Nishi Family › Compare › Frontier Radar

Frontier Radar — Evaluation and Grading (Referee)

Where the 2025/26 research frontier is moving, and where Nishi should test, deepen, or research next.

How this works. The nishi researcher banked the current (2024-2026) frontier for this domain over sovereign TLS (keyless OpenAlex/arXiv). For each capability axis this radar measures frontier momentum = how often the frontier corpus mentions it, times our organ presence (probed on disk). Absent + hot = a research opportunity / where to test. Corpus measured: 2347521 bytes. Generated by nx_swcompare_gapmap over a data-only domain spec (referee.q + referee.axes) — zero domain-specific code.
Top research opportunities (the 2025/26 frontier is active here and Nishi has no organ yet):
Capability axisNishi organFrontier momentum (2025/26)Signal
QA benchmark harnesspresent
53 mentions		COVERED
Anti-drift claim coachingpresent
46 mentions		COVERED
Multi-profile quality gradingpresent
46 mentions		COVERED
Contamination detectionabsent
20 mentions		OPPORTUNITY
Human-preference evaluationabsent
17 mentions		OPPORTUNITY
LLM-as-judge evaluationabsent
3 mentions		OPPORTUNITY
Liar-killed census generationpresent
3 mentions		COVERED
Regression tracking over timeabsent
1 mentions		OPPORTUNITY
Property-based independent oraclespresent
0 mentions		COVERED
Statistical rigor (CIs, variance)absent
0 mentions		dormant
Safety-critical gradingpresent
0 mentions		COVERED
Honesty and overclaim gradingpresent
0 mentions		COVERED

Opportunities 4 · covered 7 · dormant 1

frontier momentum is a mechanical keyword count over real 2024-2026 works; our presence is probed on disk. A discovery signal, not a ranking of importance. Zero JS, zero trackers.