artifact_id: duckdb-wasm-metricflow
rubric_version: 2.8.0
formula: baseline
judges:
- openai:gpt-5.6-terra
rows:
- criterion_id: DEL-01
  category: delivery
  checker: program
  verdict: 'yes'
  points_possible: 10
  points_earned: 10.0
  evidence: ''
  agreement: null
  votes: 0
- criterion_id: DEL-02
  category: delivery
  checker: program
  verdict: 'yes'
  points_possible: 0
  points_earned: -4.0
  evidence: 1 console errors
  agreement: null
  votes: 0
- criterion_id: DEL-03
  category: delivery
  checker: program
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: ''
  agreement: null
  votes: 0
- criterion_id: COR-01
  category: correctness
  checker: program
  verdict: na
  points_possible: 0
  points_earned: 0.0
  evidence: the brief has no reference numbers
  agreement: null
  votes: 0
- criterion_id: WRK-01
  category: working
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked the dashboard for page-level failures, empty shells, error states, spinners, and missing
    data across the visible panels.
  agreement: 1.0
  votes: 1
- criterion_id: WRK-02
  category: working
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked each visible chart and metric panel for blank content, error messages, loading indicators,
    or placeholders.
  agreement: 1.0
  votes: 1
- criterion_id: HON-01
  category: honesty
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked the horizontal open-issues bar charts' value axes. Both visible value axes begin at
    0.
  agreement: 1.0
  votes: 1
- criterion_id: HON-02
  category: honesty
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked chart titles, card labels, and displayed values for rate/share/% wording paired with
    plainly count-like values.
  agreement: 1.0
  votes: 1
- criterion_id: HON-03
  category: honesty
  checker: judge
  verdict: 'yes'
  points_possible: 0
  points_earned: -12.0
  evidence: 'feature: lavender bar vs blue line | bug: lavender bar vs orange line | task: lavender bar
    vs green line | other: lavender bar vs gray line'
  agreement: 1.0
  votes: 1
- criterion_id: HON-04
  category: honesty
  checker: judge
  verdict: na
  points_possible: 0
  points_earned: 0.0
  evidence: Checked the visible charts for two independent value axes used in a single chart without series-to-axis
    mapping.
  agreement: 1.0
  votes: 1
- criterion_id: HON-05
  category: honesty
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked side-by-side peer charts for the same measure shown on different scales without disclosure.
  agreement: 1.0
  votes: 1
- criterion_id: HON-06
  category: honesty
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked line charts' category ordering. The visible line charts use weekly/monthly time sequences
    on their x-axes.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-01
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked all charts for pie/donut, 3D, trends shown as tables or pies, and rankings shown as
    lines.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-02
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked whether two or more charts use a form that hides their primary comparison.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-03
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked multi-series/category charts for distinguishable colors and label or legend mapping.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-04
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: 'Checked ranked category comparisons: the issue-category bars descend by value (feature, bug,
    other, task), and the milestone bars also descend by value (No milestone, v2.0, then smaller milestones).'
  agreement: 1.0
  votes: 1
- criterion_id: FRM-05
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked whether any standalone metric is rendered as a gauge or one-bar chart rather than
    a number.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-07
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked for duplicate charts showing the same data in the same form.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-08
  category: form
  checker: judge
  verdict: 'yes'
  points_possible: 0
  points_earned: -8.0
  evidence: ISSUES_OPENED_PER_WEEK — the approximately 440-issue spike around June dominates the 0–400+
    scale, making the much smaller regular weekly values difficult to compare
  agreement: 1.0
  votes: 1
- criterion_id: FRM-06
  category: form
  checker: judge
  verdict: cannot_determine
  points_possible: 0
  points_earned: 0.0
  evidence: Checked the first and last points of the visible time series for abrupt endpoint changes and
    looked for partial-period annotations.
  agreement: null
  votes: 1
- criterion_id: LEG-01
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked chart titles, tick labels, legends, and data labels across all visible charts.
  agreement: 1.0
  votes: 1
- criterion_id: LEG-02
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked all visible charts for overlapping text.
  agreement: 1.0
  votes: 1
- criterion_id: LEG-03
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked visible titles, labels, metric-card text, chart labels, and query text for clipping,
    ellipses, or overflow.
  agreement: 1.0
  votes: 1
- criterion_id: LEG-04
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked text legibility using the full-resolution tiles, including chart ticks, legends, metric-card
    supporting text, and query blocks.
  agreement: 1.0
  votes: 1
- criterion_id: LEG-05
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked whether the plotted bars and lines remain distinguishable at their displayed sizes.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-01
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked all headline tiles and chart axes for count, duration, currency, or percentage units.
