Skip to main content
Back to challenges
Challenge

LangGraph Litigation Funding & TPLF Risk Engine

Property and casualty carriers face rising litigation costs driven by third-party litigation funding (TPLF) in claim disputes. Build a LangGraph workflow to detect TPLF involvement from legal filings and estimate defense cost inflation.

Machine LearningHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a stateful LangGraph graph to parse legal pleadings and output litigation escalation probabilities.

Delivery guide

How work is evaluated

Evaluation

Evaluates TPLF classification accuracy and defense cost prediction error.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

tplf_flag_accuracy

Ensures true positive TPLF identification

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

alae_mae

Mean absolute error on defense cost multiplier • target: 0.15 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Construct a LangGraph pipeline to monitor court docket text for third-party funding markers

  • Forecast litigation duration and total defense expense under TPLF presence

  • Generate early settlement strategy recommendations for claims managers

Resources and assets

Reference links and supporting material

Dataset notes

Court pleading documents and litigation outcome records across NC civil court dockets.

Challenge setup

Evaluates TPLF classification accuracy and defense cost prediction error.

Challenge input

JSON containing docket_text and initial_claim_reserve

LangChain

Provides LangGraph primitives for stateful graph construction

Evaluated output

JSON with tplf_detected (bool), projected_alae_multiplier, and settlement_recommendation

Evaluation checks
  • Ensures true positive TPLF identification
  • Mean absolute error on defense cost multiplier • target: 0.15 • range: 0-1
Configured evaluation evidence
  • Benchmark: Litigation-Risk-Bench
  • Alae Mae target: 0.15
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • LangGraph · Required
  • Graphlit · Optional
  • Amazon Bedrock · Optional
Orchestration
  • LangGraph · Required

Evaluation contract

  • tplf_flag_accuracy · Weight 1
  • alae_mae · Weight 1

Metrics

  • alae_mae · Target 0.15

Benchmarks

  • Litigation-Risk-Bench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing docket_text and initial_claim_reserve

    Output: JSON with tplf_detected (bool), projected_alae_multiplier, and settlement_recommendation

    Execution harness: Python

Evaluation tools

  • LangChain · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about LangGraph Litigation Funding & TPLF Risk Engine