labmlai/annotated_deep_learning_paper_implementations — GitHub trend

FINDING #2738 · UNIT ID 290091948

labmlai/annotated_deep_learning_paper_implementations

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

[ PYTHON ][ ORG ][ VERIFIED ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0000545

ENGAGEMENT0.44

FRESHNESS1.16

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

2.21

ACCEL

-0.03

RETENTION

10.2%

PEAK 2026-03-14 · FORK-RETENTION 43.4% · 398 STARS / WINDOW

Author Audience

AUDIENCE

40,536

FOLLOWERS

2,837

OWNER ★

70,736

Engagement Signals

FORKS

6,738

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 397 / 398 (DIVERSITY 1.00)

Why This Is A Finding

labmlai/annotated_deep_learning_paper_implementations собрал 398 звёзд за окно, тогда как у автора всего 2,837 подписчиков — эффективная аудитория ≈ 40,536. Это даёт surprise-индекс 0.0000545 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 43.4% и 2 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 8% OF 2987 FINDINGS

#03originalankur/maptoposter[ PYTHON ]0.0234 #05HeartMuLa/heartlib[ PYTHON ]0.0222 #08sickn33/agentic-awesome-skills[ PYTHON ]0.0207 #14cft0808/edict[ PYTHON ]0.0183 #17aden-hive/hive[ PYTHON ]0.0175

METRICS IN CONTEXT

MEDIAN ACROSS ALL 2987 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 8%

VELOCITY2.212.84-0.63ABOVE 33%

RETENTION10.2%6.8%+3.3 PPABOVE 65%

FORKS6,7381,068+5,670ABOVE 88%

SURPRISE0.000.00-0.00ABOVE 10%