Python · Apache-2.0
cpt13-g/build-research-evidence
面向 AI/CS 科研的多 Skill 实验智能体：助力全自动科研实验，以 Claim 驱动、骨干实验优先、独立结果审计与 Evidence Freeze，把发散的模型能力收束为可追溯、可复现、可收敛的论文证据。
★ 46
Stars
2 forks · 0 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
18.6
Momentum / 100
see the breakdown below
55d ago
Created
last push 18d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 13.7 | last push 18d ago; decays to zero at 180 days |
| Scale | 15 | 4.9 | 46 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 18.6 | capped at 35 because growth is unmeasured |
Detail
| Topics | agentic-aiai-researchautomated-experimentscodex-skillsevidence-drivenmachine-learningreproducible-researchresearch-agent |
| Matched on | AI Agents (agentic-ai) |
| Short window | +0 stars over 9 days = 0.0/day |
| Long window | +5 stars over 19 days = 0.3/day |
| Lifetime average | 0.87 stars/day over 53 days |
| First seen here | 2026-10-17 |
| Last read | 12d ago |