get_verdict_divergence
Where the LLM's verdicts disagree with the model's authored state.
Instructions
Where the LLM's verdicts disagree with the model's authored state.
Two coverage divergence kinds, distinguished by the LLM's p_covers
(probability the control covers the CO), shown as "model confidence":
missing_mapping: HIGH p_covers, but the CO is NOT mapped — the LLM is confident the control covers it, so it should be mapped. Accepting ADDS the mapping.spurious_mapping: LOW p_covers, but the CO IS mapped — the LLM is confident the control does NOT cover it, so the mapping is likely wrong and inflates apparent coverage. Accepting REMOVES the mapping. Only confident rows surface; the uncertain middle band is dropped. So a ~100%-confidence row is a strong "add" and a ~0%-confidence row is a strong "remove" — both are actionable, in opposite directions.
Rows are sorted by confidence, so the strongest calls come first. Each
section is paginated: its pagination.filtered_total reports the full
count, so when it exceeds the rows returned, raise limit (up to 500) or
page with offset to review every divergence — not only the first page.
Also returns group_sufficiency divergences (observation-only). Apply
coverage rows with accept_coverage_divergences; set aside rows the
structural model got right with dismiss_verdict_divergences.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Optional filter — "missing_mapping", "spurious_mapping", or "group_sufficiency". Empty returns all kinds. | |
| limit | No | Max rows per section (clamped to 1-500, default 100). Set to 500 to pull an entire section in one call. | |
| offset | No | Skip the first N rows of each section, for pagination. | |
| model_id | Yes | ID of the threat model. | |
| server_version | Yes | ||
| include_dismissed | No | When true, return ONLY previously-dismissed rows (the undo view) instead of the active list. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||