Index
Grant: Mitigating Reward Hacking Through RL Training Interventions (Manifund → Aria Wong)
Verdictconfirmed95%
1 check · 7/20/20261 → confirmed
Our claim
entire record- Name
- Mitigating Reward Hacking Through RL Training Interventions
- Amount
- $7,900
- Currency
- USD
- Date
- February 18, 2026
- Notes
- Technical AI safety
Source evidence
1 src · 1 checkconfirmed95%deterministic-row-match · 7/20/2026
- Name
- Mitigating Reward Hacking Through RL Training Interventions
- Slug
- mitigating-reward-hacking-through-rl-training-interventions
- Date
- 2026-02-18T19:10:34.473Z
- Amount
- 7,900
NoteDeterministic match: name, amount matched in source snapshot (20000 rows)
Case № bs34HNgJhuFiled 7/20/2026Confidence 95%