code wiki / _hdl_build / nx_examiner.nx
nx_examiner.nx
buildroot/runtime/_hdl_build/nx_examiner.nx
about
nx_examiner.nx -- the EXAMINER organ (operator: the team must PERFORM its own evaluation; put the
grading capabilities with the team member that owns this, or create that member -- created). The
Examiner is the team's assessor: it OWNS and RUNS the grading the team needs, so the team grades
ITSELF instead of Claude doing it by hand. Three jobs, one organ (single responsibility):
1. grade a CAPABILITY for S-class exceed (the S-class grader, skeptical + triangulated).
2. grade a NEW measured RESULT -- did it beat the naive baseline, and did it beat SOTA?
3. grade the TEAMMATES (the scorecard) -> the next growth target + whether the team passes.
RACI partnership: the EXAMINER benchmarks/grades performance; the CRITIC judges belief-truth
(counter-theory, provisionality); the BUILDER builds what the Examiner finds weakest/below-S; the
growth loop consumes the Examiner's verdicts. The Examiner never builds or fixes -- it measures.
license_tier: ORIGINAL Refs: separation of judging (Critic=truth) from grading (Examiner=performance).
dependencies 2 imports · 2 importers
imports: nx_sclass_grader.nxnx_team_scorecard.nx
imported by: nx_andelinwest_crew.nxnx_examiner_test.nx
structs
| none |
consts
| none |
functions
| 17 | func exam_grade_capability(has_ext: i64, verified: i64, beats: i64, triangulated: i64, matches: i64) -> i64 |
| 24 | func exam_grade_result(metric_new: i64, metric_baseline: i64, metric_sota: i64) -> i64 |
| 32 | func exam_next_growth(n: i64, scores: *i64, leverage: *i64) -> i64 { return tsc_growth_target(n, scores, leverage, TSC_BENCHMARK) } |
| 33 | func exam_team_passes(n: i64, scores: *i64) -> i64 { return tsc_all_pass(n, scores, TSC_BENCHMARK) } |
| 36 | func exam_sclass_count(n: i64, grades: *i64) -> i64 { return sg_count(n, grades, SG_S_EXCEED) } |