Figures: /tmp/kdd-modal-results/figure_real_retrieval.png /tmp/kdd-modal-results/figure_semantic_scores.png /tmp/kdd-modal-results/figure_memory_growth.png /tmp/kdd-modal-results/figure_failures.png /tmp/kdd-modal-results/figure_semantic_vs_retrieval.png /tmp/kdd-modal-results/figure_evaluator_coverage.png dataset strategy questions retr_p retr_r hit util lat_ms cost mem sem_cov sem sem_pass faith ctx ans LoCoMo no_memory 1540 0.000 0.000 0.000 0.000 0.01 154.0 0 1.000 0.000 0.000 0.000 0.000 0.000 LoCoMo verbatim 1540 0.057 0.249 0.277 0.277 3.66 1234.2 568 1.000 0.432 0.277 0.277 0.743 0.277 LoCoMo extracted_facts 1540 0.055 0.242 0.271 0.271 3.77 1234.2 568 1.000 0.422 0.271 0.271 0.724 0.271 LoCoMo episodic 1540 0.064 0.278 0.311 0.311 3.92 1234.2 568 1.000 0.465 0.311 0.311 0.774 0.311 LoCoMo hybrid 1540 0.058 0.256 0.284 0.284 3.76 1234.2 568 1.000 0.435 0.284 0.284 0.736 0.284 LongMemEval no_memory 1500 0.000 0.000 0.000 0.000 0.01 150.0 0 1.000 0.000 0.000 0.000 0.000 0.000 LongMemEval verbatim 1500 0.393 0.516 0.575 0.575 5.10 531.4 486 1.000 0.636 0.575 0.575 0.760 0.575 LongMemEval extracted_facts 1500 0.393 0.515 0.573 0.573 5.16 531.4 486 1.000 0.635 0.573 0.573 0.758 0.573 LongMemEval episodic 1500 0.393 0.516 0.575 0.575 5.16 531.4 486 1.000 0.636 0.575 0.575 0.759 0.575 LongMemEval hybrid 1500 0.393 0.516 0.575 0.575 5.10 531.4 486 1.000 0.636 0.575 0.575 0.758 0.575 MemoryArena no_memory 4850 0.000 0.000 0.000 0.000 0.04 485.0 0 1.000 0.000 0.000 0.000 0.000 0.000 MemoryArena verbatim 4850 0.180 0.348 0.356 0.356 0.11 708.3 1 1.000 0.367 0.356 0.356 0.388 0.356 MemoryArena extracted_facts 4850 0.613 0.785 0.794 0.794 0.11 752.3 1 1.000 0.804 0.794 0.794 0.823 0.794 MemoryArena episodic 4850 0.190 0.350 0.359 0.359 0.11 700.3 1 1.000 0.370 0.359 0.359 0.394 0.359 MemoryArena hybrid 4850 0.180 0.347 0.356 0.356 0.14 708.4 1 1.000 0.366 0.356 0.356 0.387 0.356 Raw trace: /tmp/kdd-modal-results/run_20260509_081659_real_raw.json Metrics: /tmp/kdd-modal-results/run_20260509_081659_real_metrics.json Summary TSV: /tmp/kdd-modal-results/run_20260509_081659_real_summary.tsv Modal artifacts synced: raw: /Users/syaikhipin/Documents/Phd/Publish Paper/kdd/experiment/results/run_20260509_151530_real_raw.json metrics: /Users/syaikhipin/Documents/Phd/Publish Paper/kdd/experiment/results/run_20260509_151530_real_metrics.json summary: /Users/syaikhipin/Documents/Phd/Publish Paper/kdd/experiment/results/run_20260509_151530_real_summary.tsv