Research map / Reinforcement learning / Policy gradient and actor-critic
Counterfactual Evaluation of Peer-Review Assignment Policies
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Increase text-similarity weight from the bid-focused range to 0.75–0.9 | TPDP assignment policy · TPDP | reviewer-reported expertise | Helped |
| Increase text-similarity weight to 0.9–1 | TPDP assignment policy · TPDP | reviewer-reported expertise | Mixed |
| Use randomized rather than deterministic assignment | TPDP assignment policy · TPDP | reviewer-reported expertise | No clear effect |
| Set text-similarity weight to 0.5 or lower rather than the on-policy value | AAAI assignment policy · AAAI | reviewer-reported expertise | Hurt |
| Increase positive-bid weight to at least the on-policy value | AAAI assignment policy · AAAI | reviewer-reported expertise | Helped |
| Increase q to 0.6 or higher, reducing assignment randomness | AAAI assignment policy · AAAI | reviewer-reported expertise | Helped |
| Optimize assignment to minimize rather than maximize total similarity | TPDP and AAAI assignment policies · TPDP and AAAI | reviewer-reported expertise | Hurt |
| Use monotonicity or Lipschitz constraints to bound unobserved review outcomes | Off-policy evaluation · TPDP and AAAI | bound informativeness | Helped |
Closest papers by meaning
- Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments (NeurIPS 2020 · similarity 0.90)
- A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding (NeurIPS 2025 · similarity 0.86)
- From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review (NeurIPS 2025 · similarity 0.85)
- Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards (ICML 2025 · similarity 0.84)
- Are Key-Phrases All That Reviewers Care About? A Comprehensive Benchmarking of Reviewer Matchmaking Systems (AAAI 2025 · similarity 0.83)
- Eliciting Honest Information from Authors Using Sequential Review (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.