ML reanalysis of historic plates confirms transients cluster within 24h of nuclear tests
coherence · x · 2026-10-13
A peer-reviewed Scientific Reports paper by Villarroel et al. uses machine learning to validate mysterious star-like transients on pre-Sputnik photographic plates. Trained on 250 expert-labeled image pairs (AUC=0.81, sensitivity/specificity=0.71), the model scored 107,875 transients. After controlling for plate defects, transient counts stay significantly elevated within ±1 day of nuclear tests (p=0.024; p<0.0001 for highest-probability transients), peaking 24 hours before a test, and the Earth's-shadow deficit remains significant (p<0.001), strengthening as contamination drops—supporting an unrecognized transient population.
More from Research
- Hugging Face researcher admits the decision index now faces MTEB's leaderboard-gaming problem — antoine_chaffin · 2026-10-13
- Researchers release research blog post months in the making — logangraham · 2026-10-13
- Decision Index is facing MTEB's benchmark-gaming problem, its author says — antoine_chaffin · 2026-10-13
- NeurIPS position paper warns generative molecular dynamics evaluation is misleading the field — FrankNoeBerlin · 2026-10-13
- Live talk: MinerU-Popo paper on fixing OCR's cross-page context failures — HamelHusain · 2026-10-13
- OpenAI math repo's 'exact complex arithmetic' claim draws fire over arbitrary-precision assumption — jessi_cata · 2026-10-13