> ## Documentation Index > Fetch the complete documentation index at: https://docs.fuseai.com/llms.txt > Use this file to discover all available pages before exploring further. # Per-arm results of a campaign's A/B splits > For each A/B split in the campaign's sequence: per arm, the leads routed to it and their share, the leads it reached, LinkedIn invitations sent and accepted, human replies, positive replies and meetings booked (rates are per lead routed), bounces and unsubscribes; for all time and, once the split's weights changed on the running campaign, for the leads the split routed since (leads the change moved to the other arm count in all time only, in their new arm). Each split also carries `replySeries`, its replies per arm over time. `since` and `to` keep only the leads that entered an arm in that range; leads waiting at a split are counted whatever the range. A lead counts in the arm it is in, whatever step it replied to. There is no winner and no significance test: `isSmallSample` is true below 20 replies across both arms, where a gap is most likely chance. Only the token owner's own campaigns resolve here. Rate limit: 30 requests/minute and 1,000/day per token owner, shared by every campaign, scheduled-send, campaign-template and knowledge-hub endpoint. Errors: - `404` `CAMPAIGN_NOT_FOUND` — No campaign with this id exists, it belongs to another account (including a campaign delegated to you or shared by your team's visibility settings), or it has been deleted. - `422` `VALIDATION_FAILED` — campaignId is not a 24-character hex id, since or to is not an ISO 8601 date-time, since is in the future, to is earlier than since, or timezone is not a known IANA name. - `429` `RATE_LIMITED` — More than 30 campaign requests in a minute, or 1,000 in a day, for this token owner (the bucket is shared by every /business/campaigns, /business/scheduled-sends, /business/campaign-templates and /business/knowledge-hubs call). - `500` `UNEXPECTED_ERROR` — An unhandled failure; the detail stays in our logs and is never returned. Requires one of the following token scopes: campaigns. ## OpenAPI ````yaml /openapi.json get /business/campaigns/{campaignId}/split-results openapi: 3.1.0 info: title: Fuse Business API version: 1.0.0 description: >- External API for lists, campaigns, prospect search and contacts. Authenticate with your API token as HTTP Basic. All paths are under /api/v1. servers: - url: https://api.tryfuse.ai/api/v1 description: Production security: - basicAuth: [] tags: - name: Lists - name: Custom columns - name: Smart columns - name: Exports - name: Campaigns - name: Knowledge hubs - name: Analytics - name: Website intent - name: Account - name: Prospect search - name: Campaign steps - name: Scheduled sends - name: Campaign templates - name: Agents - name: Research - name: Company search - name: Saved searches - name: Folders - name: Contacts paths: /business/campaigns/{campaignId}/split-results: get: tags: - Campaigns summary: Per-arm results of a campaign's A/B splits description: >- For each A/B split in the campaign's sequence: per arm, the leads routed to it and their share, the leads it reached, LinkedIn invitations sent and accepted, human replies, positive replies and meetings booked (rates are per lead routed), bounces and unsubscribes; for all time and, once the split's weights changed on the running campaign, for the leads the split routed since (leads the change moved to the other arm count in all time only, in their new arm). Each split also carries `replySeries`, its replies per arm over time. `since` and `to` keep only the leads that entered an arm in that range; leads waiting at a split are counted whatever the range. A lead counts in the arm it is in, whatever step it replied to. There is no winner and no significance test: `isSmallSample` is true below 20 replies across both arms, where a gap is most likely chance. Only the token owner's own campaigns resolve here. Rate limit: 30 requests/minute and 1,000/day per token owner, shared by every campaign, scheduled-send, campaign-template and knowledge-hub endpoint. Errors: - `404` `CAMPAIGN_NOT_FOUND` — No campaign with this id exists, it belongs to another account (including a campaign delegated to you or shared by your team's visibility settings), or it has been deleted. - `422` `VALIDATION_FAILED` — campaignId is not a 24-character hex id, since or to is not an ISO 8601 date-time, since is in the future, to is earlier