Knowledge base›Sources›Metehan Yesilyurt
A model of result fusion as RRF with derived rules ("2x top-40 or 3x top-90").
The fusion is not observable; the hit counts are markedly lower for us. The RRF thesis is cited in the field (Peec) but remains a hypothesis.
| Claim | Status | Evidence |
|---|---|---|
| ChatGPT fuses fan-out results by Reciprocal Rank Fusion, k=60, threshold tau>=0.020 | unverifiable | Server-side. refs.ranking_score_present is false for us; no scores in the object. |
| ChatGPT retrieves 38-65 sources per answer | outdated | 14-22 URLs per searching question in the standard mode for us. |