← back

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.

Edit thesis
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
Generate memo
Add / edit details

Correct facts used on the next screening or memo.

Similar baseline plays (YC · idea space)

TrainLoop · Active
Reasoning Fine-Tuning
founders not scraped yet
Unsloth AI · Active
Open-Source Reinforcement Learning (RL) & Fine-tuning for LLMs.
founders not scraped yet
Nuntius · Inactive
Making Models Follow Rules.
founders not scraped yet
RunRL · Active
Reinforcement learning as a service
founders not scraped yet
Osmosis · Active
Reinforcement Learning (RL) for AI Agents
founders not scraped yet