Changing the number of retrieved WebShop trajectories from k=3 to k=5 changes success rate by less than two points for every executor; the differences are within standard deviation for Qwen3-8B and GPT-5.4, and the main experiments use k=3.

Changing the number of retrieved WebShop trajectories from k=3 to k=5 changes success rate by less than two points for every executor; the differences are within standard deviation for Qwen3-8B and GPT-5.4, and the main experiments use k=3. · CiteArk

Measurement results

0/12 assessed

0 supported0 disputed or conflicting12 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.
Reported	Latest observation	Evidence judgment
61.1 points	—	Not assessed
32.8 percentage points	—	Not assessed
60.5 points	—	Not assessed
32.8 percentage points	—	Not assessed
61 points	—	Not assessed
50.5 percentage points	—	Not assessed
59.2 points	—	Not assessed
48.6 percentage points	—	Not assessed
53.8 points	—	Not assessed
45.4 percentage points	—	Not assessed
53.4 points	—	Not assessed
45.3 percentage points	—	Not assessed

Changing the number of retrieved WebShop trajectories from k=3 to k=5 changes success rate by less than two points for every executor; the differences are within standard deviation for Qwen3-8B and GPT-5.4, and the main experiments use k=3.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results