| Field | Type | Required | Description |
|---|---|---|---|
verdict |
models.Verdict | ✔️ | The ruling your past decisions point to for this content. |
similarity |
float | ✔️ | How close the nearest matching case is, from 0 to 1. 1 means the content is identical to something you have already decided. |
agreement |
float | ✔️ | How unanimous the matching cases are, from 0 to 1: the share of them that decided this way, ignoring how many there are. Always at least 0.8 when a ruling is returned — below that the casebook reports a disagreement instead of picking a side — so it tells you how clean the consensus was, and is not a threshold to re-apply yourself. |
confidence |
float | ✔️ | How strongly the casebook holds this ruling, from 0 to 1: the agreement scaled by how much evidence backs it, so a handful of close, recent cases outweighs one distant one. Older cases count for less, halving in weight roughly every 180 days. This is the number to use in rules when you want a strength condition. |
case_count |
float | ✔️ | How many of your past cases backed this ruling. |
topic |
Nullable[models.Topic] | ✔️ | The topic the closest matching case is filed under, or null when it has not been grouped into one yet. |