func TestRetrievalRecallGate(t *testing.T)

gh-eq-7c47795b5cf0ee3esource-comment-equation

meanRecall@10 >= 0.8: a healthy search recalls nearly every relevant id within the top ten of a twelve

Read the equation

This relation defines meanRecall@10 >= 0.8: a healthy search recalls nearly every relevant id within the top ten in the source section “func TestRetrievalRecallGate(t *testing.T)”. It specifies the displayed relationship between the named quantities or parameters. Its interpretation depends on the source’s stated variables and conditions; this record does not assign an unprovided physical or cognitive meaning to them.

Terms & definitions

The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.

How it works

Read meanRecall@10 >= 0.8: a healthy search recalls nearly every relevant id within the top ten as the quantity being defined or updated by this relation.
Substitute the source-defined variables or recorded values and follow the displayed arithmetic and indexing exactly.
Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.

Assumptions & limits

This source expression was recovered from the pinned code revision. Its presence does not establish that the associated program was built, run, or scientifically validated.

Original context

Read the surrounding source passage

	// Floors. Each gold query's relevant candidates are lexically present AND semantically near the query, and
	// the org holds only twelve candidates, so a correct hybrid search ranks the relevant ones at or near the
	// top and recall at ten is essentially complete. The floors sit well below the expected healthy values so
	// a passing run is unambiguous, while a real regression (embeddings drift, HNSW ef_search cut, a broken
	// mission gate, or an RRF k constant change that scrambles the fusion) drops a metric below its floor.
	//
	// meanRecall@10 >= 0.8: a healthy search recalls nearly every relevant id within the top ten of a twelve
	// candidate pool, so 0.8 is a conservative floor that a correct search clears comfortably and a recall
	// regression breaks.
	if meanRecall10 < 0.8 {
		t.Fatalf("REGRESSION: mean recall@10 = %.3f is below the 0.8 floor; the hybrid search is no longer recalling the relevant candidates", meanRecall10)
	}
	// meanMRR >= 0.5: a healthy search puts a relevant candidate in the top two on average (rank one is 1.0,
	// rank two is 0.5), so 0.5 is a conservative floor on first relevant rank that a ranking regression breaks.
	if meanMRR < 0.5 {
		t.Fatalf("REGRESSION: mean MRR = %.3f is below the 0.5 floor; the first relevant candidate is ranking too deep", meanMRR)
	}

Exact original notation

meanRecall@10 >= 0.8: a healthy search recalls nearly every relevant id within the top ten of a twelve