> ## Documentation Index > Fetch the complete documentation index at: https://agent-observability-docs.splunk.com/llms.txt > Use this file to discover all available pages before exploring further. # Validate Decision Scorer Dataset > Test a decision evaluator on dataset rows. The results go to a new metrics_testing run. The evaluator fields have the shape of the log record request. dataset_id, dataset_version_index, limit and starting_token select the rows, as in the LLM dataset request. scoreable_node_types holds one node type, trace or llm. Read the results with metric_key=decision_scorer_validation. ## OpenAPI ````yaml https://api.galileo.ai/public/v2/openapi.json post /v2/scorers/decision/validate/dataset openapi: 3.1.0 info: title: FastAPI version: 0.1.0 servers: - url: https://api.galileo.ai description: Galileo Public APIs - galileo-v2 security: [] paths: /v2/scorers/decision/validate/dataset: post: tags: - data - prompts - rows summary: Validate Decision Scorer Dataset description: >- Test a decision evaluator on dataset rows. The results go to a new metrics_testing run. The evaluator fields have the shape of the log record request. dataset_id, dataset_version_index, limit and starting_token select the rows, as in the LLM dataset request. scoreable_node_types holds one node type, trace or llm. Read the results with metric_key=decision_scorer_validation. operationId: >- validate_decision_scorer_dataset_v2_scorers_decision_validate_dataset_post requestBody: content: application/json: schema: $ref: '#/components/schemas/ValidateDecisionScorerDatasetRequest' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ValidateScorerLogRecordResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] - ClassicAPIKeyHeader: [] - OAuth2PasswordBearer: [] - HTTPBasic: [] components: schemas: ValidateDecisionScorerDatasetRequest: properties: dataset_id: type: string format: uuid4 title: Dataset Id dataset_version_index: anyOf: - type: integer - type: 'null' title: Dataset Version Index limit: type: integer title: Limit description: Maximum number of dataset rows to process. default: 100 starting_token: anyOf: - type: integer - type: 'null' title: Starting Token description: Pagination offset into dataset rows. model_name: type: string maxLength: 255 minLength: 1 title: Model Name question: type: string maxLength: 2000 minLength: 1 title: Question answer_options: anyOf: - items: type: string type: array - items: $ref: '#/components/schemas/DecisionChoice' type: array - items: $ref: '#/components/schemas/DecisionLevel' type: array - $ref: '#/components/schemas/DecisionBooleanCriteria' - type: 'null' title: Answer Options scorer_configuration: $ref: '#/components/schemas/DecisionScorerTestConfiguration' type: object required: - dataset_id - model_name - question - scorer_configuration title: ValidateDecisionScorerDatasetRequest description: >- Test a decision evaluator on dataset rows. The dataset fields select the rows. dataset_id, dataset_version_index, limit and starting_token have the same meaning and defaults as in the LLM dataset request. scoreable_node_types must be trace or llm. ValidateScorerLogRecordResponse: properties: metrics_experiment_id: type: string format: uuid4 title: Metrics Experiment Id project_id: type: string format: uuid4 title: Project Id type: object required: - metrics_experiment_id - project_id title: ValidateScorerLogRecordResponse description: >- Response model for validating a scorer based on log records. Returns the uuid of the experiment created with the copied log records to store the metric testing results. Also returns the project_id so callers can poll /projects/{project_id}/traces/search. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError DecisionChoice: properties: label: type: string title: Label description: anyOf: - type: string - type: 'null' title: Description additionalProperties: false type: object required: - label title: DecisionChoice description: >- One option of a choice question, with an optional description of when it applies. Extra fields are forbidden, so a level, which has a ``level`` field, never validates as a choice. DecisionLevel: properties: level: type: integer maximum: 9 minimum: 0 title: Level label: type: string title: Label description: anyOf: - type: string - type: 'null' title: Description type: object required: - level - label title: DecisionLevel description: >- One level of a score question. A question's levels run 0, 1, 2 and so on, with no gaps. DecisionBooleanCriteria: properties: 'true': type: string title: 'True' 'false': type: string title: 'False' additionalProperties: false type: object required: - 'true' - 'false' title: DecisionBooleanCriteria description: >- What a true answer and a false answer mean, for a yes/no question. The two are set together. DecisionScorerTestConfiguration: properties: output_type: $ref: '#/components/schemas/OutputTypeEnum' description: One of boolean_probability, categorical, discrete. scoreable_node_types: items: $ref: '#/components/schemas/StepType' type: array maxItems: 1 minItems: 1 title: Scoreable Node Types input_type: anyOf: - $ref: '#/components/schemas/InputTypeEnum' - type: 'null' ground_truth: type: boolean title: Ground Truth default: false type: object required: - output_type - scoreable_node_types title: DecisionScorerTestConfiguration description: >- The evaluator settings of a decision Test request, the same place as the LLM scorer_configuration. scoreable_node_types holds exactly one node type. input_type defaults to the decision default for it (get_decision_input_type). ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError OutputTypeEnum: type: string enum: - boolean - categorical - count - discrete - freeform - percentage - multilabel - retrieved_chunk_list_boolean - boolean_multilabel - boolean_probability title: OutputTypeEnum description: Enumeration of output types. StepType: type: string enum: - http - llm - retriever - tool - workflow - agent - control - trace - session title: StepType InputTypeEnum: type: string enum: - basic - llm_spans - retriever_spans - sessions_normalized - sessions_trace_io_only - tool_spans - trace_input_only - trace_io_only - trace_normalized - trace_output_only - agent_spans - workflow_spans title: InputTypeEnum description: Enumeration of input types. securitySchemes: APIKeyHeader: type: apiKey in: header name: Splunk-AO-API-Key ClassicAPIKeyHeader: type: apiKey in: header name: Galileo-API-Key OAuth2PasswordBearer: type: oauth2 flows: password: scopes: {} tokenUrl: https://api.galileo.ai/login HTTPBasic: type: http scheme: basic ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.