A multi-tier weak-supervision cascade on 232M TLE records creates 8.6M labeled sequences, enabling a 6.5M-parameter Transformer to reach 55% maneuver recall and 63% decay recall on held-out data for orbital anomaly triage.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Tier Labeling and Physics-Informed Learning for Orbital Anomaly Detection at Scale
A multi-tier weak-supervision cascade on 232M TLE records creates 8.6M labeled sequences, enabling a 6.5M-parameter Transformer to reach 55% maneuver recall and 63% decay recall on held-out data for orbital anomaly triage.