Graph learning found a fairness–cooperation link in a British survey sample
Source check: Source checked. Not independent scientific confirmation.
Finding: A learned graph fitted to 1,805 Great Britain responses in the European Social Survey consistently linked perceived police procedural fairness with willingness to cooperate. The link appeared in all 20 near-best graph classes, whereas the link between moral alignment and cooperation was uncertain. Directions in the reported ordered graph came from the researchers' theory-based ordering, so the findings describe relationships in survey responses.
Technology: DAGGLE; latent Gaussian graph structure learning
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- DAGGLE learned latent-construct adjacency structure jointly with measurement and structural parameters. It used likelihood-based edge screening and comparison across graph equivalence classes; theory supplied any reported link orientation.
- Test and result
- The study examined 15 survey measures and five latent constructs. It compared candidates with the published structural equation model and exhaustively assessed the small graph-class space in addition to the fitted search. The fairness–cooperation association was retained with the same sign in reported subgroup fits under the specified ordering.
- Limitation / still unknown
- The associations are retrospective and model-dependent. The data do not identify the direction of the fairness–cooperation relationship, or show that changing policing would cause a change in willingness to cooperate.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/abs/2610.27873 · https://arxiv.org/html/2610.27873 · https://arxiv.org/abs/2610.06086
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 21 Nov 2026. Review scope: Original arXiv v1 abstract and history, HTML §3 and European Social Survey §§6.1–6.3; earlier related DAG-CLIP primary abstract.
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.