```xml <result> <column_name>Occupation: Business, finance & legal</column_name> <family>additive</family> <subtype>intensive_additive</subtype> <confidence>0.85</confidence> <requires_user_confirmation>false</requires_user_confirmation> <sum_meaningful>false</sum_meaningful> <signed>false</signed> <reducers> <primary_reducer>mean</primary_reducer> <valid_reducers>mean, min, max, median, distribution</valid_reducers> <excluded_reducers>sum (summing percentages across entities is meaningless), product (not a ratio measure)</excluded_reducers> <average_semantics>arithmetic_mean</average_semantics> </reducers> <inner_outer_measure> <inner_measure_reducer>min</inner_measure_reducer> <outer_measure_reducer>max</outer_measure_reducer> </inner_outer_measure> <multiplicative_partner_derivable>false</multiplicative_partner_derivable> <reasoning> Table type is DIMENSION with no sequence axis, making multiplicative highly implausible. The column contains percentage values (0.00% to 1.49%) representing occupation proportions at entity level. These are intensive measures (proportions/shares) where summing across entities is meaningless—you cannot add "0.90% + 1.39%" to get a meaningful result. The appropriate aggregation is averaging to find typical occupation representation. This is a classic intensive_additive pattern: an absolute level measure (proportion) where mean is the natural rollup, not sum. </reasoning> <table_type_conflict>false</table_type_conflict> </result> ```