Add the missing Claim 5 page: rerun the COMPAS case study on real ProPublica data; optimal fair thresholds differ by 0.08-0.13 across groups and forcing a single threshold costs 52-341 utility

Map exact current anchored claims to existing independent evidence

Repurpose low-score audit: exact calibrated fairness reproduction

Update logbook: Repro - NanoQuant: Efficient Sub-1-bit Quantization of Large Language Models

Update logbook: Repro - NanoQuant: Efficient Sub-1-bit Quantization of Large Language Models

initial commit