arize-experiment（阿里兹实验）

Arize Experiment Skill

Concepts

• Experiment = a named evaluation run against a specific dataset version, containing one run per example
• Experiment Run = the result of processing one dataset example -- includes the model output, optional evaluations, and optional metadata
• Dataset = a versioned collection of examples; every experiment is tied to a dataset and a specific dataset version
• Evaluation = a named metric attached to a run (e.g., correctness, relevance), with optional label, score, and explanation

The typical flow: export a dataset → process each example → collect outputs and evaluations → create an experiment with the runs.

Prerequisites

Proceed directly with the task — run the ax command you need. Do NOT check versions, env vars, or profiles upfront.

If an ax command fails, troubleshoot based on the error:

• command not found or version error → see references/ax-setup.md
• 401 Unauthorized / missing API key → run ax profiles show to inspect the current profile. If the profile is missing or the API key is wrong: check .env for ARIZE_API_KEY and use it to create/update the profile via references/ax-profiles.md. If .env has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys)
• Space ID unknown → check .env for ARIZE_SPACE_ID, or run ax spaces list -o json, or ask the user
• Project unclear → check .env for ARIZE_DEFAULT_PROJECT, or ask, or run ax projects list -o json --limit 100 and present as selectable options

List Experiments: ax experiments list

Browse experiments, optionally filtered by dataset. Output goes to stdout.

ax experiments list
ax experiments list --dataset-id DATASET_ID --limit 20
ax experiments list --cursor CURSOR_TOKEN
ax experiments list -o json

Flags

Get Experiment: ax experiments get

Quick metadata lookup -- returns experiment name, linked dataset/version, and timestamps.

ax experiments get EXPERIMENT_ID
ax experiments get EXPERIMENT_ID -o json

Flags

Response fields

Export Experiment: ax experiments export

Download all runs to a file. By default uses the REST API; pass --all to use Arrow Flight for bulk transfer.

ax experiments export EXPERIMENT_ID
# -> experiment_abc123_20260305_141500/runs.json

ax experiments export EXPERIMENT_ID --all
ax experiments export EXPERIMENT_ID --output-dir ./results
ax experiments export EXPERIMENT_ID --stdout
ax experiments export EXPERIMENT_ID --stdout | jq '.[0]'

Flags

REST vs Flight (--all)

• REST (default): Lower friction -- no Arrow/Flight dependency, standard HTTPS ports, works through any corporate proxy or firewall. Limited to 500 runs per page.
• Flight (--all): Required for experiments with more than 500 runs. Uses gRPC+TLS on a separate host/port (flight.arize.com:443) which some corporate networks may block.

Agent auto-escalation rule: If a REST export returns exactly 500 runs, the result is likely truncated. Re-run with --all to get the full dataset.

Output is a JSON array of run objects:

[
  {
    "id": "run_001",
    "example_id": "ex_001",
    "output": "The answer is 4.",
    "evaluations": {
      "correctness": { "label": "correct", "score": 1.0 },
      "relevance": { "score": 0.95, "explanation": "Directly answers the question" }
    },
    "metadata": { "model": "gpt-4o", "latency_ms": 1234 }
  }
]

Create Experiment: ax experiments create

Create a new experiment with runs from a data file.

ax experiments create --name "gpt-4o-baseline" --dataset-id DATASET_ID --file runs.json
ax experiments create --name "claude-test" --dataset-id DATASET_ID --file runs.csv

Flags

Passing data via stdin

Use --file - to pipe data directly — no temp file needed:

echo '[{"example_id": "ex_001", "output": "Paris"}]' | ax experiments create --name "my-experiment" --dataset-id DATASET_ID --file -

# Or with a heredoc
ax experiments create --name "my-experiment" --dataset-id DATASET_ID --file - << 'EOF'
[{"example_id": "ex_001", "output": "Paris"}]
EOF

Required columns in the runs file

Additional columns are passed through as additionalProperties on the run.