    The duration tiles use “d” and say “Avg days to close” / “Median bug fix”; count charts label their
    measures as open issues or issues opened.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-02
  category: labeling
  checker: judge
  verdict: 'yes'
  points_possible: 0
  points_earned: -4.0
  evidence: 'Metric registry: “open_issue_count” | Metric registry: “avg_time_to_close” | Metric registry:
    “issues_opened_per_week” | Metric registry: “bug_fix_velocity” | Chart title: “OPEN_ISSUE_COUNT ·
    BY DIMENSION” | Chart title: “AVG_TIME_TO_CLOSE · WEEKLY TREND BY CATEGORY” | Chart title: “ISSUES_OPENED_PER_WEEK
    & BUG_FIX_VELOCITY”'
  agreement: 1.0
  votes: 1
- criterion_id: LBL-03
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked whether the dashboard states its subject and shows a reporting period. It is titled
    “dbt Semantic Layer · MetricFlow Metrics” and covers issue metrics; charts show dated weekly/monthly
    axes spanning Jun 2025 through Oct 2026.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-04
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked each headline tile for a period or time context. “Issues opened last week,” “Avg days
    to close (4 wk),” and “Median bug fix (4 wk)” state periods; open issues are described in the registry
    as currently open.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-05
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked all visible charts for a title or label describing the content. The bar charts are
    under “OPEN_ISSUE_COUNT · BY DIMENSION,” the line chart is under “AVG_TIME_TO_CLOSE · WEEKLY TREND
    BY CATEGORY,” and the lower pair is under “ISSUES_OPENED_PER_WEEK & BUG_FIX_VELOCITY.”
  agreement: 1.0
  votes: 1
- criterion_id: LBL-07
  category: labeling
  checker: judge
  verdict: na
  points_possible: 0
  points_earned: 0.0
  evidence: Checked visible tiles and charts for percentage or share measures with an unclear denominator.
    No percentages or share/rate values are shown.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-08
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Compared chart titles and axis labels with the plotted measures. Open-issue charts use open-issue
    counts, the trend chart uses average days to close, and the lower charts use issues opened and median
    days to close; no visible mismatch was found.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-09
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked visible headline values against the displayed component values and chart labeling.
    The open-issue category bars shown as 282, 201, 23, and 5 sum to the 511 Open issues headline; no
    conflicting dates, totals, or statements are visible.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-01
  category: layout
  checker: judge
  verdict: 'yes'
  points_possible: 0
  points_earned: -5.0
  evidence: Large unused blank band to the right of the dashboard content across the page
  agreement: 1.0
  votes: 1
- criterion_id: LAY-02
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked alignment of the metric-registry cards, snapshot cards, paired charts, and compiled-query
    panels.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-04
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked whether registry/detail content or query text is placed above or given more emphasis
    than the metric snapshot and charts.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-05
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked whether card fills, borders, colored values, and other decorative treatment outweigh
    the data visualizations.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-06
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked color usage in the bar and line charts and the metric snapshot cards for unexplained
    or misleading encodings.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-07
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Checked visible text and components for placeholders, debug output, test elements, or accidental
    scaffolding.
  agreement: 1.0
  votes: 1
- criterion_id: EXC-01
  category: excellence
  checker: judge
  verdict: 'no'
  points_possible: 10
  points_earned: 0.0
  evidence: Checked the page title, metric registry, snapshot cards, and chart headings for a narrative
    finding supported by a chart.
  agreement: 1.0
  votes: 1
- criterion_id: EXC-03
  category: excellence
  checker: judge
  verdict: 'no'
  points_possible: 3
  points_earned: 0.0
  evidence: Checked all four headline snapshot cards for a prior-period comparison, target, or peer benchmark.
  agreement: 1.0
  votes: 1
- criterion_id: EXC-04
  category: excellence
  checker: judge
  verdict: 'no'
  points_possible: 6
  points_earned: 0.0
  evidence: Checked the bar and line charts for annotated spikes/dips, target lines, or a singled-out
    highlighted mark.
