BDS Pipeline Performance Notes
Observed behavior across indexing, extraction, QA, and entity-card generation workloads.
Coming soonBenchmark notes, retrieval findings, hardware experiments, pipeline behavior, and visual research updates.
Every signal, column, and concept these lab notes rely on — Channel, Similarity, the Result Critic, anchors, wikilink repair, the corpus-shape trap — defined once, in plain language. The posts link back to it.
Open the Glossary →Why “not in the corpus” is a useful finding, not a system failure.
Read →How a VIOSINT build moved from Hermes/Gemma4 to Claude Opus, why the pivot happened, and what agent orchestration judgment is worth.
Read →Observed behavior across indexing, extraction, QA, and entity-card generation workloads.
Coming soonWhy vector, BM25, and both signals need different interpretation rules.
Coming soon