Oakley Square Wire

eye 60 · model_key SQUARE WIRE · bridge 17

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 01:56:42 UTC	4	0.8465	0ae11f5b9224	SQUARE_WIRE 60-17.8.DAT	angles-reorderedmixed-object-types	2
2026-08-12 21:57:16 UTC	4	0.8465	0ae11f5b9224	SQUARE_WIRE 60-17.8.DAT	angles-reorderedmixed-object-types	2
2026-08-12 14:32:02 UTC	4	0.8465	0ae11f5b9224	SQUARE_WIRE-60.oma	angles-reorderedmixed-object-types	2
2026-08-12 01:06:53 UTC	4	0.8465	0ae11f5b9224	SQUARE_WIRE-60.oma	angles-reorderedmixed-object-types	2

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 (4 datasets)

capture 298 · R
capture 298 · L
capture 309 · R
capture 309 · 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 298 · R

capture 298 · L

capture 309 · R

capture 309 · 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-reorderedmixed-object-types

capture_count: 2
n_traces: 4
n_captures (stats): 2
radial RMS (mm): 0.2886
radial max (mm): 0.8465
max-dev angle (deg): 147.6000
circumference stdev (mm): 0.3039
L/R asymmetry (mm): 0.1087
HBOX stdev (mm): 0.0150
VBOX stdev (mm): 0.1050
DBL stdev (mm): 0.7000
low_n: yes
stats computed_at: Aug 13, 2026, 01:56 AM UTC

Catalog match

method: brand-model-size
confidence: 90%
rxoffice_tracedata_id: 36841
flags: no-code-token

Captures (2)

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

id	capture_time	residual (mm)	flags	excluded
309	Apr 14, 2026, 09:19 PM UTC	0.2781	parsenone resolution model-from-filename alignmentnone	—
298	Apr 14, 2026, 09:19 PM UTC	0.2889	parsenone 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.