Files
aimsight-labeling/auto/analyses/long-labels/NIEDERHORN/report.md
T
maximeandClaude Opus 5.5 ddb17c2189 auto: labels requalified under the 5-noise rules (only what stands out from the noise): 32 analyses refined, the 6 paused periods verified, the long labels requalified with the fixes the period analysts found; 1153 -> 961 labels
- 32 analyses: each label kept, rewritten or removed by its analyst (section Requalification of the report; mm magnitudes where the targets have them)
- SNCF01 x3, WILDSTRUBEL 2026-09-01 -> 2026-10-06 x3: verified from their existing labels under the new rules
- long labels (no analysis): auto/analyses/long-labels/<STATION>/; NORDEND-169 and -195 run to 07/11, so NORDEND-283 and -284 (their continuation) are removed
- reading-rules.md, stations.md: the citations of removed or rewritten labels point to their successor, or to [expert]

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-17 23:58:00 +01:00

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.