Basic Examples (4) 

The first article ever on ArXiv:

In[1]:=

Out[1]=

In[2]:=

Out[2]=

In[3]:=

Out[3]=

In[4]:=

Out[4]=

A DateListPlot showing the trends in the most popular title words in theoretical physics category (hep-th):

In[5]:=

Out[5]=

All the 50 most common 2-neighbour title words on the whole ArXiv, ever:

In[6]:=

1750.871668`

Out[6]=

Let us also show an author's citations graph, with the tooltip indicating the articles ids:

In[7]:=

Out[7]=

Scope (11) 

The dimensions whole ArXiv dataset (at the end of July 2024):

In[8]:=

Out[8]=

Let us create a super-database with all computer science "cs" type primary or cross-list categories:

In[9]:=

and then let us visualize the most frequent and less frequent title words:

In[10]:=

Out[10]=

Let us compute the 4 most frequent categories, with their meaning:

In[11]:=

Out[11]=

Using only titles and abstracts, we can train a NN to classify different categories:

In[12]:=

In[13]:=

Out[13]=

In[14]:=

Out[14]=

Even with a basic 17 minutes training on laptop CPU, we obtain 98% accuracy:

In[15]:=

Out[15]=

In[16]:=

Out[16]=

We could even classify authors within the same category, with ArXivClassifyAuthorNet.

Extracting TEX introduction:

In[17]:=

Out[17]=

also TEX formulae:

In[18]:=

Out[18]=

Explain a technical concept using an article introduction and LLMSynthesize:

In[19]:=

Out[19]=

Let us visualize all authors with more than 7 papers, in primary category "cs.NA":

In[20]:=

Out[20]=

Let us pick a random author among them and use LLM functionality to explain his overall work:

In[21]:=

Out[21]=