  agreement: 1.0
  votes: 1
- criterion_id: EXC-06
  category: excellence
  checker: judge
  verdict: 'no'
  points_possible: 5
  points_earned: 0.0
  evidence: Checked chart color usage for mostly neutral-gray data with one accent reserved for the subject.
  agreement: 1.0
  votes: 1
- criterion_id: EXC-07
  category: excellence
  checker: judge
  verdict: 'no'
  points_possible: 4
  points_earned: 0.0
  evidence: Checked the multi-series weekly trend chart for direct labels on its series rather than reliance
    on its legend.
  agreement: 1.0
  votes: 1
- criterion_id: EXC-08
  category: excellence
  checker: judge
  verdict: 'yes'
  points_possible: 5
  points_earned: 5.0
  evidence: '"Number of currently open non-epic issues." | "filter: state = ''OPEN'' AND issue_category
    != ''epic''" | "Average hours from open to close across non-epic issues." | "filter: issue_category
    = ''bug''" | "WHERE state = ''OPEN'' AND issue_category != ''epic''" | "GROUP BY 1 HAVING COUNT(*)
    >= 3"'
  agreement: 1.0
  votes: 1
- criterion_id: BRF-01
  category: answers_brief
  checker: judge
  verdict: na
  points_possible: 0
  points_earned: 0.0
  evidence: judged without a brief
  agreement: null
  votes: 0
- criterion_id: BRF-02
  category: answers_brief
  checker: judge
  verdict: na
  points_possible: 0
  points_earned: 0.0
  evidence: judged without a brief
  agreement: null
  votes: 0
score: 0.331
category_scores:
  delivery: 0.6
  excellence: 0.152
agreement: 1.0
judge_errors: []
votes:
- criterion_id: WRK-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked the dashboard for page-level failures, empty shells, error states, spinners, and missing
    data across the visible panels.
  round: 1
- criterion_id: WRK-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked each visible chart and metric panel for blank content, error messages, loading indicators,
    or placeholders.
  round: 1
- criterion_id: HON-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked the horizontal open-issues bar charts' value axes. Both visible value axes begin at
    0.
  round: 1
- criterion_id: HON-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked chart titles, card labels, and displayed values for rate/share/% wording paired with
    plainly count-like values.
  round: 1
- criterion_id: HON-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: 'feature: lavender bar vs blue line | bug: lavender bar vs orange line | task: lavender bar
    vs green line | other: lavender bar vs gray line'
  round: 1
- criterion_id: HON-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: na
  evidence: Checked the visible charts for two independent value axes used in a single chart without series-to-axis
    mapping.
  round: 1
- criterion_id: HON-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked side-by-side peer charts for the same measure shown on different scales without disclosure.
  round: 1
- criterion_id: HON-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked line charts' category ordering. The visible line charts use weekly/monthly time sequences
    on their x-axes.
  round: 1
- criterion_id: FRM-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked all charts for pie/donut, 3D, trends shown as tables or pies, and rankings shown as
    lines.
  round: 1
- criterion_id: FRM-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked whether two or more charts use a form that hides their primary comparison.
  round: 1
- criterion_id: FRM-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked multi-series/category charts for distinguishable colors and label or legend mapping.
  round: 1
- criterion_id: FRM-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: 'Checked ranked category comparisons: the issue-category bars descend by value (feature, bug,
    other, task), and the milestone bars also descend by value (No milestone, v2.0, then smaller milestones).'
  round: 1
- criterion_id: FRM-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked whether any standalone metric is rendered as a gauge or one-bar chart rather than
    a number.
  round: 1
- criterion_id: FRM-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked for duplicate charts showing the same data in the same form.
  round: 1
- criterion_id: FRM-08
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: ISSUES_OPENED_PER_WEEK — the approximately 440-issue spike around June dominates the 0–400+
    scale, making the much smaller regular weekly values difficult to compare
  round: 1
- criterion_id: FRM-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: cannot_determine
  evidence: Checked the first and last points of the visible time series for abrupt endpoint changes and
    looked for partial-period annotations.
  round: 1
- criterion_id: LEG-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked chart titles, tick labels, legends, and data labels across all visible charts.
  round: 1
- criterion_id: LEG-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked all visible charts for overlapping text.
  round: 1
- criterion_id: LEG-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked visible titles, labels, metric-card text, chart labels, and query text for clipping,
    ellipses, or overflow.
  round: 1
- criterion_id: LEG-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked text legibility using the full-resolution tiles, including chart ticks, legends, metric-card
    supporting text, and query blocks.
  round: 1
- criterion_id: LEG-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked whether the plotted bars and lines remain distinguishable at their displayed sizes.
  round: 1
- criterion_id: LBL-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked all headline tiles and chart axes for count, duration, currency, or percentage units.