than since, or timezone is not a known IANA name. - `429` `RATE_LIMITED` — More than 30 campaign requests in a minute, or 1,000 in a day, for this token owner (the bucket is shared by every /business/campaigns, /business/scheduled-sends, /business/campaign-templates and /business/knowledge-hubs call). - `500` `UNEXPECTED_ERROR` — An unhandled failure; the detail stays in our logs and is never returned. Requires one of the following token scopes: campaigns. operationId: getCampaignSplitResults parameters: - name: campaignId in: path required: true description: >- The campaign's id (24-character hex ObjectId), as returned by POST /business/campaigns or as the campaignId of a GET /business/campaigns row. schema: type: string description: >- The campaign's id (24-character hex ObjectId), as returned by POST /business/campaigns or as the campaignId of a GET /business/campaigns row. - name: since in: query required: false description: >- ISO 8601 date-time: count only the leads that entered an arm at or after it. Default: since the campaign started. schema: type: string format: date-time description: >- ISO 8601 date-time: count only the leads that entered an arm at or after it. Default: since the campaign started. - name: to in: query required: false description: >- ISO 8601 date-time, not earlier than `since`: count only the leads that entered an arm at or before it. Default: up to now. schema: type: string format: date-time description: >- ISO 8601 date-time, not earlier than `since`: count only the leads that entered an arm at or before it. Default: up to now. - name: timezone in: query required: false description: >- IANA timezone name (e.g. `Europe/Kyiv`, `America/New_York`) whose calendar days `replySeries` is bucketed by. Offsets such as `+03:00` are rejected. Default: `UTC`. schema: type: string maxLength: 64 default: UTC description: >- IANA timezone name (e.g. `Europe/Kyiv`, `America/New_York`) whose calendar days `replySeries` is bucketed by. Offsets such as `+03:00` are rejected. Default: `UTC`. responses: '200': description: Success headers: RateLimit-Limit: schema: type: integer description: Requests permitted in the current window. RateLimit-Remaining: schema: type: integer description: Requests remaining in the current window. RateLimit-Reset: schema: type: integer description: Seconds until the current window resets. content: application/json: schema: type: object properties: splits: type: array items: type: object properties: splitStepId: type: string arms: type: array items: type: object properties: key: type: string enum: - a - b label: type: - string - 'null' weight: type: integer required: - key - label - weight description: The split's current arms and weights. weightsChangedAt: type: - string - 'null' description: >- When the weights last changed after the campaign started (ISO 8601); null if they never did. waiting: type: integer description: >- Leads at the split not routed yet: the campaign was paused when they reached it, or a weights change moved them and they are about to be routed again. allTime: type: object description: Every lead the split routed. properties: entered: type: integer replied: type: integer isSmallSample: type: boolean description: >- Fewer than 20 replies across both arms: a gap between the arms is most likely chance. arms: type: array items: type: object properties: key: type: string enum: - a - b entered: type: integer description: Leads routed to the arm. share: type: - number - 'null' description: entered / entered of both arms, 0-1. reached: type: integer description: >- Leads the arm sent at least one message, invitation or task. invitesSent: type: integer invitesAccepted: type: integer acceptanceRate: type: - number - 'null' description: invitesAccepted / invitesSent, 0-1. replied: type: integer description: >- Human replies; out-of-office and unsubscribe requests excluded. replyRate: type: - number - 'null' description: replied / entered, 0-1. positiveReplies: type: integer description: >- Replies marked interested or meeting booked. positiveReplyRate: type: - number - 'null' description: positiveReplies / entered, 0-1. meetingsBooked: type: integer description: Replies marked meeting booked. meetingRate: type: - number - 'null' description: meetingsBooked / entered, 0-1. bounced: type: integer unsubscribed: type: integer required: - key - entered - share - reached - invitesSent - invitesAccepted - acceptanceRate - replied - replyRate - positiveReplies - positiveReplyRate - meetingsBooked - meetingRate - bounced - unsubscribed required: - entered - replied - isSmallSample - arms sinceChange: type: - object - 'null' description: >- Only the leads the split routed since weightsChangedAt, not those the change moved; null when the weights never changed. properties: entered: type: integer replied: type: integer isSmallSample: type: boolean description: >- Fewer than 20 replies across both arms: a gap between the arms is most likely chance. arms: type: array items: type: object properties: key: type: string enum: - a - b entered: type: integer description: Leads routed to the arm. share: type: - number - 'null' description: entered / entered of both arms, 0-1. reached: type: integer description: >- Leads the arm sent at least one message, invitation or task. invitesSent: type: integer invitesAccepted: type: integer acceptanceRate: type: - number - 'null' description: invitesAccepted / invitesSent, 0-1. replied: type: integer description: >- Human replies; out-of-office and unsubscribe requests excluded. replyRate: type: - number - 'null' description: replied / entered, 0-1. positiveReplies: type: integer description: >- Replies marked interested or meeting booked. positiveReplyRate: type: - number - 'null' description: positiveReplies / entered, 0-1. meetingsBooked: type: integer description: Replies marked meeting booked. meetingRate: type: - number - 'null' description: meetingsBooked / entered, 0-1. bounced: type: integer unsubscribed: type: integer required: - key - entered - share - reached - invitesSent - invitesAccepted - acceptanceRate - replied - replyRate - positiveReplies - positiveReplyRate - meetingsBooked - meetingRate - bounced - unsubscribed required: - entered - replied - isSmallSample - arms replySeries: type: array description: >- The allTime window's replies per arm over time, one zero-filled point per bucket, from `since` (or the campaign's creation) to `to` (or now). Buckets are daily, ISO-weekly or monthly, the finest that keeps the series at 13 points or fewer; past 13 months they are quarterly, which runs past 13 points once the window spans more than 13 quarters. Days are calendar days in `timezone`. A reply after `to` is left out of the series but still counts in `replied`. items: type: object properties: date: type: string description: >- The bucket's start as a display label: 'Sep 1' for daily and weekly buckets, 'Sep' for monthly, 'Sep 2026' for quarterly. isoDate: type: string description: The bucket's start as YYYY-MM-DD. a: type: integer description: Replies from arm a's leads in the bucket. b: type: integer description: Replies from arm b's leads in the bucket. required: - date - isoDate - a - b required: - splitStepId - arms - weightsChangedAt - waiting - allTime - sinceChange - replySeries required: - splits example: splits: - splitStepId: 6a8dce2ef83628aea1088041 arms: - key: a label: Email first weight: 50 - key: b label: LinkedIn first weight: 50 weightsChangedAt: null waiting: 0 allTime: entered: 200 replied: 9 isSmallSample: true arms: - key: a entered: 101 share: 0.505 reached: 98 invitesSent: 0 invitesAccepted: 0 acceptanceRate: null replied: 3 replyRate: 0.0297 positiveReplies: 1 positiveReplyRate: 0.0099 meetingsBooked: 1 meetingRate: 0.0099 bounced: 2 unsubscribed: 1 - key: b entered: 99 share: 0.495 reached: 90 invitesSent: 90 invitesAccepted: 21 acceptanceRate: 0.2333 replied: 6 replyRate: 0.0606 positiveReplies: 2 positiveReplyRate: 0.0202 meetingsBooked: 1 meetingRate: 0.0101 bounced: 0 unsubscribed: 0 sinceChange: null replySeries: - date: Aug 31 isoDate: '2026-08-31' a: 1 b: 1 - date: Sep 7 isoDate: '2026-09-07' a: 1 b: 3 - date: Sep 14 isoDate: '2026-09-14' a: 1 b: 2 '400': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '402': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '409': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '422': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' security: - basicAuth: [] components: schemas: Error: type: object properties: error: type: object properties: code: type: string message: type: string param: type: - string - 'null' doc_url: type: - string - 'null' request_id: type: - string - 'null' required: - code - message required: - error securitySchemes: basicAuth: type: http scheme: basic description: >- Your API token (`af_…`) as the Basic-auth username, with an empty password. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.