fix easy task test for updated issue types

replace ambiguous salary issue with date format fix

add content moderation task with real OpenAI Moderation data

replace ambiguous fixes with deterministic ones across all tasks

improve alignment task: replace label swaps with real contamination

add alignment data QA task: 12 issues in LLM instruction-tuning data

expand datasets to include harder real-world scenarios

add fix stage+demo

fixes v1: add per step reward