FINDING #6680 · UNIT ID 1057515940
KEV0143/Comparative-analysis-of-hourly-load-forecasting-using-PatchTST-TFT-NHiTS-and-CatBoost
A comprehensive time-series benchmark evaluating state-of-the-art deep learning architectures (PatchTST, TFT, N-HiTS) against traditional gradient boosting (CatBoost) for accurate 24-hour load prediction.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
56% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S5 · PREDATES WINDOW, YET HALF+ OF ALL ITS STARS LANDED IN IT
Growth Telemetry
VELOCITY /D
4.42
ACCEL
+0.03
RETENTION
24.3%
PEAK 2026-05-09 · FORK-RETENTION 0.0% · 795 STARS / WINDOW
Author Audience
AUDIENCE
3,956
FOLLOWERS
2,250
OWNER ★
17,060
Engagement Signals
FORKS
0
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 795 / 795 (DIVERSITY 1.00)
Why This Is A Finding
KEV0143/Comparative-analysis-of-hourly-load-forecasting-using-PatchTST-TFT-NHiTS-and-CatBoost собрал 795 звёзд за окно, тогда как у автора всего 2,250 подписчиков — эффективная аудитория ≈ 3,956. Это даёт surprise-индекс 0.00111 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.
Related Findings
RANKS ABOVE 0% OF 6691 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 6691 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 0%
VELOCITY4.423.19+1.22ABOVE 63%
RETENTION24.3%10.5%+13.8 PPABOVE 82%
FORKS095-95ABOVE 0%
SURPRISE0.000.01-0.01ABOVE 17%