feat: add additional imports for model evaluation and cross-validation

feat: add figure generation script for training results visualization

feat: enhance analysis result with estimated bitrate and XAI verdict integration

feat: add XAI inference for explainable predictions in analysis results

feat: add XAI explanation models for enhanced interpretability in analysis results

feat: integrate XAI service for enhanced explainability in analysis

fix: rename variable for clarity in compute_stats function

feat: add feature statistics computation from training CSV for enhanced analysis

feat: add XAI inference service for explainable predictions with detailed feature contributions

feat: implement resume functionality in batch feature extraction to skip processed samples

feat: enhance visualization pipeline with additional figures and manifest support

feat: add dataset statistics and class balance visualizations to enhance analysis capabilities

feat: refactor worker function for batch feature extraction to support multiprocessing

feat: implement parallel processing for batch feature extraction to improve performance

feat: extend analysis route to support multiple source types including TikTok, Instagram, SoundCloud, and Twitter

feat: add full training and evaluation pipeline for AURIS

feat: enhance training pipeline with multi-model evaluation and detailed metrics

feat: enhance feature extraction with additional spectral and temporal metrics

feat: extend AudioFeatures dataclass with additional spectral and temporal metrics

feat: add spectral rolloff and MFCC delta features to audio extraction

docs: update README and .env.example with optional yt-dlp cookie authentication details

test: add tests for YouTubeDownloader error handling and authentication

fix: improve error handling and logging in YouTubeAnalysisService

feat: enhance YouTubeDownloader with cookie handling and error normalization

feat: enhance YouTubeDownloader with cookie support and player client cycling

fix: gitignore models/data and add logging to feature extraction

fix: add debug logging for vocal extraction failures in extract_sample_features

fix: add return type annotations and docstrings for clarity in Wav2Vec2MusicClassifier and AudioDataset

fix: add type annotation to _parse_response method for clarity

fix: refactor import statement and format model path for readability

fix: add docstring to Wav2Vec2DetectorService constructor for clarity

fix: add docstring to MetaClassifierService constructor for clarity

fix: add return type annotation to Wav2Vec2DetectorService constructor

fix: add return type annotation to MetaClassifierService constructor

feat: add wav2vec2 classifier for AI music detection with training loop and dataset handling

feat: add AURIS classifier training module with model evaluation and feature importance

feat: implement batch feature extraction for AURIS training pipeline

feat: add evaluation framework for AURIS models with metrics computation

feat: add SONICS dataset loader for AURIS training pipeline

feat: add AURIS training pipeline module for dataset loading and model training

feat: add wav2vec2 inference service for AURIS music detection

feat: implement meta-classifier service for AURIS score fusion

feat: update decisionSource assertion to check for auris_ prefix

feat: change decision_source type to string in AnalysisSummary schema

feat: update requirements.txt to include CLAP and FST dependencies

feat: integrate CLAP and FST detection into score fusion process

feat: add CLAP and FST indicators to score fusion results

feat: initialize CLAPDetectorService and FSTClientService in analyze.py

feat: add CLAPDetectorService and FSTClientService imports in analyze.py

feat: add parsing functions for CLAP and FST results in score fusion