https://hackerpaper.kaipfister.de/p/0711.3964/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=15332608urn:hackerpapers:mention:0711.3964:15332608Mon, 25 Sep 2017 18:06:52 GMT<p>Great question! There is a few different things we do. First of all, students can flag parts of the feedback for moderation by a teacher. Secondly we calculate the inter-rater agreement between reviewers on a submission - that way teachers can look at submissions with a high disagreement. Of the slightly more complex parts, we have some algorithms that can detect biased students (similar to this https://arxiv.org/abs/0711.3964). Another simple trick is that if one reviewer says your work is good, another that it is bad and you don&#x27;t flag the feedback saying your work is bad, then the review…</p><p><a href="https://hackerpaper.kaipfister.de/p/0711.3964/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.IRhttps://news.ycombinator.com/item?id=134848urn:hackerpapers:submission:0711.3964:134848Wed, 12 Mar 2008 02:45:14 GMT<p>Iterative Filtering for a Dynamical Reputation System</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/0711.3964/">Paper and source history</a>. A submission is not an endorsement.</p>cs.IR