Recruitment · EXPERIMENT · ACTIVE
Age Visibility Probe
Observe whether age-related profile conditions change the visible set under similar role conditions.
EXPERIMENT — OBSERVATIONS RECORDED · OBSERVED · NO MATERIAL DIFFERENCE OBSERVED
- Target platform
- Visible World Lab
- Target base URL
- https://visible.shiroand.io/lab/recommendation
- Comparison mode
- Persona comparison
- Purpose
- Record visible options, ranking, omissions, and exposure differences across career-stage profiles.
- What is observed
- Visible options, ranking, omissions, and exposure differences.
- What is not concluded
- Does not judge age discrimination or infer the system's motive. Difference observed is not proof of intent.
- Condition setup
- Configured conditions: early-career, mid-career, senior-career, and an age-neutral control. Skills, target role, location, employment type, industry, and qualification level are held constant. Synthetic profiles only.
- Personas
- 4
- Observation runs
- 4 · OBSERVED
- Evidence claims
- 8
Observation chain
- SIGNAL→
- INFERENCE→
- CANDIDATE SET→
- RANKING→
- EXPOSURE→
- USER ACTION→
- NEXT EXPOSURE
Personas
Manage- Early-careerEnabled · age-early
- Mid-careerEnabled · age-mid
- Senior-careerEnabled · age-senior
- Age-neutral controlEnabled · age-control
Runner observations
Individual run history is retained. Statuses are not overwritten in place.
- cmuhdbaxk000COMPLETED · evidence
- cmuhdaytu000COMPLETED · evidence
- cmuhdanpk000COMPLETED · evidence
- cmuhdaceh000COMPLETED · evidence
Condition comparison
DERIVED COMPARISON · NO MATERIAL DIFFERENCE OBSERVED
Completed observations show the same visible option set and ranks under these conditions. Ranking differences are observations of exposure, not conclusions about intent or fairness. This table is not an overall score.
Rank Exposure Distance describes how many shared options changed position relative to the control, plus Top 5 / Top 10 entry and exit, and the largest absolute rank change. It is a descriptive comparison, not a quality score.
| Condition | Visible count | Shared | Only here | Rank movement | Top 5 +/- | Top 10 +/- | Largest move | Run status |
|---|---|---|---|---|---|---|---|---|
| Early-career | 24 | 24 | — | 0 / 24 | 0 / 0 | 0 / 0 | 0 | COMPLETEDEvidence |
| Mid-career | 24 | 24 | — | 0 / 24 | 0 / 0 | 0 / 0 | 0 | COMPLETEDEvidence |
| Senior-career | 24 | 24 | — | 0 / 24 | 0 / 0 | 0 / 0 | 0 | COMPLETEDEvidence |
| Age-neutral controlControl | 24 | 24 | — | 0 / 24 | 0 / 0 | 0 / 0 | 0 | COMPLETEDEvidence |
- Rank Exposure Distance · Early-careerChanged positions: 0 / 24 · Top 5: 0 entered, 0 exited · Top 10: 0 entered, 0 exited · Largest movement: 0
- Rank Exposure Distance · Mid-careerChanged positions: 0 / 24 · Top 5: 0 entered, 0 exited · Top 10: 0 entered, 0 exited · Largest movement: 0
- Rank Exposure Distance · Senior-careerChanged positions: 0 / 24 · Top 5: 0 entered, 0 exited · Top 10: 0 entered, 0 exited · Largest movement: 0
Ranking differences are observations of exposure, not conclusions about intent or fairness.
Provenance describes the source of a statement. Causal status is separate: NOT ESTABLISHED means a sequence may have been observed without demonstrated cause.