What each cell measures
Each cell compares this vendor's synthetic responses against real human respondents in that demographic subgroup —
published survey ground truth, not a model's guess about the subgroup.
Higher = closer to how that real subgroup actually answered.
Demographic conditioning here is not stereotyping: every conditioned
score is checked against what real subgroup members said, not against
assumptions about them — and where the vendor's output diverges from
the real subgroup, the score drops.
- globalopinionqa — ground truth: Durmus et al. 2023, Anthropic — llm_global_opinions
Low-n cells:
cells with n < 30 are shown muted and tagged low n — suggestive only instead of color-graded; they are
reported for transparency, not as findings.
CIs:
"no CI — single run" marks point estimates from a single run with no
confidence interval yet; treat the uncertainty as unknown, never zero.
Columns:
Score = distributional parity (p_dist) restricted to the subgroup ·
p_cond = conditioning strength vs the unconditioned baseline ·
N = questions answered under that conditioning · Cov. = coverage
dot derived from N (green = high, ≥100 · amber = medium, 50–99 ·
red = low, <50). Topic tables: SPS = Survey Parity Score for the
topic · p_dist = 1 − mean(JSD) · p_rank = (1 + mean(τ)) / 2 ·
p_refuse = 1 − mean(|R_model − R_human|).
Multiple comparisons:
with this many subgroup cells, a few extreme cells are expected by
chance alone — read patterns across a dimension, not single cells.
Question-type breakdown
(6 topics)
| Topic | SPS | p_dist | p_rank | p_refuse | N |
| Health & Science
low n — suggestive only
| 0.969 | 0.939 | 1.000 | 1.000 | 1 |
| Economy & Work
low n — suggestive only
| 0.935 | 0.900 | 0.969 | 0.949 | 3 |
| General Attitudes
low n — suggestive only
| 0.760 | 0.780 | 0.739 | 1.000 | 4 |
| Trust & Wellbeing
low n — suggestive only
| 0.751 | 0.721 | 0.781 | 1.000 | 2 |
| International Relations & Security | 0.719 | 0.751 | 0.688 | 0.987 | 60 |
| Politics & Governance | 0.696 | 0.717 | 0.676 | 0.963 | 30 |
Topics with N < 10 are muted and tagged
"low n — suggestive only": too few questions for a stable
3-decimal score.
Not yet measured
This vendor has no demographic-conditioned runs for age, geography,
education, or any other subgroup dimension on globalopinionqa.
No cells are fabricated — scores appear here only when a
conditioned run actually measured them.
How to submit a demographic-conditioned run →
Question-type breakdown
(6 topics)
| Topic | SPS | p_dist | p_rank | p_refuse | N |
| Health & Science
low n — suggestive only
| 0.990 | 0.981 | 1.000 | 1.000 | 1 |
| Economy & Work
low n — suggestive only
| 0.947 | 0.895 | 1.000 | 0.949 | 3 |
| General Attitudes
low n — suggestive only
| 0.761 | 0.782 | 0.739 | 1.000 | 4 |
| International Relations & Security | 0.650 | 0.659 | 0.642 | 0.987 | 60 |
| Trust & Wellbeing
low n — suggestive only
| 0.644 | 0.571 | 0.717 | 1.000 | 2 |
| Politics & Governance | 0.618 | 0.597 | 0.639 | 0.963 | 30 |
Topics with N < 10 are muted and tagged
"low n — suggestive only": too few questions for a stable
3-decimal score.
Not yet measured
This vendor has no demographic-conditioned runs for age, geography,
education, or any other subgroup dimension on globalopinionqa.
No cells are fabricated — scores appear here only when a
conditioned run actually measured them.
How to submit a demographic-conditioned run →
No demographic conditioning data has been published for this vendor yet. The
question-type matrix above shows topic-level parity; subgroup rows fill in
once Althing-style conditioned runs land.