Machines recover up to 53% of the crowd-highlight prediction headroom, and fusing five frontier models reaches about 60%, confirmed in a pre-registered replication.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?
Machines recover up to 53% of the crowd-highlight prediction headroom, and fusing five frontier models reaches about 60%, confirmed in a pre-registered replication.