Model techniques map
Techniques

implementation detail · not yet filed

Blockwise candidate-pool selection for sparse indexing

Also called blockwise candidate selection.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

It also performs blockwise candidate selection: each block is assigned the maximum index score among its positions, and the blocks with the highest scores are selected.

coreunclearin DeepSeek-V4.1-FlashDeepSeek