Python synthetic merge

Weighted FedAvg of float32 models with the request's weights: associative, commutative and closed (a merged model carries its total weight and leaf count), with one documented rounding rule so every tree node agrees. Publishes the merged model and a JSON report. JSON score reports merge into a weights document (a synthetic consensus). Python standard library in beam-sandbox/v1.

ExternalActiveValidatedHippius artifactdistributed-runsyntheticpythonsandboxmergefedavg

Trust

External

Placements

Permissions

Versions

[package identity]

Details

Identity and execution metadata for the latest version.

Package: @beam/py-synthetic-merge
Repository: -
Author: beam
Category: ml
API version: workflow-actions/v2
Latest tag: latest -> 1.2.0
Task mode: single-worker
Default placement: external-workers
Visibility: Public
Published: Nov 1, 2026, 7:09 AM
Updated: 11/1/2026

[workflow reference]

Use in a workflow

Drop this into a workflow definition to reference the action.

{
  "actionPackageName": "@beam/py-synthetic-merge",
  "actionVersionRange": "^1.2.0",
  "config": {},
  "inputBindings": {}
}

[developer tooling]

CLI

Publish and resolve packages from a local development environment.

beam-registry publish . --tag latest
curl "https://api.lab.b3m.dev/registry/v1/resolve/%40beam/py-synthetic-merge?range=latest"