artifact_id: graphene
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: BRF-01
  category: answers_brief
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: 'Checked all six reader questions against the visible dashboard sections: current-status KPIs;
    backlog trend charts; triage chart, response-rate chart, and oldest-first queue; area and adapter
    charts; epic-progress table; and assignee chart plus most-requested-issues table.'
  agreement: 1.0
  votes: 1
- criterion_id: BRF-02
  category: answers_brief
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Compared visible requested content with non-brief content. The page is overwhelmingly occupied
    by charts, KPIs, and tables that map to the requested issue-health questions; the only apparent extra
    is the small static-HTML-export notice.
  agreement: 1.0
  votes: 1
- criterion_id: WRK-01
  category: working
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed the full dashboard for page-level failures, error states, spinners, and widespread
    empty 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 table panel for blank, loading, placeholder, or error content.
  agreement: 1.0
  votes: 1
- criterion_id: HON-01
  category: honesty
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed visible bar and area charts, including open issues by type, weekly opened/closed,
    triage status, area, adapter, and assignee charts, for non-zero value-axis baselines.
  agreement: 1.0
  votes: 1
- criterion_id: HON-02
  category: honesty
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Compared rate/share/% labels with plotted scales and values, including “New issues answered
    within 48h (%)” and epic “Complete (%)”.
  agreement: 1.0
  votes: 1
- criterion_id: HON-03
  category: honesty
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Compared repeated type-category colors across charts with Feature, Bug, Task, and Other legends.
  agreement: 1.0
  votes: 1
- criterion_id: HON-04
  category: honesty
  checker: judge
  verdict: na
  points_possible: 0
  points_earned: 0.0
  evidence: Checked charts for multiple independent value axes and unclear 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: Compared the side-by-side “Open issues by area” and “Open issues by adapter” charts; their
    axes visibly show their respective scales.
  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 for connections between unordered categories; visible line charts use
    weekly/monthly time sequences.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-01
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed all charts for pies/donuts, 3D treatments, trends rendered as tables or pies, and
    rankings rendered 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 comparison-hiding forms.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-03
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed multi-series/category charts, including issue type, triage-age, opened-versus-closed,
    area, adapter, and assignee charts, for distinguishable colors and matching legends.
  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 for ordering: areas, adapters, assignees, epics, and
    most-requested issues.'
  agreement: 1.0
  votes: 1
- criterion_id: FRM-05
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed the KPI numbers and charts for a single value unnecessarily rendered as a gauge or
    one-bar chart.
  agreement: 1.0
  votes: 1
- criterion_id: FRM-07
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Compared chart topics and forms to identify any 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: “Opened vs. closed per week” — the roughly 440 opened-issues spike forces a 0–500 scale, making
    the much smaller normal weekly opened/closed counts difficult to compare
  agreement: 1.0
  votes: 1
- criterion_id: FRM-06
  category: form
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: 'Reviewed the starts and ends of the visible time series: open issues by type, opened versus
    closed per week, and new issues answered within 48 hours.'
  agreement: 1.0
  votes: 1
- criterion_id: LEG-01
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed chart titles, legends, axes, tick labels, bar labels, and table text across the full-resolution
    tiles for visible collisions.
  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 charts for overlapping text, including the backlog, weekly opened-vs.-closed,
    triage, response-rate, area, adapter, and assignee charts.
  agreement: 1.0
  votes: 1
- criterion_id: LEG-03
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed visible titles, labels, legends, axes, and table columns within each tile for clipping,
    ellipses, or content pushed outside its card.
  agreement: 1.0
  votes: 1
- criterion_id: LEG-04
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Used the full-resolution tiles to inspect small supporting text, axis ticks, legends, chart
    labels, and table text for readability.
  agreement: 1.0
  votes: 1
- criterion_id: LEG-05
  category: legibility
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Reviewed chart sizes and mark separation for the area, adapter, assignee, triage-age, backlog,
    weekly activity, and response-rate charts.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-01
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Headline metrics, chart titles/axes, legends, and table columns for unlabeled currency, percentages,
    counts, or durations.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-02
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: All visible titles, legends, axes, and table headers for raw field names, code identifiers,
    or placeholders.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-03
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Page title and visible period references.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-04
  category: labeling
  checker: judge
  verdict: 'yes'
  points_possible: 0
  points_earned: -4.0
  evidence: '"OPEN ISSUES 485" has no visible as-of date or period | "MEDIAN DAYS TO CLOSE 16" has no
    visible reporting period | "ANSWERED WITHIN 48H 18%" has no visible reporting period'
  agreement: 1.0
  votes: 1
- criterion_id: LBL-05
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: All visible charts and tables for descriptive titles or labels.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-07
  category: labeling
  checker: judge
  verdict: 'yes'
  points_possible: 0
  points_earned: -3.0
  evidence: '"ANSWERED WITHIN 48H 18%" does not state the population used as its denominator'
  agreement: 1.0
  votes: 1
- criterion_id: LBL-08
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Chart and table labels against their plotted values and displayed measures.
