标签：information-retrieval

Rerank, filter, and compress JSON search results with TypeSafe AI's Jev.

Free English RAG benchmark for TypeSafe Jev 1.13 — frozen candidate pools, calibration, paired bootstrap CIs, $0 runs. Compared with OpenJev and NVIDIA cross-encoders.

Context-carrying graph retrieval with Jev: branching walks, reproducible ablations, and a visual replay.

Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.

Does a System One model actually beat keyword matching? A reproducible benchmark on catching disguised duplicate thesis titles. 24 cases, real production baseline, raw data and charts included.

Reproducible experiments evaluating Jev as an automated judge across benchmarks and tasks.