BM25-based recipe similarity computation runs in real time, averaging 0.8 seconds (sigma 0.1) in the worst case of 100,000 comparisons.¶

Claim · All claims
Evidence · 1 study · causal r? · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person
Design limits · Mejia-Domenzain 2025: no comparison group (read from the study by two models, 2026-10-27)

Subclaims¶

q2 i? Similarity computation over 100 random recipes in the worst-case scenario averaged 0.8 seconds (sigma = 0.1 seconds) on a laptop with an Apple M1 processor. → Mejia-Domenzain 2025

Evidence¶

Mejia-Domenzain 2025¶

Mejia-Domenzain, P., Frej, J., Neshaei, S. P., Mouchel, L., Nazaretsky, T., Wambsganss, T., Bosselut, A., & Käser, T. (2025). Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-024-00405-1

q2 · i? · causal · r?

Numerical timing evaluation of the BM25 Bag-of-Words similarity step, run on 100 random recipes under the worst-case filtered candidate set. As printed, computation time "was on average 0.8 seconds (σ = 0.1 seconds)". No effect size is printed.

"we evaluated the similarity computation time for 100 random recipes in the worst-case scenario (with 100 , 000 comparisons) and we found that the computation time was on average 0.8 seconds (σ = 0.1 seconds) on a laptop with an Apple M1 processor."

Discussion¶

Related Claims¶

• A complete four-skill open-model stack fits under 4 GB, runs at reading pace on the cheapest hardware by community measurements, and costs about one US cent of electricity per study hour — related