The gains from dynamic allocation under aggressive pruning are concentrated in generative tasks, including large recoveries on MATH-500 and LiveCodeBench.

The gains from dynamic allocation under aggressive pruning are concentrated in generative tasks, including large recoveries on MATH-500 and LiveCodeBench. · CiteArk

Measurement results

0/10 assessed

0 supported0 disputed or conflicting10 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
printedValue: 3.17	3.17 percentage points	—	Not assessed
printedValue: 1.20	1.2 percentage points	—	Not assessed
printedValue: 80.2	80.2 percentage points	—	Not assessed
printedValue: 88.0	88 percentage points	—	Not assessed
printedValue: 25.7	25.7 percentage points	—	Not assessed
printedValue: 28.6	28.6 percentage points	—	Not assessed
printedValue: 48.0	48 percentage points	—	Not assessed
printedValue: 62.5	62.5 percentage points	—	Not assessed
printedValue: 14.5	14.5 percentage points	—	Not assessed
printedValue: 0.90	0.9 percentage points	—	Not assessed

The gains from dynamic allocation under aggressive pruning are concentrated in generative tasks, including large recoveries on MATH-500 and LiveCodeBench.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results