Four test files and one node header carried no TRACES tag, so the
requirements they verify read as implemented-but-unverified. Tagging a
test is what distinguishes the two.
test_calibration.cpp is AR-023; its three [report] cases verify GR-003
and are tagged separately, since the report is fitted from the same
distributions but is its own requirement. test_similarity.cpp is the CI
half of AR-026 — equivalence against hand-computed dot products, where
throughput at scale is AR-027 and cannot run on this host.
test_face_tracker.cpp is AR-007 and AR-008.
Two headers described code that no longer exists. face_aligner_node.hpp
still documented the RANSAC fit AR-005 replaced with an Umeyama
least-squares fit over all five points — not merely out of date but the
opposite of what the file does, and it reads as a rationale for
discarding the landmarks AR-030 measures. test_face_tracker.cpp still
described the park/revive branch AR-008 deleted, and the raw-cosine
cut_revive_sim that guarded it, which AR-024 retired.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
TRACES: AR-005, AR-007, AR-008, AR-023, AR-026, AR-030 | GR-003 | SR-001, SR-002
GR-003 — the calibration fit already computed per-actor dedup counts, how many
actors are eligible for positive pairs, and a 200-bin histogram of the intra and
inter distributions, then discarded all of it to stderr. Nothing persisted, so
nobody could audit whether a gallery was any good.
The report is written alongside the gallery at build time. That is the right
moment: the matcher fits the same sigmoid at analysis time, but by then the
answer is per-run and nobody is looking, whereas build time is when a gallery's
quality is actually decided.
What it surfaces, in order of usefulness:
- actors with no usable image — a silent recall ceiling, since the pipeline can
never name them and nothing else says why
- actors below the positive-pair threshold — not broken, so nothing complains;
they just quietly weaken every threshold downstream
- near-duplicate references removed, per actor and total
- the fitted calibration AND the two distributions behind it
That last one is the point. Every threshold in the pipeline is expressed in the
probability space this sigmoid defines, so if the distributions overlap heavily
the calibration is weak and every downstream decision inherits it — while the
gallery still looks fine from the outside.
The gallery-derived prior, intra/(intra+inter), is computed and reported but the
shipped default of 0.5 is deliberately left alone. The spec records these as
disagreeing; now the real value is visible, so the decision can be made on
evidence rather than argument.
Three tests: a zero-image actor is visible in the report, an under-referenced
actor is counted, and the report round-trips through JSON.
Suite: 95 cases, 6142 assertions.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
TRACES: GR-003 | SR-001
GPU-free, model-free tests for the pure logic: gallery HDF5 save/load
round-trips (actors, embeddings, embedded calibration) and legacy JSON
read back-compat; the calibration sigmoid fit, boundary inversion, and the
in-memory hash-keyed cache reuse/staleness; TrackGallery's diversity-buffer
eviction, novelty/spread safety gates, and promotion; FaceTracker's IoU/
embedding association and cross-cut track revival; and the GEMM similarity
backend (forced to CPU so the suite runs without a GPU).
Verified: all 39 test cases / 1640 assertions pass (cmake -DSAE_BUILD_TESTS=ON).
dtourolleandClaude Opus 5