General · EXPERIMENT · ACTIVE
Default Ranking Audit
Observe which options a system's default ordering places first and which it pushes down.
EXPERIMENT — OBSERVATIONS RECORDED · OBSERVED · DIFFERENCE OBSERVED
- Target platform
- Visible World Lab
- Target base URL
- https://visible.shiroand.io/lab/recommendation
- Comparison mode
- Ranking comparison
- Purpose
- Compare default state, one controlled change, an alternative controlled change, and a reset/control.
- What is observed
- Visibility, position, omission, and reordering.
- What is not concluded
- Does not infer motive, suppression, or manipulation.
- Condition setup
- Configured conditions: default state, one controlled change, an alternative controlled change, and a reset/control. The option universe is the controlled lab catalog.
- Personas
- 4
- Observation runs
- 4 · OBSERVED
- Evidence claims
- 40
Related observation
Visible World Audit observes what becomes visible. Reference Layer Observatory examines the reference structures that may shape machine-visible information.
Observation chain
- SIGNAL→
- INFERENCE→
- CANDIDATE SET→
- RANKING→
- EXPOSURE→
- USER ACTION→
- NEXT EXPOSURE
Personas
Manage- Default stateEnabled · ranking-default
- Controlled condition change 1Enabled · ranking-change-1
- Controlled condition change 2Enabled · ranking-change-2
- Neutral reset controlEnabled · ranking-reset
Runner observations
Individual run history is retained. Statuses are not overwritten in place.
- cmuhhr52q000COMPLETED · evidence
- cmuhhqpsg000COMPLETED · evidence
- cmuhhq9s5000COMPLETED · evidence
- cmuhhpyal000COMPLETED · evidence
Condition comparison
DERIVED COMPARISON · DIFFERENCE OBSERVED
Derived from runner-observed option sets and positions. This is a comparison, not a judgment of cause or intent. 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 |
|---|---|---|---|---|---|---|---|---|
| Default stateControl | 24 | 24 | — | 0 / 24 | 0 / 0 | 0 / 0 | 0 | COMPLETEDEvidence |
| Controlled condition change 1 | 24 | 24 | — | 20 / 24 | +2 / -2 | +3 / -3 | 11 | COMPLETEDEvidence |
| Controlled condition change 2 | 24 | 24 | — | 23 / 24 | +3 / -3 | +3 / -3 | 11 | COMPLETEDEvidence |
| Neutral reset control | 24 | 24 | — | 0 / 24 | 0 / 0 | 0 / 0 | 0 | COMPLETEDEvidence |
- Rank Exposure Distance · Controlled condition change 1Changed positions: 20 / 24 · Top 5: 2 entered, 2 exited · Top 10: 3 entered, 3 exited · Largest movement: +11
- Rank Exposure Distance · Controlled condition change 2Changed positions: 23 / 24 · Top 5: 3 entered, 3 exited · Top 10: 3 entered, 3 exited · Largest movement: +11
- Rank Exposure Distance · Neutral reset controlChanged 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.