Error Attribution on MATH
62Removal RateVanilla
Evaluation Results
| Method | Links | |
|---|---|---|
| VanillaScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=MACNET2026.05 | 62 | |
| VanillaScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=DyLAN2026.05 | 33 | |
| CRSVPScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=DyLAN2026.05 | 32 | |
| CRSVPScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 30 | |
| CRSVPScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=MACNET2026.05 | 30 | |
| Two-WayScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 29 | |
| Two-WayScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=DyLAN2026.05 | 29 | |
| Right FilteringScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 28 | |
| Right FilteringScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 27 | |
| Two-WayScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 27 | |
| CRSVPScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 27 | |
| Right FilteringScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=DyLAN2026.05 | 27 | |
| VanillaScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 24 | |
| CRSVPScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 22 | |
| VanillaScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 20 | |
| CRSVPScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 20 | |
| Right FilteringScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 20 | |
| Right FilteringScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=MACNET2026.05 | 20 | |
| VanillaScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 19 | |
| Left FilteringScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 19 | |
| VanillaScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 19 | |
| Left FilteringScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 19 | |
| Left FilteringScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 19 | |
| Right FilteringScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 19 | |
| Left FilteringScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=MACNET2026.05 | 19 | |
| Two-WayScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=MACNET2026.05 | 19 | |
| Left FilteringScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=DyLAN2026.05 | 18 | |
| Two-WayScoring Function Type=Role-prompted, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 18 | |
| Left FilteringScoring Function Type=Fine-tuned, Backbone=Qwen3-1.7B, Agentic Framework=DyLAN2026.05 | 18 | |
| Two-WayScoring Function Type=Naive LLM, Backbone=gpt-4o-mini, Agentic Framework=MACNET2026.05 | 15 |