  agreement: 1.0
  votes: 1
- criterion_id: LBL-09
  category: labeling
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Headlines, charts, tables, notes, totals, and date statements for internal contradictions.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-01
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Spacing between dashboard sections, chart rows, tables, and page bands.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-02
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Alignment of KPI metrics, paired chart rows, tables, and section edges.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-04
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Relative prominence and placement of summary KPIs, charts, and detail tables.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-05
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Visual weight of borders, fills, decoration, legends, and chart styling.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-06
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Color use across issue-type stacks, weekly bars, and response-rate charts.
  agreement: 1.0
  votes: 1
- criterion_id: LAY-07
  category: layout
  checker: judge
  verdict: 'no'
  points_possible: 0
  points_earned: 0.0
  evidence: Visible page text and elements for placeholders, debug output, or leftover 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, section headings, descriptive text, and whether any explicit narrative
    finding is supported by its 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 the headline metrics: Open Issues 485, Opened (28d) 87, Closed (28d) 73, Median Days
    to Close 16, and Answered Within 48h 18%.'
  agreement: 1.0
  votes: 1
- criterion_id: EXC-04
  category: excellence
  checker: judge
  verdict: 'no'
  points_possible: 6
  points_earned: 0.0
  evidence: Checked all charts for annotations, target/reference lines, or a specifically highlighted
    observation/series.
  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 treatment across the dashboard.
  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 charts, including Open issues by type, Opened vs. closed per week,
    and stacked bar charts, for direct series labels.
  agreement: 1.0
  votes: 1
- criterion_id: EXC-08
  category: excellence
  checker: judge
  verdict: 'yes'
  points_possible: 5
  points_earned: 5.0
  evidence: “405 open issues are unassigned. The chart below shows the 15 busiest assignees.” | “Open
    issues by assignee (top 15, excluding unassigned)”
  agreement: 1.0
  votes: 1
score: 0.471
category_scores:
  delivery: 0.6
  excellence: 0.152
agreement: 1.0
judge_errors: []
votes:
- criterion_id: BRF-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: 'Checked all six reader questions against the visible dashboard sections: current-status KPIs;
    backlog trend charts; triage chart, response-rate chart, and oldest-first queue; area and adapter
    charts; epic-progress table; and assignee chart plus most-requested-issues table.'
  round: 1
- criterion_id: BRF-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Compared visible requested content with non-brief content. The page is overwhelmingly occupied
    by charts, KPIs, and tables that map to the requested issue-health questions; the only apparent extra
    is the small static-HTML-export notice.
  round: 1
- criterion_id: WRK-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed the full dashboard for page-level failures, error states, spinners, and widespread
    empty panels.
  round: 1
- criterion_id: WRK-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked each visible chart and table panel for blank, loading, placeholder, or error content.
  round: 1
- criterion_id: HON-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed visible bar and area charts, including open issues by type, weekly opened/closed,
    triage status, area, adapter, and assignee charts, for non-zero value-axis baselines.
  round: 1
- criterion_id: HON-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Compared rate/share/% labels with plotted scales and values, including “New issues answered
    within 48h (%)” and epic “Complete (%)”.
  round: 1
- criterion_id: HON-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Compared repeated type-category colors across charts with Feature, Bug, Task, and Other legends.
  round: 1
- criterion_id: HON-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: na
  evidence: Checked charts for multiple independent value axes and unclear series-to-axis mapping.
  round: 1
- criterion_id: HON-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Compared the side-by-side “Open issues by area” and “Open issues by adapter” charts; their
    axes visibly show their respective scales.
  round: 1
- criterion_id: HON-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked line charts for connections between unordered categories; visible line charts use
    weekly/monthly time sequences.
  round: 1
- criterion_id: FRM-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed all charts for pies/donuts, 3D treatments, trends rendered as tables or pies, and
    rankings rendered 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 comparison-hiding forms.
  round: 1
- criterion_id: FRM-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed multi-series/category charts, including issue type, triage-age, opened-versus-closed,
    area, adapter, and assignee charts, for distinguishable colors and matching legends.