Delete Experiment: ax experiments delete

ax experiments delete EXPERIMENT_ID
ax experiments delete EXPERIMENT_ID --force   # skip confirmation prompt

Flags

Experiment Run Schema

Each run corresponds to one dataset example:

{
  "example_id": "required -- links to dataset example",
  "output": "required -- the model/system output for this example",
  "evaluations": {
    "metric_name": {
      "label": "optional string label (e.g., 'correct', 'incorrect')",
      "score": "optional numeric score (e.g., 0.95)",
      "explanation": "optional freeform text"
    }
  },
  "metadata": {
    "model": "gpt-4o",
    "temperature": 0.7,
    "latency_ms": 1234
  }
}

Evaluation fields

At least one of label, score, or explanation should be present per evaluation.

Workflows

Run an experiment against a dataset

1. Find or create a dataset: ax datasets list ax datasets export DATASET_ID --stdout | jq 'length'
2. Export the dataset examples: ax datasets export DATASET_ID
3. Process each example through your system, collecting outputs and evaluations
4. Build a runs file (JSON array) with example_id, output, and optional evaluations: [{"example_id": "ex_001", "output": "4", "evaluations": {"correctness": {"label": "correct", "score": 1.0}}}, {"example_id": "ex_002", "output": "Paris", "evaluations": {"correctness": {"label": "correct", "score": 1.0}}}]
5. Create the experiment: ax experiments create --name "gpt-4o-baseline" --dataset-id DATASET_ID --file runs.json
6. Verify: ax experiments get EXPERIMENT_ID

Compare two experiments

1. Export both experiments: ax experiments export EXPERIMENT_ID_A --stdout > a.json ax experiments export EXPERIMENT_ID_B --stdout > b.json
2. Compare evaluation scores by example_id: # Average correctness score for experiment A jq '[.[] |.evaluations.correctness.score] | add / length' a.json # Same for experiment B jq '[.[] |.evaluations.correctness.score] | add / length' b.json
3. Find examples where results differ: jq -s '.[0] as $a |.[1][] |. as $run | {example_id: $run.example_id, b_score: $run.evaluations.correctness.score, a_score: ($a[] | select(.example_id == $run.example_id) |.evaluations.correctness.score)}' a.json b.json
4. Score distribution per evaluator (pass/fail/partial counts): # Count by label for experiment A jq '[.[] |.evaluations.correctness.label] | group_by(.) | map({label:.[0], count: length})' a.json
5. Find regressions (examples that passed in A but fail in B): jq -s ' [.[0][] | select(.evaluations.correctness.label == "correct")] as $passed_a | [.[1][] | select(.evaluations.correctness.label!= "correct") | select(.example_id as $id | $passed_a | any(.example_id == $id))] ' a.json b.json

Statistical significance note: Score comparisons are most reliable with ≥ 30 examples per evaluator. With fewer examples, treat the delta as directional only — a 5% difference on n=10 may be noise. Report sample size alongside scores: jq 'length' a.json.

Download experiment results for analysis

1. ax experiments list --dataset-id DATASET_ID -- find experiments
2. ax experiments export EXPERIMENT_ID -- download to file
3. Parse: jq '.[] | {example_id, score:.evaluations.correctness.score}' experiment_*/runs.json

Pipe export to other tools

# Count runs
ax experiments export EXPERIMENT_ID --stdout | jq 'length'

# Extract all outputs
ax experiments export EXPERIMENT_ID --stdout | jq '.[].output'

# Get runs with low scores
ax experiments export EXPERIMENT_ID --stdout | jq '[.[] | select(.evaluations.correctness.score < 0.5)]'

# Convert to CSV
ax experiments export EXPERIMENT_ID --stdout | jq -r '.[] | [.example_id, .output, .evaluations.correctness.score] | @csv'

Related Skills

• arize-dataset: Create or export the dataset this experiment runs against → use arize-dataset first
• arize-prompt-optimization: Use experiment results to improve prompts → next step is arize-prompt-optimization
• arize-trace: Inspect individual span traces for failing experiment runs → use arize-trace
• arize-link: Generate clickable UI links to traces from experiment runs → use arize-link

Troubleshooting

Save Credentials for Future Use

See references/ax-profiles.md § Save Credentials for Future Use.