From Podcast Narrative to Testable Commodity–Macro Hypotheses: A Replicable Argument-Mapping and Falsification Framework (Demonstration on Setting Course 2026, Episode 4)

This paper demonstrates a replicable workflow for turning long-form podcast/YouTube transcripts into testable commodity–macro hypotheses. It extracts and normalizes claim tokens, encodes asserted support relations as a directed acyclic graph (DAG), and operationalizes key downstream claims using Toulmin decompositions plus falsification checklists linked to measurable indicator families and monitoring cadence. The demonstration produces a reusable replication package template (claims/edges/Toulmin tables + Graphviz figures) and a measurement architecture that separates fast-moving “stock” signals from slower “evolvability” (adaptive-capacity) signals. The contribution is methodological: a transparent, auditable protocol for evaluating narrative theses ex ante.