Abstract

The setting:

https://www.courtlistener.com/about/ is a non-profit organization based in california, USA. They have among others, a bulk data api for court cases in various courts in USA.

The have these 8 kinds of data:

citations: Most important for us. Looks like that:

citing_opinion_id,cited_opinion_id
1680953,112512
1680953,111499
1680953,103438
1680953,110993
1680953,378004
1680953,553262
1680953,112799
1680953,562343
1680953,458920
...24628375 rows total...