Scores a batch of resolved probabilistic forecasts (a stated probability paired with the realized yes/no outcome) using two textbook proper scoring rules: the Brier score and the logarithmic score, plus a Brier Skill Score against a reference forecast you choose. Each forecast can carry an optional, informational subject-matter category label so results break out per category below, supplied by you rather than derived from any rule. Lower is better for both scores, 0 is a perfect score, and a forecaster's best strategy under both is to report their true belief, which is what makes them "proper."
| Probability | Outcome | Category |
|---|
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 `compute_forecast_accuracy_score`. Task: Score a batch of resolved probabilistic forecasts against realized outcomes using the Brier score and logarithmic score, plus a Brier Skill Score against a reference forecast, with an optional informational per-category breakdown.
Call it with arguments: {"policy_parameters":{}}
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-657-forecast-accuracy-scorer.html#p=v1.H4sIAAAAAAAA_wECAP3_e31Dv6ajAgAAAA