Files
aimsight-labeling/auto/analyses/NIEDERHORN_2026-10-01T0000_2026-11-01T0000/report.md
T

1.5 KiB
Raw Blame History

NIEDERHORN long labels: requalification

12 labels: 7 kept as is, 0 corrected, 5 removed.

Kept: NIEDERHORN-2 to -8. The targets e03, e04, e05, e07, e08, e11 and e12 are rejected at 718 to 721 of the 721 measurements of the month: almost always, a true Target issue. They have no curve, so no magnitude in mm.

Removed: these five targets are rejected only part of the time. None of them is a reference, so their rejections do not move the other targets. Their accepted points leave the noise no more than those of the healthy targets: these moments are the daily thermal cycles and the shared single measurements, which already have their own labels.

  • NIEDERHORN-9 (PWD_RMP_B15_017_C09): rejected at night, 42 % of the month. Its "scattered" afternoon points after 28.10 (about +2.5 mm vertically) follow the thermal cycle, like its neighbours.
  • NIEDERHORN-10 (e01): rejected by day, 36 %. Its afternoon rise and its peak of 06.10 (+1 px; e01 has no mm conversion) are shared with e02 and e06.
  • NIEDERHORN-11 (PWD_IMP_B08_024_C09): rejected by day, 21 %. Its largest swings (−3.7 mm horizontally, −9.5 mm vertically) fall on instants where the healthy targets move by 5 to 11 mm.
  • NIEDERHORN-70 (PWD_RMP_B12_019_C09): rejected at night, 36 % from 15.10. Its largest point (+7.3 mm vertically, 20.10 12:00) is the shared obstruction NIEDERHORN-93, already labelled.
  • NIEDERHORN-79 (PWD_IMP_B07_018_C09): rejected at night, 32 % from 17.10. Its swings (up to −3.7 mm horizontally) match its healthy neighbour PWD_IMP_B07_017_C09.