1Cademy - Token-Cap Comparison on LectureBank-Full: Adaptive Loses More as Cap Tightens

Learn Before

Example

Token-Cap Comparison on LectureBank-Full: Adaptive Loses More as Cap Tightens

Under a controlled token-cap protocol where both Adaptive + token-aware and Hierarchical + token-aware are reranked with the same token-aware serialization policy, the paired-bootstrap delta $\Delta\text{R@}10 =$ Adaptive − Hierarchical on LectureBank-Full ( $n = 143$ ) is negative and grows more negative as the cap is relaxed: $-0.9$ $[-2.4, +0.3]$ at a 256-token cap ( $p = 0.191$ ), $-1.7$ $[-3.6, -0.1]$ at 512 tokens ( $p = 0.045$ ), and $-3.4$ $[-6.2, -0.5]$ at 768 tokens ( $p = 0.025$ ). At the strictest 256-token cap the two systems are not individually distinguishable under the descriptive paired bootstrap; the individually significant negative deltas appear at the looser 512 and 768 caps. The reported $p$ -values are descriptive paired-bootstrap tail probabilities and are not adjusted across token caps, so the trend is directional rather than a multiplicity-corrected significance result.

Updated 2026-05-17

Contributors are:

Who are from:

References

Reference: Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls

Learn Before

Related