# Candidate-depth-aware hybrid rank fusion > Source-anchored research for Candidate-depth-aware hybrid rank fusion. Run status: BUDGET_EXHAUSTED. Parent: [Concept knowledge architecture strategies](https://llms-explorer.com/tree/concept-knowledge-architecture-strategies/) · 3 facets · 21 facts · page: https://llms-explorer.com/tree/candidate-depth-aware-hybrid-rank-fusion/ ## Measurements and reference values - OpenSearch's six-dataset comparison reported RRF nDCG@10 averaging 3.86% below its score-based hybrid comparator. (low confidence) — [source](https://opensearch.org/blog/introducing-reciprocal-rank-fusion-hybrid-search/) ## Comparisons and alternatives - The RRF rank constant differs from a nearest-neighbor count or a candidate-depth limit. (low confidence) — [source](https://learn.microsoft.com/azure/search/hybrid-search-ranking) ## Facts and statements - RRF adds reciprocal rank contributions from the input rankings; raw score magnitudes do not enter its formula. (high confidence) — [source](https://cormack.uwaterloo.ca/cormacksigir09-rrf.pdf) - In truncated-list RRF, an item absent from one input list contributes zero from that list. (low confidence) — [source](https://www.elastic.co/search-labs/blog/improving-information-retrieval-elastic-stack-hybrid) - Cormack et al. fixed k=60 during a pilot and retained it during later validation. (low confidence) — [source](https://cormack.uwaterloo.ca/cormacksigir09-rrf.pdf) - Elastic's 2023 BEIR subset experiment favored k=20 and candidate depth 1000 for the tested dense retrievers. (low confidence) — [source](https://www.elastic.co/search-labs/blog/improving-information-retrieval-elastic-stack-hybrid) - Bruch et al. found tuned convex score combination superior to RRF in their in-domain and out-of-domain experiments. (low confidence) — [source](https://arxiv.org/html/2210.11934v2) - Elasticsearch separates the per-retriever rank window from the final response size. (low confidence) (verified as of 2026-10-22) — [source](https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion) - Bruch et al.'s min-max normalization uses the minimum and maximum scores in the retrieved candidate union. (low confidence) — [source](https://arxiv.org/html/2210.11934v2) - Bruch et al. compute missing candidate scores and approximate otherwise unknown ranks within the candidate union. (low confidence) — [source](https://arxiv.org/html/2210.11934v2) - Increasing the RRF rank constant flattens relative differences between high and low ranks. (low confidence) — [source](https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion) - Bruch et al. exclude near-zero score variance from their empirical normalization analysis and identify it as a challenge for some normalizers. (low confidence) — [source](https://arxiv.org/html/2210.11934v2) - The original RRF definition models each input ranking as a permutation, with one rank per document. (low confidence) — [source](https://cormack.uwaterloo.ca/cormacksigir09-rrf.pdf) - The original RRF experiments include a TREC-3 case where CombMNZ outscored RRF, so the paper does not show universal dominance. (low confidence) — [source](https://cormack.uwaterloo.ca/cormacksigir09-rrf.pdf) - Elasticsearch requires a fixed rank window for stable RRF pagination; changing that window can change previously seen ordering. (low confidence) (verified as of 2026-10-22) — [source](https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion) - Exact-term matching depends on indexed field analysis; Elasticsearch's standard text analyzer removes most punctuation and lowercases tokens. (low confidence) (verified as of 2026-10-22) — [source](https://www.elastic.co/docs/reference/query-languages/query-dsl/query-dsl-term-query) - Bruch et al.'s normalization rank-equivalence result for one query does not by itself establish equivalent learned weights across all queries. (low confidence) — [source](https://arxiv.org/html/2210.11934v2) - Azure documents a fused RRF score bound that increases with the number of query lists being fused. (low confidence) (verified as of 2026-10-22) — [source](https://learn.microsoft.com/azure/search/hybrid-search-ranking) - Azure semantic reranking runs after RRF and reports its score separately from the fusion score. (low confidence) (verified as of 2026-10-22) — [source](https://learn.microsoft.com/azure/search/hybrid-search-ranking) - The EAHR preprint bounds unread RRF contributions and requests deeper channel ranks while they can change complete-list top-K membership or order. (low confidence) — [source](https://arxiv.org/abs/2608.07152) - EAHR's reported anti-correlated cases exhaust both input lists; its authors do not guarantee a speedup on every request. (low confidence) — [source](https://arxiv.org/abs/2608.07152)