Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optim
Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion, limiting its effectiveness as a correctness signal. We pro
https://arxiv.org/abs/2607.14614v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
None
How close the company’s idea is to your thesis statement
Sector
ai
Overlap with sectors you care about
Geography
Outside
Outside your target regions — scores 0
Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”
Founder → stable
Traction → stable
Idea vs market ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
W
Weiwen Xu
3.2
low confidence
J
Jia Liu
2.0
low confidence
Hou Pong Chan
HK
2.0
low confidence
L
Long Li
2.0
low confidence
D
Deng Cai
2.0
low confidence
M
Min Chen
2.0
low confidence
H
Hao Zhang
2.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Unsloth AI
· Active
Open-Source Reinforcement Learning (RL) & Fine-tuning for LLMs.
founders not scraped yet