Question

Buckets: SMALL < $2B, MID $2B–$10B, LARGE > $10B by market cap at the cutoff (row attribute `market_cap_bucket`); return over 20 sessions = adjusted close today / adjusted close 20 sessions ago − 1. Find US-listed common equities (instruments without a reported market cap — warrants, units, rights, preferred series, notes — are not in the universe) with 20-day average dollar volume greater than $100M; within each market-cap bucket (SMALL < $2B, MID $2B–$10B, LARGE > $10B) take the top 5 by 20-day return descending. Scope: only entities with a known value for 20-day average dollar volume, 20-day return, market-cap bucket (SMALL < $2B, MID $2B–$10B, LARGE > $10B) in the snapshot; entities lacking any of them are out of scope and must not be returned. Return the picks grouped by the group value exactly as it appears in the data, each group's list in the requested order (best first); group membership and order are graded. Rebuild policy: metrics that are not served as fields (fundamental ratios, growth rates, valuation, technical signals) must be recomputed by you from the raw facts and daily bars the tools serve, following the definitions in list_metrics.compute_yourself to the letter (period selection, latest-filing copy, quarter arithmetic); do the arithmetic with run_calculation over the fetched data. The reference answer was computed from the same facts by the same definitions.