  round: 1
- criterion_id: FRM-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: 'Checked ranked category comparisons for ordering: areas, adapters, assignees, epics, and
    most-requested issues.'
  round: 1
- criterion_id: FRM-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed the KPI numbers and charts for a single value unnecessarily rendered as a gauge or
    one-bar chart.
  round: 1
- criterion_id: FRM-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Compared chart topics and forms to identify any 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: “Opened vs. closed per week” — the roughly 440 opened-issues spike forces a 0–500 scale, making
    the much smaller normal weekly opened/closed counts difficult to compare
  round: 1
- criterion_id: FRM-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: 'Reviewed the starts and ends of the visible time series: open issues by type, opened versus
    closed per week, and new issues answered within 48 hours.'
  round: 1
- criterion_id: LEG-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed chart titles, legends, axes, tick labels, bar labels, and table text across the full-resolution
    tiles for visible collisions.
  round: 1
- criterion_id: LEG-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked all charts for overlapping text, including the backlog, weekly opened-vs.-closed,
    triage, response-rate, area, adapter, and assignee charts.
  round: 1
- criterion_id: LEG-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed visible titles, labels, legends, axes, and table columns within each tile for clipping,
    ellipses, or content pushed outside its card.
  round: 1
- criterion_id: LEG-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Used the full-resolution tiles to inspect small supporting text, axis ticks, legends, chart
    labels, and table text for readability.
  round: 1
- criterion_id: LEG-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Reviewed chart sizes and mark separation for the area, adapter, assignee, triage-age, backlog,
    weekly activity, and response-rate charts.
  round: 1
- criterion_id: LBL-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Headline metrics, chart titles/axes, legends, and table columns for unlabeled currency, percentages,
    counts, or durations.
  round: 1
- criterion_id: LBL-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: All visible titles, legends, axes, and table headers for raw field names, code identifiers,
    or placeholders.
  round: 1
- criterion_id: LBL-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Page title and visible period references.
  round: 1
- criterion_id: LBL-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: '"OPEN ISSUES 485" has no visible as-of date or period | "MEDIAN DAYS TO CLOSE 16" has no
    visible reporting period | "ANSWERED WITHIN 48H 18%" has no visible reporting period'
  round: 1
- criterion_id: LBL-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: All visible charts and tables for descriptive titles or labels.
  round: 1
- criterion_id: LBL-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: '"ANSWERED WITHIN 48H 18%" does not state the population used as its denominator'
  round: 1
- criterion_id: LBL-08
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Chart and table labels against their plotted values and displayed measures.
  round: 1
- criterion_id: LBL-09
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Headlines, charts, tables, notes, totals, and date statements for internal contradictions.
  round: 1
- criterion_id: LAY-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Spacing between dashboard sections, chart rows, tables, and page bands.
  round: 1
- criterion_id: LAY-02
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Alignment of KPI metrics, paired chart rows, tables, and section edges.
  round: 1
- criterion_id: LAY-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Relative prominence and placement of summary KPIs, charts, and detail tables.
  round: 1
- criterion_id: LAY-05
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Visual weight of borders, fills, decoration, legends, and chart styling.
  round: 1
- criterion_id: LAY-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Color use across issue-type stacks, weekly bars, and response-rate charts.
  round: 1
- criterion_id: LAY-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Visible page text and elements for placeholders, debug output, or leftover scaffolding.
  round: 1
- criterion_id: EXC-01
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked the page title, section headings, descriptive text, and whether any explicit narrative
    finding is supported by its chart.
  round: 1
- criterion_id: EXC-03
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: 'Checked the headline metrics: Open Issues 485, Opened (28d) 87, Closed (28d) 73, Median Days
    to Close 16, and Answered Within 48h 18%.'
  round: 1
- criterion_id: EXC-04
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked all charts for annotations, target/reference lines, or a specifically highlighted
    observation/series.
  round: 1
- criterion_id: EXC-06
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked chart color treatment across the dashboard.
  round: 1
- criterion_id: EXC-07
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'no'
  evidence: Checked the multi-series charts, including Open issues by type, Opened vs. closed per week,
    and stacked bar charts, for direct series labels.
  round: 1
- criterion_id: EXC-08
  judge: gpt-5.6-terra
  sample: 0
  verdict: 'yes'
  evidence: “405 open issues are unassigned. The chart below shows the 15 busiest assignees.” | “Open
    issues by assignee (top 15, excluding unassigned)”
  round: 1