manycore-research/SpatialLM — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #1489 · UNIT ID 948245457

manycore-research/SpatialLM

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0195

ENGAGEMENT0.35

FRESHNESS1.00

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

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

5% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

38.00

ACCEL

-26.64

RETENTION

0.9%

PEAK 2026-10-11 · FORK-RETENTION 20.0% · 266 STARS / WINDOW

Author Audience

AUDIENCE

1,906

FOLLOWERS

333

OWNER ★

6,202

Engagement Signals

FORKS

437

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 266 / 266 (DIVERSITY 1.00)

Why This Is A Finding

manycore-research/SpatialLM собрал 266 звёзд за окно, тогда как у автора всего 333 подписчиков — эффективная аудитория ≈ 1,906. Это даёт surprise-индекс 0.0195 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 20.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 85% OF 9651 FINDINGS

#02Oldcircle/geo-sleuth[ PYTHON ]0.78 #05Arekejoker/qwen21-nsfw-pose-skill[ PYTHON ]0.64 #31ardeyouxipianyi/workbuddy2api-hub[ PYTHON ]0.35 #38AsherJN/recall[ PYTHON ]0.31 #40MerZlin/dsh-pet-indesktop[ PYTHON ]0.30

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9651 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.01ABOVE 85%

VELOCITY38.003.14+34.86ABOVE 95%

RETENTION0.9%16.7%-15.8 PPABOVE 15%

FORKS437277+160ABOVE 59%

SURPRISE0.020.00+0.02ABOVE 80%