Most people got the badges they were targeting, meaning that many people did not target "results replicated". We followed ACM's criteria regarding RR: "results should support the main takeaways of the paper".
-
-
-
Thanks! I belatedly found the badge legend (https://sysartifacts.github.io/badges.html ), which says as much. A sensible criterion, given how difficult exact reproduction of performance results can be (and hence my curiosity).
- Još 4 druga odgovora
Novi razgovor -
-
-
It appears that the main predictor for failing to reproduce was not participating, which is a shame. Each of those papers is not science.
-
To be fair, the timeline was kind of short. Authors had to do this in addition to preparing the camera ready. So some authors might not have participated simply due to time constraints, we’ll try to fix this in the next iteration of artifact evaluation.
- Još 5 drugih odgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.