Research / Knowledge Work

The Cascade Graph

An interactive, cited knowledge graph that maps physical, geopolitical, and economic constraints across the global economy, with node evidence pages, feedback loops, and an accessible text index.

Clear27/30
Useful24/30
Specific18/20
Complete13/20
The Cascade Graph screenshot

Why it was accepted

The page clearly presents a functional research product with a specific purpose: mapping how stress moves through the real economy and where it leads to investable exposures. The snapshot shows substantial product evidence, including 393 nodes, 562 sourced edges, feedback loops, search, filtering, focus mode, export/share features, and an accessible no-JS index. It is useful to researchers and market analysts, and the page explains how to navigate and interpret the graph.

Weakness

The snapshot does not show the full breadth of the underlying source set, update cadence, or whether the graph is regularly maintained. It also does not make it easy to tell how exhaustive the ticker coverage is or how users should evaluate the quality of the ‘reasoned’ links beyond the brief grading labels.

Review status

69 days ago #1265 ↓ -2

Last evaluated 69 days ago. Current rank #1265. Down 2 spots in the rankings.

Score history

82

Related listings

Primus AI Researcher – Free screenshot

Research / Knowledge Work

Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.

Below the Fold — A New York Times X-Ray Dashboard screenshot

Research / Data Visualization

An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.

CAD-Bench screenshot
#302 CAD-Bench
88

Research / Knowledge Work

An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.

Benchmarking Inference Engines on Agentic Workloads screenshot

Research / Knowledge Work

A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.