Switch Stage3 to explicit-only no-why selection, drop bear probe, and set k=1 defaults

Consolidate pending pipeline, structural, and analysis updates

Remove dead retrieval/display helpers and simplify debug paths

Simplify Stage3 chunking to interleave-only and add eval diagnostics

Add eval audit tools, caption-evident set, and logging

Record non-fatal pipeline issues in eval JSONL outputs

Fix eval_categorized.py to work with eval_pipeline.py output

Add ranking metrics infrastructure to eval pipeline

Add per-tag evidence tracking and wiki extraction script

Add structural tag inference (Stage 3s) and compact eval output

Default min_why to strong_implied; add retrieval gap analysis script

Normalize GT annotations: expand implications, exclude non-evaluable tags

Add tag implication expansion (fox→canine→canid→mammal)

Fix min_why not passed to workers in parallel eval mode

Add --min-why threshold to filter Stage 3 selections by confidence level

Add diagnostic eval metrics, why-distribution tracking, and generic character filter

Add parallel processing to eval pipeline with ThreadPoolExecutor

Add independent character tag metrics to eval pipeline

Improve eval harness: shuffle samples, always write results

Add end-to-end evaluation harness for pipeline metrics