Evidence records

Susceptibility chi predicts best-of-n feature drift on a real bank

Store key campaign.adjudication.CHI-DRIFT

The reading

  • H-chi-bon confirmed
  • H-chi-beats-var confirmed

registered

card
CHI-DRIFT
status
adjudicated
reason
not measured
killed
false
staged_violation
false
pre_freeze_violation
false

Uncertainty

ci_low
not measured
ci_high
not measured
ci_level
not measured
n
not measured
n_effective
not measured
seed_spread
not measured
method
none

Subject

card
CHI-DRIFT
spec
campaign-chi-drift
signals
not measured
dataset
not measured
readout
not measured
frame
not measured
interventions
not measured
gauge
invariant
calibration
not measured
observable_version
1.0
trust
registered

Measurements

metrics

chi_bon_spearman
0.9643
chi_bon_spearman_ci_low
0.75
chi_bon_spearman_ci_high
1
chi_bon_spearman_second_model
1
chi_minus_variance_baseline_spearman
0.5714
chi_minus_variance_baseline_spearman_ci_low
0.07143
chi_minus_variance_baseline_spearman_ci_high
0.5714

thresholds

H-chi-bon
0.3
H-chi-beats-var
0

comparators

H-chi-bon
>
H-chi-beats-var
>

kill_thresholds

K-chi
0.3

kill_comparators

K-chi
<

killed_by

No rows returned.

overlay_notes

No rows returned.

Provenance

git_sha
f93f4b5578c221d3d2665f9b305f3e86759be862+dirty
study
study:campaign-chi-drift@v1#1c12042d
config_hash
not measured
gpu_seconds
0
tokens
0
wall_seconds
0
gpu
cpu
arc
reporting
seeds
not measured
oracle_calls
not measured
created_at
parents, Derived from

Rendered on

ev:c978e3958769ecf93dcf079771a3aedb