Noru FlowResearch
Navigation menu
All researchEvidence

What 7 of 8 does and does not mean

On one locked synthetic fixture, Noru's selector surfaced relevant prior evidence for 7 of 8 answerable queries and abstained on 2 of 2 no-answer queries. We did not test agent task outcomes.

On this page
  1. What we ran
  2. What failed
  3. What we did not run
  4. The supported conclusion
Locked synthetic fixture: relevant evidence in the top three for 7 of 8 answerable cases, not agent task completion or a generalized product success rate. Precision and future-candidate counts shown are after the temporal fix.

A promising number is most useful when its boundary stays attached.

We evaluated Noru's contextual-recall selector on a fixed synthetic corpus. The purpose was to test a mechanism: can the selector surface labelled prior evidence without filling the agent's context with an unlimited history dump?

It was not a test of whether an agent completed more work.

What we ran

The fixture contained 10 unique retrieval cases and 32 synthetic capture bundles. Eight queries had relevant prior evidence. Two no-answer queries were designed to test abstention. Five repeated selector passes produced 50 case-runs for local latency and determinism checks; those repeats were not treated as independent evidence.

MeasureResult
Relevant evidence in the top three, answerable cases7 / 8
Correct no-answer abstentions2 / 2
Returned-candidate precision after the temporal fix9 / 12
Future candidates after the temporal fix0 / 12

The fixture was synthetic. The embedding configuration was deterministic. The sample was small. Those facts are part of the result, not footnotes to remove when the number becomes a headline.

What failed

The missed answerable case relied on weak OCR and visual similarity. The implemented selector uses visual distance to reorder candidates admitted through text; it does not yet provide an independent visual candidate path. That limitation explains the miss and defines a concrete next experiment.

The initial run also returned one future-timestamped candidate at rank one. We added a strict query-time cutoff and reran the same locked fixture. Future candidates fell from one to zero, Hit@3 remained 7 of 8, and correct abstentions remained 2 of 2. Because the fixture had already been seen, this is regression evidence for the fix, not independent confirmation.

What we did not run

We planned paired agent runs across current perception, manual history retrieval, and automatic hints. Zero paired agent runs were executed. The safe isolation path needed to combine fresh observation with an ephemeral synthetic history corpus was not yet qualified, and weakening the production guard would have made the comparison less trustworthy.

So the public decision remains simple: do not claim that Noru improves agent task performance from this evaluation. We measured whether a selector found labelled items in one controlled fixture. We did not measure completed tasks, intervention rates, or improvement across clients and models.

The supported conclusion

On this locked synthetic fixture, Noru's selector returned relevant prior evidence among at most three candidates for 7 of 8 answerable queries and correctly abstained on 2 of 2 no-answer queries. After the temporal cutoff, it returned zero future candidates in the same fixture.

A result becomes more credible, not less ambitious, when it says exactly what was measured and stops there.

macOS 13+ · Apple Silicon

Noru for Mac.

Download free

v0.3.1 · Signed & notarized by Apple

Installation guide