OpenChainGraph Suite · ART-370 · Simulation & replay

Supervisory Scenario Replay (DFAST-lite)

Replays the Federal Reserve's published 2026 supervisory stress test scenario paths (28 variables, baseline and severely adverse, Q1:2026 through Q1:2029) against loss and PPNR coefficient functions you supply, and returns a quarterly profit-and-loss and capital walk. The scenario data is pinned from the Fed's final published release and never fetched at runtime.

Simulation & ReplayFed 2026 supervisory scenariosZero PIIW3C VC §13.11
🔒 All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Not a supervisory result
This tool is NOT the Federal Reserve's model, NOT a DFAST submission, and NOT a supervisory result. It replays loss and PPNR functions you declare over the Fed's officially published scenario paths. The receipt below carries a digest of the exact scenario data used, so the replay is checkable against the source. It is not a claim about what any regulator would conclude.
Scenario source
Board of Governors of the Federal Reserve System, "2026 Supervisory Stress Test Scenarios," released 2026-02-04. Tables 3.A/3.B (baseline) and 4.A/4.B (severely adverse), all 28 published variables, transcribed verbatim from the final PDF (the Fed does not publish a CSV/XLSX for this release). Fixture set + per-file digests: provenance.json. Annual re-pin required each February when the Fed publishes new scenarios.
Presets
Scenario
Bank Parameters
Loss Function (intercept + ∑ coefficient × variable, per quarter)
PPNR Function
Result
Execution Hash & §4 Artifact
SHA-256 execution hash (JCS canonical, RFC 8785):

      

        
        
        
        
        
      

    

  


  
  

    

  







  

    
Ask your agent

    
  

  
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.

  
Run the AINumbers MCP tool `replay_supervisory_scenario`. Task: Replay the Federal Reserve's published 2026 supervisory stress test scenario paths (28 variables, baseline and severely adverse) against user-supplied loss and PPNR coefficient functions.
Call it with arguments: {"policy_parameters":{"scenario":"severely_adverse","starting_capital_mn":5000,"rwa_mn":40000,"tax_rate":0.21,"loss_function":{"intercept":50,"coefficients":{"unemployment_rate":25,"house_price_index":-0.4,"cre_price_index":-0.3}},"ppnr_function":{"intercept":300,"coefficients":{"real_gdp_growth":8,"treasury_10y_yield":10}}}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-370-supervisory-scenario-replay.html#p=v1.H4sIAAAAAAAA_wExAc7-eyJzY2VuYXJpbyI6InNldmVyZWx5X2FkdmVyc2UiLCJzdGFydGluZ19jYXBpdGFsX21uIjo1MDAwLCJyd2FfbW4iOjQwMDAwLCJ0YXhfcmF0ZSI6MC4yMSwibG9zc19mdW5jdGlvbiI6eyJpbnRlcmNlcHQiOjUwLCJjb2VmZmljaWVudHMiOnsidW5lbXBsb3ltZW50X3JhdGUiOjI1LCJob3VzZV9wcmljZV9pbmRleCI6LTAuNCwiY3JlX3ByaWNlX2luZGV4IjotMC4zfX0sInBwbnJfZnVuY3Rpb24iOnsiaW50ZXJjZXB0IjozMDAsImNvZWZmaWNpZW50cyI6eyJyZWFsX2dkcF9ncm93dGgiOjgsInRyZWFzdXJ5XzEweV95aWVsZCI6MTB9fX3H38J_MQEAAA