> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mathfi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Feature refinement result — columnStatus + refined download links

> The finished run's outcome: each original column's KEEP/REMOVE decision plus short-lived signed download URLs for the reduced train + prediction CSVs (the columns the loop eliminated are dropped). The download URLs are populated once the state is REFINEMENT_COMPLETED, and null before then.



## OpenAPI

````yaml api-reference/openapi.yaml GET /api/v1/feature-refinery/{featureRefinementKey}/result
openapi: 3.0.1
info:
  title: MathFi.ai API
  description: >
    The MathFi.ai REST API runs the two products end to end.


    **Feature Refinery** takes your labelled data and works out which columns

    actually carry the signal. It returns a reduced train and test pair, a

    per-column keep/remove decision, and the performance target the refined data

    reached.


    **Model Crucible** takes a dataset, trains every algorithm family against it

    at once, ranks the results on held-out data by fewest wrong decisions, and

    keeps the best three as versions of one model. You pick which one
    predictions

    run against.


    Everything is asynchronous: you create a thing, upload to a signed URL,
    start

    it, then poll until the state is terminal. Nothing streams and nothing
    blocks.
  contact:
    name: MathFi.ai
    url: https://mathfi.ai
    email: support@mathfi.ai
  license:
    name: MathFi.ai
    url: https://mathfi.ai
  version: 1.0.0
servers:
  - url: https://{tenant}-api.mathfi.ai
    description: >-
      Your tenant's API. Each customer has their own, so the host varies.
      Replace {tenant} with the name issued when your tenant was created.
    variables:
      tenant:
        default: your-tenant
        description: The tenant name issued to you.
security:
  - BearerAuth: []
tags:
  - name: Authentication
    description: Exchange credentials for a bearer token
  - name: Feature Refinery
    description: Reduce a dataset to the columns that earn their place
  - name: Datasets
    description: >-
      Prepare labelled data for training, from uploads or from a finished
      refinement
  - name: Training
    description: Run the Crucible against a dataset and choose the champion model
  - name: Models
    description: Trained models and their versions
  - name: Predictions
    description: Score unlabelled data against a champion model
paths:
  /api/v1/feature-refinery/{featureRefinementKey}/result:
    get:
      tags:
        - Feature Refinery
      summary: Feature refinement result — columnStatus + refined download links
      description: >-
        The finished run's outcome: each original column's KEEP/REMOVE decision
        plus short-lived signed download URLs for the reduced train + prediction
        CSVs (the columns the loop eliminated are dropped). The download URLs
        are populated once the state is REFINEMENT_COMPLETED, and null before
        then.
      operationId: getFeatureRefinementResult
      parameters:
        - name: featureRefinementKey
          in: path
          required: true
          schema:
            type: string
            format: uuid
      responses:
        '200':
          description: Result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/FeatureRefineryResultOutput'
        '404':
          description: Unknown feature refinement key
        '500':
          description: Internal server error
components:
  schemas:
    FeatureRefineryResultOutput:
      description: >-
        The finished run's outcome — the per-column KEEP/REMOVE decisions and
        signed download URLs for the reduced deliverables. The download URLs are
        short-lived and null until the run reaches REFINEMENT_COMPLETED.
      type: object
      properties:
        featureRefinementKey:
          type: string
          format: uuid
        state:
          type: string
        columnStatus:
          type: array
          description: >-
            One entry per original column, in column order, with its keep/remove
            outcome.
          items:
            $ref: '#/components/schemas/ColumnDecision'
        refinedTrainUrl:
          type: string
          nullable: true
          description: >-
            Short-lived signed GET URL for the reduced train CSV. Null before
            REFINEMENT_COMPLETED.
        refinedPredictionUrl:
          type: string
          nullable: true
          description: >-
            Short-lived signed GET URL for the reduced prediction/test CSV. Null
            before REFINEMENT_COMPLETED.
        refinedColumnStatusUrl:
          type: string
          nullable: true
          description: >-
            Short-lived signed GET URL for the column-status filter file (the
            per-column KEEP/REMOVE 1/0 vector as CSV) — the same decisions as
            columnStatus above, downloadable as a file so it can be reapplied to
            drop columns from a later prediction file. Null before
            REFINEMENT_COMPLETED.
    ColumnDecision:
      description: >-
        One original column's keep/remove outcome. columnIndex is 0-based over
        the uploaded train CSV's columns in header order; columnName is that
        header cell, null on runs created before names were captured.
      required:
        - columnIndex
        - outcome
      type: object
      properties:
        columnIndex:
          type: integer
        columnName:
          type: string
          nullable: true
        outcome:
          type: string
          enum:
            - KEEP
            - REMOVE
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT

````