You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
we have many variants per abstract content (post rect concern, see #22 )
there are a multiple ways to process this:
shallow variant tracing (default): we consider the content under an abstract to be duplicative: the algorithm only looks at the top-performing variant under an abstract
allowlisted deep tracing: a TIMC can manually select one or more variants under an abstract, and the abstract itself, for inclusion or exclusion. Selection is respected, and when no selection is made we fall back to shallow variant tracing
full variant tracing: the processing algorithm looks at every variant and does internal deduplication
full tracing: the processing algorithm looks at every variant and the abstract public data
The text was updated successfully, but these errors were encountered:
we can also mark whole abstract content for inclusion or exclusion, or apply a performance filter on them, so that a variant will not be processed even if it is the best under an abstract but it is still not good enough for our rect-level bar. we can also include or exclude by tag, so that some very high performing videos might be excluded because they are comedy rather than instruction videos, for example.
we have many variants per abstract content (post rect concern, see #22 )
there are a multiple ways to process this:
The text was updated successfully, but these errors were encountered: