# Find runs by invocation_id
MLflow:search_runs_by_tags(experiment_id, {"invocation_id": "<invocation_id>"})

# Query for example model/task runs
MLflow:query_runs(experiment_id, "tags.model LIKE '%<model>%'")
MLflow:query_runs(experiment_id, "tags.task_name LIKE '%<task_name>%'")

# Get a config from run's artifacts
MLflow:get_artifact_content(run_id, "config.yml")

# Get nested stats from run's artifacts
MLflow:get_artifact_content(run_id, "artifacts/eval_factory_metrics.json")

uv run --with pandas python3 << 'EOF'
import pandas as pd
# ... compute deltas, averages, etc.
EOF

<harness>.<task>/
├── artifacts/
│   ├── config.yml                # Fully resolved config used during the evaluation
│   ├── launcher_unresolved_config.yaml # Unresolved config passed to the launcher
│   ├── results.yml               # All results in YAML format
│   ├── eval_factory_metrics.json # Runtime stats (latency, tokens count, memory)
│   ├── report.html               # Request-Response Pairs samples in HTML format (if enabled)
│   └── report.json               # Request-Response Pairs samples in JSON format (if enabled)
└── logs/
    ├── client-*.log              # Evaluation client
    ├── server-*-N.log            # Deployment per node
    ├── slurm-*.log               # Slurm job
    └── proxy-*.log               # Request proxy