Insert New
Slide
​
Roboto
A
Slide Break Defaults…
​
Cell Actions
Window Options
Start Presentation
▼

Slide
1
of
9
​
​

Scholarly Insight through the ArXivExplore Paclet

Daniele Gregori, Soochow University
Institute for Advanced Study
​​
#WolframTechConf

Slide
2
of
9
​
​

ABSTRACT

In[]:=
abstract="ArXivExplore helps the deep data analysis of all 2.6M physics, math, computer science, etc. articles on ArXiv, providing functionality for e.g. title/abstract word statistics, TeX source/formulae/citations dissection, NNs for classification or recommendation and LLM-automated concept explanations and author reports.";
Out[]=
​

Paclet loading


Slide
3
of
9
​
​

Introduction

On ArXiv

A “deep data” problem

Academic “chat” vs scientific “insight”

Some ArXiv questions


Slide
4
of
9
​
​

ArXiv data mining

ArXiv main data

Categories

Full
T
E
X
scraping

Citations API


Slide
5
of
9
​
​

Real insights from “just counting”

Submission trends

Counting total words

Word popularity trends

Word logic combinations


Slide
6
of
9
​
​

Some Machine Learning

Basic classification

Advanced training

Feature extraction

Clustering


Slide
7
of
9
​
​

LLMs to enhance understanding

The importance of introductions

Explaining specific concepts

Creating author reports


Slide
8
of
9
​
​

Conclusions

Unlimited explorations

Planned improvements

New horizons in “deep data”


Slide
9
of
9
​
​

Thank you!

Out[]=