fix: QA review fixes for 0.1.0 release

- Fix README readability example property names
- Add validation for empty references after tokenisation in ROUGE
- Guard against zero sentence count in readability metric
- Implement LRU cache with max size for semantic embeddings
- Add .score property to LexicalResult for API consistency
- Use defensive list copy in composite validators

changelog.md

@@ -5,6 +5,21 @@ All notable changes to Veritext will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Fixed
+
+- Fixed README example using incorrect property names (`grade_level` → `flesch_kincaid_grade`, `reading_ease` → `flesch_reading_ease`)
+- Fixed potential crash in ROUGE metric when all references are empty after tokenisation
+- Fixed potential division by zero in readability metric when text has no sentence endings
+- Fixed unbounded cache growth in `SemanticSimilarity` by implementing LRU eviction with configurable max size
+- Fixed mutable list aliasing in `AllOf` and `AnyOf` composite validators
+
+### Added
+
+- Added `.score` property to `LexicalResult` for API consistency with other result types
+- Added `cache_max_size` parameter to `SemanticSimilarity` (default: 1000 embeddings)
+
 ## [0.1.0] — 2026-02-03
 
 Initial release of Veritext, a semantic text validation framework for Python.