Skip to main content
StripePatent grant

Stripe was granted a patent for machine-learning network routing.

Source: Autobound Signal API · 174 signals tracked for Stripe · updated

Get Stripe's live signals in Claude or ChatGPT, or by API

AskWhat changed at Stripe this week? Use Autobound signals for stripe.com.

What happened

In November 2026 Stripe patented adaptive routing technology for selecting efficient paths for messages across digital networks.

Source

patents.google.comNov 17, 2026

US patent US12803883

Variational outcome-mapping model for network routing

Abstract

A method and related systems may generate and use a machine learning model that determines multiple outcome values for multiple message routes, where the model may account for unknown node values in one or more nodes during model creation. Some embodiments may then compare the multiple outcome values to select a target route for the message. Moreover, some embodiments may facilitate efficient network route determination through an adaptive weight node network by selecting different dynamic routing protocols based on critical thresholds.

patents.google.com/patent/US12803883Read the full source

Extracted by Autobound

From the Signal API record
Signal
Patent grant

What this signalsA new patent often shows where a company is putting its R&D budget.

Grant date
Nov 17, 2026
Inventors
4
Tech area
networking / data transmission
Patent number
US12803883

The full record

From the Signal API record

People

  • Joshua AckermanInventor
  • Michael CribbinInventor
  • Andrei ZahariaInventor
  • Niall O'HaraInventor
  • Aidan FoleyInventor
  • Cody Ley-HanInventor

Details

Primary CPC class
H04L 41/16 (Transmission of digital information)
USPTO assignee
Stripe, LLC
What the invention does
A model scores several possible message routes, fills in missing information about network nodes, and chooses the path with the best predicted outcome.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Machine Learning
  • Network

Technologies named

  • machine learning
  • network routing
  • adaptive networks

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Stripe and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Stripe this week?”

  2. Send it to your own tools

    The Signal API returns patent signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full patents-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/2b05d52b-4313-5b26-83b2-d8e6b4bc16a4 returns this record as JSON. POST /v1/companies/enrich returns every signal for stripe.com.

{
  "signal_id": "2b05d52b-4313-5b26-83b2-d8e6b4bc16a4",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:53:28+00:00",
  "company": {
    "name": "Stripe",
    "domain": "stripe.com"
  },
  "data": {
    "cpc": [
      {
        "code": "H04L 41/16",
        "label": "Transmission of digital information"
      },
      {
        "code": "H04L 45/028",
        "label": "Transmission of digital information"
      },
      {
        "code": "H04W 24/02",
        "label": "Wireless communication networks"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "Network"
    ],
    "detail": "In November 2026 Stripe patented adaptive routing technology for selecting efficient paths for messages across digital networks.",
    "summary": "Stripe was granted a patent for machine-learning network routing.",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Joshua Ackerman",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Michael Cribbin",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Andrei Zaharia",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Niall O'Hara",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/niallohara1"
      },
      {
        "name": "Aidan Foley",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/aidanfoley7"
      },
      {
        "name": "Cody Ley-Han",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "networking / data transmission",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12803883",
    "cpc_primary": {
      "code": "H04L 41/16",
      "label": "Transmission of digital information"
    },
    "patent_title": "Variational outcome-mapping model for network routing",
    "patent_number": "US12803883",
    "uspto_assignee": "Stripe, LLC",
    "patent_abstract": "A method and related systems may generate and use a machine learning model that determines multiple outcome values for multiple message routes, where the model may account for unknown node values in one or more nodes during model creation. Some embodiments may then compare the multiple outcome values to select a target route for the message. Moreover, some embodiments may facilitate efficient network route determination through an adaptive weight node network by selecting different dynamic routing protocols based on critical thresholds.",
    "precision_class": "structural",
    "invention_explanation": "A model scores several possible message routes, fills in missing information about network nodes, and chooses the path with the best predicted outcome.",
    "technologies_mentioned": [
      "machine learning",
      "network routing",
      "adaptive networks"
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.