content="en-US" />
   <meta name="dc.relation.ispartof" content="Manubot" />
@@ -76,9 +76,9 @@
   <meta name="citation_fulltext_html_url" content="https://LengerichLab.github.io/context-review/" />
   <meta name="citation_pdf_url" content="https://LengerichLab.github.io/context-review/manuscript.pdf" />
   <link rel="alternate" type="application/pdf" href="https://LengerichLab.github.io/context-review/manuscript.pdf" />
-  <link rel="alternate" type="text/html" href="https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/" />
-  <meta name="manubot_html_url_versioned" content="https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/" />
-  <meta name="manubot_pdf_url_versioned" content="https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/manuscript.pdf" />
+  <link rel="alternate" type="text/html" href="https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/" />
+  <meta name="manubot_html_url_versioned" content="https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/" />
+  <meta name="manubot_pdf_url_versioned" content="https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/manuscript.pdf" />
   <meta property="og:type" content="article" />
   <meta property="twitter:card" content="summary_large_image" />
   <link rel="icon" type="image/png" sizes="192x192" href="https://manubot.org/favicon-192x192.png" />
@@ -95,10 +95,10 @@ <h1 class="title">Context-Adaptive Statistical Inference: Recent Progress, Open
 </header>
 <p><small><em>
 This manuscript
-(<a href="https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/">permalink</a>)
+(<a href="https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/">permalink</a>)
 was automatically generated
-from <a href="https://github.com/LengerichLab/context-review/tree/0d464534086e06b64933605aad0134f91fa46906">LengerichLab/context-review@0d46453</a>
-on October 11, 2024.
+from <a href="https://github.com/LengerichLab/context-review/tree/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1">LengerichLab/context-review@2528d57</a>
+on October 23, 2024.
 </em></small></p>
 <h2 id="authors">Authors</h2>
 <ul>
@@ -221,6 +221,14 @@ <h3 id="advances-in-varying-coefficient-models">Advances in Varying-Coefficient
 <p>TODO: Outlining key theoretical and methodological breakthroughs.</p>
 <h3 id="integration-with-state-of-the-art-machine-learning">Integration with State-of-the-Art Machine Learning</h3>
 <p>TODO: Assessing the enhancement of VC models through modern ML technologies (e.g. deep learning, boosted trees, etc).</p>
+<h3 id="context-invariant-training">Context-Invariant Training</h3>
+<p>TODO: The converse of VC models, exploring the implications of training context-invariant models.
+e.g. out-of-distribution generalization, robustness to adversarial attacks.</p>
+<h2 id="context-adaptive-interpretations-of-context-invariant-models">Context-Adaptive Interpretations of Context-Invariant Models</h2>
+<p>In the previous section, we discussed the importance of context in model parameters.
+Such context-adaptive models can be learned by explicitly modeling the impact of contextual variables on model parameters, or learned implicitly in a model containing interaction effects between the context and the input features.
+In this section, we will focus on recent progress in understanding how context influences interpretations of statistical models, even when the model was not originally designed to incorporate context.</p>
+<p>TODO: Discussing the implications of context-adaptive interpretations for traditional models. Related work including LIME/DeepLift/DeepSHAP.</p>
 <h2 id="opportunities-for-foundation-models">Opportunities for Foundation Models</h2>
 <h3 id="expanding-frameworks">Expanding Frameworks</h3>
 <p>TODO: Define foundation models, Explore how foundation models are redefining possibilities within statistical models.</p>

manuscript.md

@@ -5,7 +5,7 @@ keywords:
 - publishing
 - manubot
 lang: en-US
-date-meta: '2024-10-11'
+date-meta: '2024-10-23'
 author-meta:
 - Ben Lengerich
 - Caleb N. Ellington
@@ -20,11 +20,11 @@ header-includes: |
   <meta name="citation_title" content="Context-Adaptive Statistical Inference: Recent Progress, Open Problems, and Opportunities for Foundation Models" />
   <meta property="og:title" content="Context-Adaptive Statistical Inference: Recent Progress, Open Problems, and Opportunities for Foundation Models" />
   <meta property="twitter:title" content="Context-Adaptive Statistical Inference: Recent Progress, Open Problems, and Opportunities for Foundation Models" />
-  <meta name="dc.date" content="2024-10-11" />
-  <meta name="citation_publication_date" content="2024-10-11" />
-  <meta property="article:published_time" content="2024-10-11" />
-  <meta name="dc.modified" content="2024-10-11T19:49:14+00:00" />
-  <meta property="article:modified_time" content="2024-10-11T19:49:14+00:00" />
+  <meta name="dc.date" content="2024-10-23" />
+  <meta name="citation_publication_date" content="2024-10-23" />
+  <meta property="article:published_time" content="2024-10-23" />
+  <meta name="dc.modified" content="2024-10-23T19:50:33+00:00" />
+  <meta property="article:modified_time" content="2024-10-23T19:50:33+00:00" />
   <meta name="dc.language" content="en-US" />
   <meta name="citation_language" content="en-US" />
   <meta name="dc.relation.ispartof" content="Manubot" />
@@ -45,9 +45,9 @@ header-includes: |
   <meta name="citation_fulltext_html_url" content="https://LengerichLab.github.io/context-review/" />
   <meta name="citation_pdf_url" content="https://LengerichLab.github.io/context-review/manuscript.pdf" />
   <link rel="alternate" type="application/pdf" href="https://LengerichLab.github.io/context-review/manuscript.pdf" />
-  <link rel="alternate" type="text/html" href="https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/" />
-  <meta name="manubot_html_url_versioned" content="https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/" />
-  <meta name="manubot_pdf_url_versioned" content="https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/manuscript.pdf" />
+  <link rel="alternate" type="text/html" href="https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/" />
+  <meta name="manubot_html_url_versioned" content="https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/" />
+  <meta name="manubot_pdf_url_versioned" content="https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/manuscript.pdf" />
   <meta property="og:type" content="article" />
   <meta property="twitter:card" content="summary_large_image" />
   <link rel="icon" type="image/png" sizes="192x192" href="https://manubot.org/favicon-192x192.png" />
@@ -69,10 +69,10 @@ manubot-clear-requests-cache: false
 
