feat: Implement wait_for_updates action for handling delayed cases and evidence

feat: tighten EscalationROI, add ambiguous medium case, LLM note judge wrapper

feat: Implement multi-round dispute lifecycle with arbitration scoring and related tests

feat: Implement Issuer agent for multi-round dispute lifecycle

refactor: tighten rubric discrimination + LLM path + add running doc

refactor: update difficulty levels and enhance scoring rubrics in documentation and code

Refactor evidence building and improve code readability in iso_adapter.py

fix: squash inflated evidence scores for wrongly contested concedable cases

feat: add card network metadata, trim README, add limitations section

fix: address Codex adversarial review findings

feat: add adversarial evidence, nightmare difficulty, and benchmark splits

feat: harden grading, expand task catalog, add episode persistence

refactor: reorganize source files into core/, evaluation/, runners/, scenarios/ directories