Info for tutors

You can find all submitted code in the .Submission/Group_11_code folder. Usage is explained either by the readme in the folder or by the markdown in the notebook.

The extracted math and feature data is contained in .Submission/Group_11_data. The full TeX data fetched from arXiv is uploaded on the Dropbox folder linked in the team_info file.

Links

1. PROJECT REPORT
2. Progress Report slides
3. Pitch slides

TODO:

Dataset

arXiv Downloads - DONE

• Write script to check downloaded papers for matching titles LINUS

Math Extraction - DONE

• Update Math-Extraction Script to parse properly LEON
• Run the script again LINUS

Feature Extraction - DONE

• Run the script LEON
• Check 10 files for whether feature Extraction is correct LINUS
• Update script to append normalized dependent variable values to predict (accepted/rejected) to csv LEON

Analysis/Validation - DEADLINE Friday 30.01 Evening

• Correlation Analysis - JAISIDH
• Linear Regression with Review Scores LEON
• Logistic Regression with Accept/Reject LEON
• Hypothesis Testing to get p-values for how separated the accepted/rejections populations are - JAISIDH
• Compile Analysis results in a clear document JAISIDH
• Compile Analysis results in a clear document LEON
• Compile Analysis results in a clear document ANUPAM

Visualization

• Prelim dataset overview figure (Saturday 8th Feb)
• Figure (: out analysis sketches
• Nice matplotlib styling (Saturday 8th Feb)

Code - DEADLINE Friday 30.01 Evening

• Put some comments. Should be readable. LINUS
• Put all analysis into a singular notebook. LINUS
• Make sure only the code we actually used is submitted. LINUS

Report (DEADLINE Su 09.02.25)

• First, very rough draft LINUS
• Abstract
• Introduction
• Assembling Dataset LINUS
• Analysis
• Results
• Discussion

Requirements

Evaluation Criteria