rlat-gap-scan

Detect knowledge corpus gaps by evaluating retrieved context during session-based reading to classify whether specific answers exist, surfacing true gaps for later action.

Recurrence logging for gap detection tracks candidate gaps across sessions on a .rlat corpus, applying a recurrence gate to promote recurring candidate gaps to confirmed status based on user judgment labels.

Yes, you can identify unanswered questions in a local .rlat corpus without external APIs. The gap detection process relies entirely on user judgment to label gaps and classify retrieved context during sessions.

Start a gap-filling workflow by running the gap scan against your loaded .rlat corpus to identify unanswered questions, logging confirmed gaps to guide subsequent review and content addition actions.

Yes, this gap detection approach works across multiple reading sessions on the same .rlat corpus, logging recurring findings to distinguish newly identified candidate gaps from previously confirmed gaps over time.