Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PPCR-IM: A System for Multi-layer DAG-based Public Policy Consequence Reasoning and Social Indicator Mapping

Zichen Song, Weijia Li

TL;DR

PPCR-IM is a system for multi-layer DAG-based consequence reasoning and social indicator mapping that addresses this gap in public policy decisions, using an LLM-driven, layer-wise generator to construct a directed acyclic graph of intermediate consequences.

Abstract

Public policy decisions are typically justified using a narrow set of headline indicators, leaving many downstream social impacts unstructured and difficult to compare across policies. We propose PPCR-IM, a system for multi-layer DAG-based consequence reasoning and social indicator mapping that addresses this gap. Given a policy description and its context, PPCR-IM uses an LLM-driven, layer-wise generator to construct a directed acyclic graph of intermediate consequences, allowing child nodes to have multiple parents to capture joint influences. A mapping module then aligns these nodes to a fixed indicator set and assigns one of three qualitative impact directions: increase, decrease, or ambiguous change. For each policy episode, the system outputs a structured record containing the DAG, indicator mappings, and three evaluation measures: an expected-indicator coverage score, a discovery rate for overlooked but relevant indicators, and a relative focus ratio comparing the systems coverage to that of the government. PPCR-IM is available both as an online demo and as a configurable XLSX-to-JSON batch pipeline.

PPCR-IM: A System for Multi-layer DAG-based Public Policy Consequence Reasoning and Social Indicator Mapping

TL;DR

PPCR-IM is a system for multi-layer DAG-based consequence reasoning and social indicator mapping that addresses this gap in public policy decisions, using an LLM-driven, layer-wise generator to construct a directed acyclic graph of intermediate consequences.

Abstract

Public policy decisions are typically justified using a narrow set of headline indicators, leaving many downstream social impacts unstructured and difficult to compare across policies. We propose PPCR-IM, a system for multi-layer DAG-based consequence reasoning and social indicator mapping that addresses this gap. Given a policy description and its context, PPCR-IM uses an LLM-driven, layer-wise generator to construct a directed acyclic graph of intermediate consequences, allowing child nodes to have multiple parents to capture joint influences. A mapping module then aligns these nodes to a fixed indicator set and assigns one of three qualitative impact directions: increase, decrease, or ambiguous change. For each policy episode, the system outputs a structured record containing the DAG, indicator mappings, and three evaluation measures: an expected-indicator coverage score, a discovery rate for overlooked but relevant indicators, and a relative focus ratio comparing the systems coverage to that of the government. PPCR-IM is available both as an online demo and as a configurable XLSX-to-JSON batch pipeline.
Paper Structure (19 sections, 3 figures, 1 table)

This paper contains 19 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Task Formulation and Evaluation
  3. Inputs and outputs
  4. DAG reasoning and indicator mapping
  5. Evaluation objectives
  6. System Architecture and Methods
  7. Overall architecture and data flow
  8. Layer-wise DAG construction
  9. Indicator mapping and prediction
  10. Experiment and Results
  11. Runtime configuration and batch pipeline
  12. Dataset and metric computation
  13. Results, case studies, and limitations
  14. Demo Availability, Reproducibility
  15. Online demo and interaction modes
  16. ...and 4 more sections

Figures (3)

  • Figure 1: A policy description and contextual attributes are used to generate a multi-layer consequence DAG that models causal impact pathways. The system maps DAG nodes to a fixed indicator vocabulary with directional effects and supporting evidence links, enabling structured impact assessment and downstream evaluation.
  • Figure 2: Web-based interface of the Policy Consequence DAG Evaluation System. Users provide policy descriptions and contextual information to trigger DAG-based consequence evaluation and indicator-level impact metrics.
  • Figure 3: Regional distribution of the 1,027 policy episodes used in our experiments.