seed: 17 data: root: datasets/mvp image_size: 224 train_size: 30000 validation_size: 3000 test_id_size: 3000 test_ood_size: 3000 num_objects: 2 model: backbone: tiny clip_model: openai/clip-vit-base-patch32 siglip2_model: google/siglip2-giant-opt-patch16-384 state_dim: 256 num_visual_slots: 6 num_text_slots: 3 extractor_layers: 2 num_heads: 8 dropout: 0.1 training: batch_size: 32 learning_rate: 0.0003 weight_decay: 0.01 epochs: 10 num_workers: 0 type_weight: 0.5 alignment_weight: 0.2 contrastive_temperature: 0.1 output_dir: artifacts/prototype prototype: enabled: true weight: 0.2 evaluation: gates: text_fact_rule_f1: 0.98 visual_fact_f1: 0.90 cross_modal_recall_at_1: 0.80 hard_negative_recall_at_1: 0.75 ood_fact_f1: 0.80 null_slot_accuracy: 0.95