Claude 3e0f3d007c fix: correct COI formulation to measure price erosion over time
The fundamental error was treating COI as instantaneous margin × alpha.
The corrected formulation is:

    COI = E[p_start] - p_transaction

This measures price erosion over time, capturing how agents using
multiple sessions gather information and drive prices down.

Key changes:
- Add coi.py with COIWindow, COITracker, and compute_multi_session_coi
- Add separability.py with KL-divergence behavioral classification
- Update simplified_env.py to track initial prices and compute windowed COI
- Add corrected COI metrics (coi_*_corrected) alongside legacy metrics

The new approach:
1. Tracks prices at episode start as E[p] (expected price)
2. Computes transaction prices as p (actual sale price)
3. Measures leak as the difference (price erosion)
4. Includes order statistic erosion (Theorem 1: N agents -> min price)
2026-01-26 15:23:32 +00:00
2025-11-04 14:29:30 +00:00
2026-01-22 21:02:10 +01:00
2026-01-21 19:11:54 +01:00
2026-01-23 10:37:48 +01:00
2025-11-29 17:50:16 +01:00

PHANTOM

Build PDF TPU Research Cloud Vercel Deploy Vercel Deploy

Description
No description provided
Readme 19 MiB
Languages
Python 48.8%
TeX 22.2%
Jupyter Notebook 14.1%
TypeScript 9.6%
Shell 2.9%
Other 2.3%