#calibration

Trustworthy AI for satellite conjunction triage using calibrated ML, Bayesian logistic regression, and uncertainty-aware escalation on public CDM data.

Author, validate, preview, calibrate, diff, and export criterion-level AI evaluation rubrics.

Open, experimental specification (v0.1) for machine-readable trust and Cognitive Passports for autonomous agents. A proposal, not a standard.

Claude Haiku 5.5 as a decision model, benchmarked head-to-head against Jev and the OpenAI Decisions API

Autonomous LLM agent trading Polymarket with fake money. Objective: profit after realistic costs. Diagnostic: Brier score vs. the market. Every fill walks a real order book.