    The duration tiles use “d” and say “Avg days to close” / “Median bug fix”; count charts label their
    measures as open issues or issues opened.
  round: 1
- criterion_id: LBL-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: 'Metric registry: “open_issue_count” | Metric registry: “avg_time_to_close” | Metric registry:
    “issues_opened_per_week” | Metric registry: “bug_fix_velocity” | Chart title: “OPEN_ISSUE_COUNT ·
    BY DIMENSION” | Chart title: “AVG_TIME_TO_CLOSE · WEEKLY TREND BY CATEGORY” | Chart title: “ISSUES_OPENED_PER_WEEK
    & BUG_FIX_VELOCITY”'
  round: 1
- criterion_id: LBL-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked whether the dashboard states its subject and shows a reporting period. It is titled
    “dbt Semantic Layer · MetricFlow Metrics” and covers issue metrics; charts show dated weekly/monthly
    axes spanning Jun 2025 through Oct 2026.
  round: 1
- criterion_id: LBL-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked each headline tile for a period or time context. “Issues opened last week,” “Avg days
    to close (4 wk),” and “Median bug fix (4 wk)” state periods; open issues are described in the registry
    as currently open.
  round: 1
- criterion_id: LBL-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked all visible charts for a title or label describing the content. The bar charts are
    under “OPEN_ISSUE_COUNT · BY DIMENSION,” the line chart is under “AVG_TIME_TO_CLOSE · WEEKLY TREND
    BY CATEGORY,” and the lower pair is under “ISSUES_OPENED_PER_WEEK & BUG_FIX_VELOCITY.”
  round: 1
- criterion_id: LBL-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: na
  evidence: Checked visible tiles and charts for percentage or share measures with an unclear denominator.
    No percentages or share/rate values are shown.
  round: 1
- criterion_id: LBL-08
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Compared chart titles and axis labels with the plotted measures. Open-issue charts use open-issue
    counts, the trend chart uses average days to close, and the lower charts use issues opened and median
    days to close; no visible mismatch was found.
  round: 1
- criterion_id: LBL-09
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked visible headline values against the displayed component values and chart labeling.
    The open-issue category bars shown as 282, 201, 23, and 5 sum to the 511 Open issues headline; no
    conflicting dates, totals, or statements are visible.
  round: 1
- criterion_id: LAY-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: Large unused blank band to the right of the dashboard content across the page
  round: 1
- criterion_id: LAY-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked alignment of the metric-registry cards, snapshot cards, paired charts, and compiled-query
    panels.
  round: 1
- criterion_id: LAY-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked whether registry/detail content or query text is placed above or given more emphasis
    than the metric snapshot and charts.
  round: 1
- criterion_id: LAY-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked whether card fills, borders, colored values, and other decorative treatment outweigh
    the data visualizations.
  round: 1
- criterion_id: LAY-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked color usage in the bar and line charts and the metric snapshot cards for unexplained
    or misleading encodings.
  round: 1
- criterion_id: LAY-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked visible text and components for placeholders, debug output, test elements, or accidental
    scaffolding.
  round: 1
- criterion_id: EXC-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked the page title, metric registry, snapshot cards, and chart headings for a narrative
    finding supported by a chart.
  round: 1
- criterion_id: EXC-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked all four headline snapshot cards for a prior-period comparison, target, or peer benchmark.
  round: 1
- criterion_id: EXC-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked the bar and line charts for annotated spikes/dips, target lines, or a singled-out
    highlighted mark.
  round: 1
- criterion_id: EXC-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked chart color usage for mostly neutral-gray data with one accent reserved for the subject.
  round: 1
- criterion_id: EXC-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked the multi-series weekly trend chart for direct labels on its series rather than reliance
    on its legend.
  round: 1
- criterion_id: EXC-08
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: '"Number of currently open non-epic issues." | "filter: state = ''OPEN'' AND issue_category
    != ''epic''" | "Average hours from open to close across non-epic issues." | "filter: issue_category
    = ''bug''" | "WHERE state = ''OPEN'' AND issue_category != ''epic''" | "GROUP BY 1 HAVING COUNT(*)
    >= 3"'
  round: 1