Evidence retrieval on tau-bench multi-burst-augmented cache
68Hit@2OSU-Mem + GF
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OSU-Mem + GFBudget=B=5122026.06 | 68 | 38.6 | |
| OSU-Mem (no novelty)Budget=B=5122026.06 | 68 | 38.6 | |
| OSU-MemBudget=B=5122026.06 | 67.6 | 38.4 | |
| Coverage-AwareBudget=B=5122026.06 | 67.3 | 36.6 | |
| Flat + MMRBudget=B=5122026.06 | 64.6 | 33.5 | |
| Flat VectorBudget=B=5122026.06 | 57.4 | 31.8 | |
| OSU-Mem (disjoint)Budget=B=5122026.06 | 52 | 28.8 | |
| OSU-Mem (sim only)Budget=B=5122026.06 | 46.6 | 24.3 | |
| Disjoint HierarchyBudget=B=5122026.06 | 46.5 | 27.1 | |
| OSU-MemBudget=B=2562026.06 | 43.5 | 24.1 | |
| OSU-Mem + GFBudget=B=2562026.06 | 43.5 | 24.1 | |
| OSU-Mem (no novelty)Budget=B=2562026.06 | 41.9 | 23.3 | |
| OSU-Mem (disjoint)Budget=B=2562026.06 | 38.7 | 20.9 | |
| Periodic SummaryBudget=B=5122026.06 | 34.7 | 21.9 | |
| Flat + MMRBudget=B=2562026.06 | 34.7 | 20.1 | |
| Coverage-AwareBudget=B=2562026.06 | 33.3 | 20.1 | |
| Flat VectorBudget=B=2562026.06 | 32.8 | 20.3 | |
| Tree AbstractionBudget=B=5122026.06 | 31.6 | 20.3 | |
| OSU-Mem (sim only)Budget=B=2562026.06 | 28.5 | 15.7 | |
| Disjoint HierarchyBudget=B=2562026.06 | 28.1 | 18 | |
| OSU-MemBudget=B=1282026.06 | 25 | 14.5 | |
| OSU-Mem + GFBudget=B=1282026.06 | 25 | 14.5 | |
| OSU-Mem (no novelty)Budget=B=1282026.06 | 25 | 14.5 | |
| Tree AbstractionBudget=B=2562026.06 | 19.3 | 13.3 | |
| Periodic SummaryBudget=B=2562026.06 | 18.8 | 12.7 | |
| Disjoint HierarchyBudget=B=1282026.06 | 18.1 | 12.3 | |
| Flat + MMRBudget=B=1282026.06 | 17.2 | 13.4 | |
| Coverage-AwareBudget=B=1282026.06 | 17.1 | 13.6 | |
| Budget-Trunc ReplayBudget=B=5122026.06 | 16.3 | 17.8 | |
| Sliding WindowBudget=B=5122026.06 | 16.1 | 17.7 | |
| OSU-Mem (disjoint)Budget=B=1282026.06 | 15 | 9.3 | |
| OSU-Mem (sim only)Budget=B=1282026.06 | 14.5 | 8.6 | |
| Flat VectorBudget=B=1282026.06 | 14.1 | 12.2 | |
| Tree AbstractionBudget=B=1282026.06 | 13 | 12.3 | |
| OSU-MemBudget=B=642026.06 | 12.5 | 8.5 | |
| OSU-Mem + GFBudget=B=642026.06 | 12.5 | 8.5 | |
| OSU-Mem (no novelty)Budget=B=642026.06 | 12.5 | 8.5 | |
| OSU-Mem (disjoint)Budget=B=642026.06 | 10.9 | 6.1 | |
| Disjoint HierarchyBudget=B=642026.06 | 9.9 | 8 | |
| Budget-Trunc ReplayBudget=B=2562026.06 | 8.1 | 9.1 | |
| Tree AbstractionBudget=B=642026.06 | 8.1 | 8.6 | |
| Sliding WindowBudget=B=2562026.06 | 7.9 | 9 | |
| OSU-Mem (sim only)Budget=B=642026.06 | 6.3 | 4.5 | |
| Flat VectorBudget=B=642026.06 | 5.1 | 7.6 | |
| Flat + MMRBudget=B=642026.06 | 3.7 | 7.9 | |
| Coverage-AwareBudget=B=642026.06 | 3.2 | 7.6 | |
| Periodic SummaryBudget=B=1282026.06 | 2.6 | 5.3 | |
| Budget-Trunc ReplayBudget=B=1282026.06 | 0.5 | 4.9 | |
| Budget-Trunc ReplayBudget=B=642026.06 | 0.3 | 3.5 | |
| Periodic SummaryBudget=B=642026.06 | 0.3 | 3.4 | |
| Sliding WindowBudget=B=642026.06 | 0 | 2.6 | |
| Sliding WindowBudget=B=1282026.06 | 0 | 4.4 |