IBM / Project_CodeNet

This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX
Apache License 2.0
1.55k stars 193 forks source link

What is type-4 similarity? #49

Closed vadim0x60 closed 1 year ago

vadim0x60 commented 2 years ago

A sentence from README. "The problem-submission relationship in Project CodeNet corresponds to type-4 similarity and can be used for code search and clone detection". Some readers (me included) do not know what this refers to. Turning "type-4 similarity" into a hyperlink to a page that explains the concept would be very useful.

project-codenet commented 2 years ago

Hi Vadim, a link has been added to explain type-4 similarity. The README should be updated by Monday. The link is to this PhD thesis https://escholarship.org/uc/item/45r2308g. You can find the definition on page 6.