DOC-API-MODEL-schema-1jo37n9pqa#overview
ScoreAggregate
Count and average for scores grouped by name and source.
Meaning and usage
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#meaning
See the definition above.
Usage profiles
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#fields
| Usage | Fields and validation |
|---|---|
| In responses | View fields |
In responses
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#response
API JSON uses JSON field names (camelCase).
| Field | Type | Presence | Meaning |
|---|---|---|---|
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#field-nameSection ID: DOC-API-MODEL-schema-1jo37n9pqa#response-field-namename | string | Optional | Metric name shared by the aggregated scores. |
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#field-sourceSection ID: DOC-API-MODEL-schema-1jo37n9pqa#response-field-sourcesource | string (SCORE_SOURCE_JUDGE, SCORE_SOURCE_HUMAN, SCORE_SOURCE_USER, SCORE_SOURCE_HARNESS, SCORE_SOURCE_EVAL) or integer (int32) | Optional; explicit presence | Source classification reported for the evaluation score. |
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#field-countSection ID: DOC-API-MODEL-schema-1jo37n9pqa#response-field-countcount | string (int64) | Optional | Number of evaluation records represented by this group. Pattern: ^-?\d+$. |
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#field-averageSection ID: DOC-API-MODEL-schema-1jo37n9pqa#response-field-averageaverage | number (double) or string (NaN, Infinity, -Infinity) | Optional | Average score value reported for the aggregate. |
Values of source
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#response-values-source
Platform classification of who produced an evaluation score. The provider source label retains its original vocabulary: writes accept API or ANNOTATION, while EVAL is reserved for the provider's internal evaluators and is rejected through its public API.
SCORE_SOURCE_HUMAN maps to ANNOTATION. SCORE_SOURCE_USER, SCORE_SOURCE_JUDGE and SCORE_SOURCE_HARNESS map to API.
Reviewer and end-user scores also use separate name namespaces: reviewer scores do not use names beginning with user-feedback-.
| Value | No. | Form | Meaning |
|---|---|---|---|
SCORE_SOURCE_JUDGE | 0 | Canonical | A score produced by an automated judge. |
SCORE_SOURCE_HUMAN | 1 | Canonical | A score entered by a human reviewer through the annotation path. |
SCORE_SOURCE_USER | 2 | Canonical | Feedback supplied by an end user. |
SCORE_SOURCE_HARNESS | 3 | Canonical | A score written by an evaluation harness or another API-based producer. |
SCORE_SOURCE_EVAL | 4 | Canonical | A read-only score produced by the evaluation provider's managed evaluators; it cannot be written through the public score API. |
Where used
Section ID: DOC-API-MODEL-schema-1jo37n9pqa#where-used
| Reference | Relationship |
|---|---|
| Get the eval overview | POST /api/v1/evals/get-overview |
Models containing this value
| Model | Relationship |
|---|---|
| EvalOverview | Nested in model |
Download the public reference contract.
Document ID: DOC-API-MODEL-schema-1jo37n9pqa