Retrieval / provenance / review

An answer is a start.
Follow the citation.

Open a recorded query. Trace the returned sentence to a source hash. Then inspect the baselines and the cases the support guard missed.

This explorer loads checked-in evaluation results. It does not run a search service or a model. The actual Python service runs on local loopback; its source and tests are public.

—source documents / hashed snapshots
—authored development queries
—unsupported guard probes missed

Loading recorded evidence.

Run it yourself

Small enough to inspect.

Incremental Markdown ingestion, SQLite BM25, character TF-IDF, reciprocal-rank fusion and extractive citations. No model credential is required.

Source, one-command demo and CI ↗
Know the boundary

Provenance is not truth.

Ten owner-authored documents are a development corpus. No independent relevance labels, free-form model generation, public backend or production adoption is claimed.

Read the failure analysis ↗ · Raw recorded output ↗