Strands Decider: Why Not an Encoder?

Automated excerpt

The state attends to the whole state bidirectionally, and each question attends to state and itself. First, let’s look at accuracy and calibration. b2 does very well here, beating v19 on JevBench accuracy and Brier, and on JF100 Brier at the same accuracy. The really interesting comparison is v19 and e1b. e1b slightly beats v19 on JevBench accuracy (but within the run-to-run variance on v19), with slightly worse calibration, and ties on calibration on JF100 with slightly weaker performance.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.