Linnaeus: A highly reusable and adaptable ML based log classification pipeline · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2103.06927/Collected HN comments and submissions linking this paper.enTue, 10 Nov 2026 07:51:04 GMTLinnaeus: A highly reusable and adaptable ML based log classification pipeline — mentioned by armcathttps://news.ycombinator.com/item?id=50436847urn:hackerpapers:mention:2103.06927:50436847Tue, 10 Nov 2026 06:39:46 GMT<p>About six years ago we built a ticket classification/routing model and pipeline [1]. The initial version was trained using SVMs, it took a couple of minutes to train, and the ticket classification was just a few milliseconds. It&#x27;s so fascinating to watch how the field moved over to LLMs, and then back to faster/cheaper classifiers again. [1] &quot;Linnaeus: A highly reusable and adaptable ML based log classification pipeline&quot;, https://arxiv.org/abs/2103.06927 NOTE: the work was actually accepted at the International Conference on Software Engineering (ICSE) in 2021.</p><p><a href="https://hackerpaper.kaipfister.de/p/2103.06927/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG