Section ID:
Values of
Values of
Values of
DOC-API-MODEL-schema-1jm5lo00e7#overview
Score
Evaluation score with its value, source, target identity, and generation attribution.
Meaning and usage
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#meaning
See the definition above.
Usage profiles
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#fields
| Usage | Fields and validation |
|---|---|
| In responses | View fields |
In responses
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#response
API JSON uses JSON field names (camelCase).
| Field | Type | Presence | Meaning |
|---|---|---|---|
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-scoreidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-scoreidscoreId | string | Optional | Identifier of the evaluation score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-targettypeSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-targettypetargetType | string (EVAL_TARGET_TYPE_TRACE, EVAL_TARGET_TYPE_OBSERVATION, EVAL_TARGET_TYPE_DATASET_RUN, EVAL_TARGET_TYPE_SESSION) or integer (int32) | Optional; explicit presence | Kind of evaluation object to which the score applies. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-targetidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-targetidtargetId | string | Optional | Identifier of the evaluation object to which the score applies. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-nameSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-namename | string | Optional | Metric name identifying the recorded evaluation score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-datatypeSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-datatypedataType | string (SCORE_DATA_TYPE_NUMERIC, SCORE_DATA_TYPE_CATEGORICAL, SCORE_DATA_TYPE_BOOLEAN, SCORE_DATA_TYPE_TEXT) or integer (int32) | Optional; explicit presence | Value type used to interpret numeric, categorical, Boolean, or text score values. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-numericvalueSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-numericvaluenumericValue | number (double) or string (NaN, Infinity, -Infinity) | Optional | Numeric score value reported by the evaluator. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-stringvalueSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-stringvaluestringValue | string | Optional | Category label recorded for a categorical evaluation score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-booleanvalueSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-booleanvaluebooleanValue | boolean | Optional | Boolean value recorded for a Boolean evaluation score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-sourceSection ID: DOC-API-MODEL-schema-1jm5lo00e7#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-1jm5lo00e7#field-commentSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-commentcomment | string | Optional | Explanatory text attached to the evaluation score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-createdatSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-createdatcreatedAt | string (date-time) | Optional | Time when this record was created. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-textvalueSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-textvaluetextValue | string | Optional | Text value of the evaluation score. |
authorUserId | string | Optional | Identifier recorded for the user who authored the score. A stored author identifier alone does not attest to verified human provenance. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-configidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-configidconfigId | string | Optional | Identifier of the score configuration defining the score’s value domain. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-queueidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-queueidqueueId | string | Optional | Identifier of the annotation queue. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-traceidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-traceidtraceId | string | Optional | Identifier of the evaluation trace. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-observationidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-observationidobservationId | string | Optional | Identifier of the evaluation observation. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-sessionidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-sessionidsessionId | string | Optional | Identifier of the evaluation session grouping related traces. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-datasetrunidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-datasetruniddatasetRunId | string | Optional | Identifier of the dataset run associated with the score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-environmentSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-environmentenvironment | string | Optional | Environment label attached to the evaluation record. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-metadatajsonSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-metadatajsonmetadataJson | string | Optional | Additional attributes serialized as a JSON object. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-updatedatSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-updatedatupdatedAt | string (date-time) | Optional | Time when this record was last updated. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-timestampSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-timestamptimestamp | string (date-time) | Optional | Timestamp associated with the evaluation score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-tracenameSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-tracenametraceName | string | Optional | Trace name included with the score for display in score listings. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-useridSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-useriduserId | string | Optional | User identifier recorded with the evaluation score. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-sourcelabelSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-sourcelabelsourceLabel | string | Optional | Original evaluation-provider source label, such as API, ANNOTATION or EVAL. Interpret it alongside source and authorship: API alone does not distinguish an end-user rating from a harness, and a source label does not independently prove verified human provenance. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-conversationidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-conversationidconversationId | string | Optional | Conversation identifier recorded in the score’s own metadata. Scores authored directly in the evaluation store can lack platform attribution; an empty link is not repaired by retrying. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-messageidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-messageidmessageId | string | Optional | Identifier of the conversation message associated with the evaluation record. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-messagesequenceSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-messagesequencemessageSequence | string (int64) | Optional | Sequence number of the evaluated message within its conversation. Pattern: ^-?\d+$. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-profileidSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-profileidprofileId | string | Optional | Identifier of the agent profile associated with the generation. |
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#field-confighashSection ID: DOC-API-MODEL-schema-1jm5lo00e7#response-field-confighashconfigHash | string | Optional | Fingerprint of the profile ID, model and resolved prompt hash used to group evaluation results. Other settings are excluded; this is not an immutable profile revision. |
Values of targetType
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#response-values-targettype
Kind of evaluation object a score or evaluation configuration addresses.
| Value | No. | Form | Meaning |
|---|---|---|---|
EVAL_TARGET_TYPE_TRACE | 0 | Canonical | A complete trace identified by its trace identifier. |
EVAL_TARGET_TYPE_OBSERVATION | 1 | Canonical | A specific observation within a trace. |
EVAL_TARGET_TYPE_DATASET_RUN | 2 | Canonical | An evaluation run over a dataset. |
EVAL_TARGET_TYPE_SESSION | 3 | Canonical | A session grouping multiple traces. The evaluation harness attaches session-scoped judge scores directly; the provider does not expose a session-level evaluator target. |
Values of dataType
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#response-values-datatype
Scores
Data representation of an evaluation score or score configuration.
| Value | No. | Form | Meaning |
|---|---|---|---|
SCORE_DATA_TYPE_NUMERIC | 0 | Canonical | A numeric measurement or rating. |
SCORE_DATA_TYPE_CATEGORICAL | 1 | Canonical | A value chosen from a named set of categories. |
SCORE_DATA_TYPE_BOOLEAN | 2 | Canonical | A true-or-false evaluation result. |
SCORE_DATA_TYPE_TEXT | 3 | Canonical | Free-form text supplied by an evaluator or reviewer. The provider supports text values on score definitions and scores; support through this API depends on the operation. |
Values of source
Section ID: DOC-API-MODEL-schema-1jm5lo00e7#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-1jm5lo00e7#where-used
| Reference | Relationship |
|---|---|
| Get the eval overview | POST /api/v1/evals/get-overview |
| Get a session | POST /api/v1/evals/get-session |
| Get a trace | POST /api/v1/evals/get-trace |
| List observations | POST /api/v1/evals/list-observations |
| List scores | POST /api/v1/evals/list-scores |
| List sessions | POST /api/v1/evals/list-sessions |
| List traces | POST /api/v1/evals/list-traces |
Models containing this value
| Model | Relationship |
|---|---|
| EvalOverview | Nested in model |
| Observation | Nested in model |
| SessionSummary | Nested in model |
| TraceDetail | Nested in model |
| TraceSummary | Nested in model |
Download the public reference contract.
Document ID: DOC-API-MODEL-schema-1jm5lo00e7