Oakley Holbrook

eye 56 · model_key HOLBROOK · bridge 19

Generations (4)

Keyed by (brand, model_key, eye_size), not this frame’s numeric id -- a `resolve_all` recompute can recreate the frame row and null out a generation’s `frame_id` pointer, but its natural-key identity (and so its attribution here) survives. The same `geometry_digest` across two rows means the same shape was regenerated, not that anything actually changed.

created_at (UTC)	n	stdev_max (mm)	geometry_digest	output	flags	captures
2026-08-13 01:56:38 UTC	7	0.2179	0b489daa3c02	HOLBROOK 56-18.3.DAT	angles-reorderedsurplus-angles-truncated	4
2026-08-12 21:57:15 UTC	7	0.2179	0b489daa3c02	HOLBROOK 56-18.3.DAT	angles-reorderedsurplus-angles-truncated	4
2026-08-12 14:32:00 UTC	7	0.2179	0b489daa3c02	HOLBROOK-56.oma	angles-reorderedsurplus-angles-truncated	4
2026-08-12 01:06:42 UTC	7	0.2179	0b489daa3c02	HOLBROOK-56.oma	angles-reorderedsurplus-angles-truncated	4

Canonical mean ± deviation

Solid line: mean shape. Shaded bands: +/-1sigma (dark) and +/-2sigma (light) from frame_stats.profile_mm. Outer ring: deviation heat map, calm-to-hot, bucketed at 3.60° -- reflects the frame's latest generation only.

Ensemble overlay (7 datasets)

capture 290 · R
capture 1269 · R
capture 1269 · L
capture 1344 · R
capture 1344 · L
capture 1345 · R
capture 1345 · L

Display registration only: each trace is independently re-centered on its own bounding box and left eyes are mirrored to right orientation for visual comparison -- this is not the pipeline's own registration.register() output and performs no rotation alignment or resampling.

Per-capture traces

As captured (L eyes unmirrored) -- unlike the ensemble overlay above, which always mirrors a left eye into right-eye orientation for comparison (F7).

capture 290 · R

capture 1269 · R

capture 1269 · L

capture 1344 · R

capture 1344 · L

capture 1345 · R

capture 1345 · L

Stats

Shape-level flags (has-excluded-captures, no-bridge, high-divergence-ensemble, ...) live on a generation, not on the frame itself -- shown below as the LATEST generation’s flags, not this frame’s own.

latest generation flags:angles-reorderedsurplus-angles-truncated

capture_count: 4
n_traces: 7
n_captures (stats): 4
radial RMS (mm): 0.1295
radial max (mm): 0.2179
max-dev angle (deg): 255.2400
circumference stdev (mm): 0.1659
L/R asymmetry (mm): 0.0628
HBOX stdev (mm): 0.1458
VBOX stdev (mm): 0.3612
DBL stdev (mm): 0.8374
low_n: no
stats computed_at: Aug 13, 2026, 01:56 AM UTC

Catalog match

method: brand-model-size
confidence: 90%
rxoffice_tracedata_id: 35111
flags: no-code-token

Captures (4)

Exclusion decisions are CLI-only (human-only doctrine).

id	capture_time	residual (mm)	flags	excluded
1344	Jul 27, 2026, 07:05 PM UTC	0.0996	parse angle-count-inconsistent resolutionnone alignmentnone	—
1345	Jul 14, 2026, 06:38 PM UTC	0.1991	parse angle-count-inconsistent resolutionnone alignmentnone	—
1269	May 19, 2026, 07:44 PM UTC	0.0749	parse angle-count-inconsistent resolutionnone alignmentnone	—
290	Apr 14, 2026, 09:19 PM UTC	0.0749	parse angle-count-inconsistent resolutionnone alignmentnone	—

Reviews (0)

Advisory only (DECISIONS #55) -- a score never changes whether a capture is averaged; that stays a human CLI decision. Reviews attach to a specific capture, not the frame itself -- open a capture above to add one.

No reviews yet.