 <small><em>
 This manuscript
-([permalink](https://LengerichLab.github.io/context-review/v/0d464534086e06b64933605aad0134f91fa46906/))
+([permalink](https://LengerichLab.github.io/context-review/v/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1/))
 was automatically generated
-from [LengerichLab/context-review@0d46453](https://github.com/LengerichLab/context-review/tree/0d464534086e06b64933605aad0134f91fa46906)
-on October 11, 2024.
+from [LengerichLab/context-review@2528d57](https://github.com/LengerichLab/context-review/tree/2528d57ccdac66e46f2d69ffb7d5b0879572f6d1)
+on October 23, 2024.
 </em></small>
 
 
@@ -246,6 +246,19 @@ TODO: Outlining key theoretical and methodological breakthroughs.
 ### Integration with State-of-the-Art Machine Learning
 TODO: Assessing the enhancement of VC models through modern ML technologies (e.g. deep learning, boosted trees, etc).
 
+### Context-Invariant Training
+TODO: The converse of VC models, exploring the implications of training context-invariant models.
+e.g. out-of-distribution generalization, robustness to adversarial attacks.
+
+## Context-Adaptive Interpretations of Context-Invariant Models
+
+In the previous section, we discussed the importance of context in model parameters. 
+Such context-adaptive models can be learned by explicitly modeling the impact of contextual variables on model parameters, or learned implicitly in a model containing interaction effects between the context and the input features.
+In this section, we will focus on recent progress in understanding how context influences interpretations of statistical models, even when the model was not originally designed to incorporate context.
+
+TODO: Discussing the implications of context-adaptive interpretations for traditional models. Related work including LIME/DeepLift/DeepSHAP.
+
+
 ## Opportunities for Foundation Models
 
 ### Expanding Frameworks

spelling-error-locations.txt

@@ -32,20 +32,25 @@ content/03.vc.md:4:TODO
 content/03.vc.md:7:TODO
 content/03.vc.md:10:TODO
 content/03.vc.md:10:VC
-content/04.foundation.md:4:TODO
-content/04.foundation.md:8:TODO
-content/05.applications.md:4:TODO
-content/05.applications.md:7:TODO
-content/06.tools.md:4:TODO
-content/06.tools.md:7:TODO
-content/07.future_trends.md:4:TODO
-content/07.future_trends.md:7:TODO
-content/08.open_problems.md:4:identifiability
-content/08.open_problems.md:4:TODO
-content/08.open_problems.md:7:interpretability
-content/08.open_problems.md:7:regulatability
-content/08.open_problems.md:7:TODO
-content/08.open_problems.md:10:TODO
-content/08.open_problems.md:12:TODO
-content/09.conclusion.md:4:TODO
-content/09.conclusion.md:8:TODO
+content/03.vc.md:13:TODO
+content/03.vc.md:13:VC
+content/04.interpretations.md:7:DeepLift
+content/04.interpretations.md:7:DeepSHAP
+content/04.interpretations.md:7:TODO
+content/05.foundation.md:4:TODO
+content/05.foundation.md:8:TODO
+content/06.applications.md:4:TODO
+content/06.applications.md:7:TODO
+content/07.tools.md:4:TODO
+content/07.tools.md:7:TODO
+content/08.future_trends.md:4:TODO
+content/08.future_trends.md:7:TODO
+content/09.open_problems.md:4:identifiability
+content/09.open_problems.md:4:TODO
+content/09.open_problems.md:7:interpretability
+content/09.open_problems.md:7:regulatability
+content/09.open_problems.md:7:TODO
+content/09.open_problems.md:10:TODO
+content/09.open_problems.md:12:TODO
+content/10.conclusion.md:4:TODO
+content/10.conclusion.md:8:TODO

spelling-errors.txt

@@ -1,12 +1,14 @@
-Adaptivity
+adaptivity
 arxiv
 blengerich
 cnellington
 covariate
 covariates
+DeepLift
+DeepSHAP
 identifiability
 interpretability
-lengerich
+Lengerich
 OLS
 Personalization
 probablybots