Research map / Multi-agent systems and games / Games and equilibria
Catch Me if I Can: Detecting Strategic Behaviour in Peer Assessment
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 |
|---|---|---|---|
| Add impartial rankings as supervision (ablation) | Strategic-behaviour detection test · Strategic-behaviour experiment, Round 1 | detection rate: 0.17 -> 0.61 | Helped |
| Add impartial rankings as supervision (ablation) | Strategic-behaviour detection test · Strategic-behaviour experiment, Round 2 | detection rate: 0.02 -> 0.57 | Helped |
| Add impartial rankings as supervision (ablation) | Strategic-behaviour detection test · Strategic-behaviour experiment, Round 3 | detection rate: 0.16 -> 0.87 | Helped |
| Add impartial rankings as supervision (ablation) | Strategic-behaviour detection test · Strategic-behaviour experiment, Round 4 | detection rate: 0.01 -> 1.00 | Helped |
| Add impartial rankings as supervision (ablation) | Strategic-behaviour detection test · Strategic-behaviour experiment, Round 5 | detection rate: 0.08 -> 0.09 | No clear effect |
| Use the Reverse manipulation strategy rather than truthful ranking (ablation) | A single strategic reviewer against truthful reviewers · Borda count simulation | expected gain in final-ranking positions | No clear effect |
| Use the Worse-to-Bottom manipulation strategy rather than truthful ranking (ablation) | A single strategic reviewer against truthful reviewers · Borda count simulation | expected gain in final-ranking positions | Hurt |
| Use Distance or See-Saw manipulation rather than truthful ranking (ablation) | A single strategic reviewer against truthful reviewers · Borda count simulation | expected gain in final-ranking positions | Helped |
| Use Better-to-Bottom or 2x-Distance manipulation rather than truthful ranking (ablation) | A single strategic reviewer against truthful reviewers · Borda count simulation | expected gain in final-ranking positions | Mixed |
| Add noise to impartial rankings (ablation) | Test with supervision · Semi-synthetic Distance-strategy simulations | detection power | Hurt |
| Add Gaussian noise to reviewers' perceived submission scores (ablation) | Strategic-behaviour detection test · Semi-synthetic simulations | detection power | Hurt |
Closest papers by meaning
- Optimal Spot-Checking for Improving Evaluation Accuracy of Peer Grading Systems (AAAI 2018 · similarity 0.85)
- Better Peer Grading through Bayesian Inference (AAAI 2023 · similarity 0.84)
- Strategic Hypothesis Testing (NeurIPS 2025 · similarity 0.83)
- Look-Ahead Reasoning on Learning Platforms (NeurIPS 2025 · similarity 0.82)
- Classification Under Strategic Self-Selection (ICML 2024 · similarity 0.82)
- Fast Peer Adaptation with Context-aware Exploration (ICML 2024 · similarity 0.82)
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.