FINDING #6136 · UNIT ID 1322509558
AMAP-ML/LongHorizon-Harness
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
4% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
10.00
ACCEL
+0.25
RETENTION
42.6%
PEAK 2026-10-09 · FORK-RETENTION 0.0% · 70 STARS / WINDOW
Author Audience
AUDIENCE
3,070
FOLLOWERS
383
OWNER ★
11,518
Engagement Signals
FORKS
188
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 70 / 70 (DIVERSITY 1.00)
Why This Is A Finding
AMAP-ML/LongHorizon-Harness собрал 70 звёзд за окно, тогда как у автора всего 383 подписчиков — эффективная аудитория ≈ 3,070. Это даёт surprise-индекс 0.00322 (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 37% OF 9747 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9747 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 37%
VELOCITY10.003.57+6.43ABOVE 78%
RETENTION42.6%33.3%+9.3 PPABOVE 63%
FORKS188104+84ABOVE 64%
SURPRISE0.000.01-0.01ABOVE 27%