69 lines
1.9 KiB
YAML
69 lines
1.9 KiB
YAML
|
# The interface's first experiment: does the portrait earn its place?
|
||
|
|
#
|
||
|
|
# This tests DELIVERY, which this interface owns. The competition about which
|
||
|
|
# editorial voice travels belongs to the campaign and is run on the per-variant
|
||
|
|
# engagement this interface reports — see docs/observation.md.
|
||
|
|
#
|
||
|
|
# fluid experiment design --file experiments/E-tg-delivery.yaml
|
||
|
|
# fluid experiment start E-tg-delivery --generation 2 \
|
||
|
|
# --default-revision R-2 --policy-out rp.json
|
||
|
|
# fluid policy put --file rp.json
|
||
|
|
fluid_experiment:
|
||
|
|
schema_version: "0.1"
|
||
|
|
|
||
|
|
id: "E-tg-delivery"
|
||
|
|
interface_id: "helix-forge-telegram-publishing"
|
||
|
|
|
||
|
|
hypothesis_refs:
|
||
|
|
- "H-tg-visual"
|
||
|
|
- "H-tg-textonly"
|
||
|
|
|
||
|
|
# R-2 attaches the portrait, R-3 publishes text only. Neither is an
|
||
|
|
# incumbent: R-1 publishes without either treatment being settled, so this
|
||
|
|
# is a comparison between two answers rather than against a baseline.
|
||
|
|
control_revision: "R-2"
|
||
|
|
candidate_revisions:
|
||
|
|
- "R-3"
|
||
|
|
|
||
|
|
cohorts:
|
||
|
|
- "telegram-subscribers"
|
||
|
|
|
||
|
|
allocation:
|
||
|
|
control: 0.5
|
||
|
|
candidate: 0.5
|
||
|
|
|
||
|
|
# An even split because there is no incumbent to protect. The usual 90/10
|
||
|
|
# caution limits exposure to an unproven candidate; here both arms are
|
||
|
|
# equally unproven and the scarce resource is posts, not safety.
|
||
|
|
|
||
|
|
metrics:
|
||
|
|
primary:
|
||
|
|
- "engagement_rate"
|
||
|
|
guardrails:
|
||
|
|
- "unreviewed_publication"
|
||
|
|
- "missing_source_attribution"
|
||
|
|
- "missing_subject_consent"
|
||
|
|
- "error_rate"
|
||
|
|
secondary:
|
||
|
|
- "source_link_rate"
|
||
|
|
- "forward_rate"
|
||
|
|
learning:
|
||
|
|
- "time_to_first_view"
|
||
|
|
|
||
|
|
start_conditions:
|
||
|
|
- "both revisions verified against the private test channel"
|
||
|
|
- "channel has at least 100 subscribers"
|
||
|
|
|
||
|
|
stop_conditions:
|
||
|
|
- "hard_guardrail_violation"
|
||
|
|
- "unreviewed_publication"
|
||
|
|
- "manual_stop"
|
||
|
|
- "max_duration_reached"
|
||
|
|
|
||
|
|
max_duration_hours: 2160 # 90 days
|
||
|
|
|
||
|
|
result:
|
||
|
|
state: "PLANNED"
|
||
|
|
preferred_revision: null
|
||
|
|
evidence_refs: []
|