Improve system/hybrid to top benchmark positions

Improve benchmark scores: fix FC detection, add calibration anchors

Pre-benchmark fixes: remove MBFC leakage, add checkpoint/resume, fix scoring, add rate limiting

Fix data leakage: anonymize MBFC references in LLM and Articles mode prompts

Fix methodology.py prompt: align credibility exceptions with MBFC spec

Fix MBFC methodology compliance issues from Gemini/GPT audit

Implement full MBFC 2025 methodology compliance

Fix hybrid mode: eliminate double synthesis, add smart routing and LLM synthesis

Last updated code by Ilyas

Refactor: anti-contamination prompts and standard FactScore decomposition

first commit