webis-bm25-gpt-oss — Retrieval Task

Please describe in details how this run was generated: We used openai-gpt-oss-120b with 5 long query reduction prompts that we developed in the previous year. The LLM had the original query as input, and was framed to remove words that do not help with retrieval. We used 5 different prompts and submitted the five reduced queries against PyTerrier with BM25 in default configuration and used reciprocal rank fusion implemented in ranx to fuse the 5 runs.
Specify datasets used in this run.: ['Other']
(if you checked "other", describe here): We did not train any approaches, only re-used our existing long-query-reduction prompts.
Are you 100% confident that no data from https://github.com/microsoft/Tip-of-the-Tongue-Known-Item-Retrieval-Dataset-for-Movie-Identification or iRememberThisMovie.com (besides the training data provided as part of this year's track) was used for producing this run (including any data used for pretraining models that you are building on top of)?: no
Did you use any of the official baseline runs in any way to produce this run?: yes
If you did use any of the official baseline runs in any way to produce this run, please describe how below in sufficient detail (e.g., as reranking candidates or in ensemble with other approaches).: The PyTerrier Index.