Evidence records
Bias battery predicts RM-Bench Hard ranking
Store key
campaign.adjudication.STYLE-RMB The reading
- H-style-transfer inconclusive
- H-style-perm inconclusive
- H-style-baseline inconclusive
registered
- card
- STYLE-RMB
- status
- inconclusive
- reason
- missing intermediate: no intermediate 'campaign.bias.battery' for roster_key='armorm' slice='diagnostic-v3-degradation'; the arc that produces it has not run or its shard was not merged
- 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
- STYLE-RMB
- spec
- campaign-style-rmb
- 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
No rows returned.
thresholds
- H-style-transfer
- 0.6
- H-style-perm
- 0.05
- H-style-baseline
- 0
comparators
- H-style-transfer
- >
- H-style-perm
- <
- H-style-baseline
- >=
kill_thresholds
- K-style
- 0.05
kill_comparators
- K-style
- >=
killed_by
No rows returned.
overlay_notes
No rows returned.
Provenance
- git_sha
- f93f4b5578c221d3d2665f9b305f3e86759be862+dirty
- study
- study:campaign-style-rmb@v1#59c45767
- 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
- not measured
Rendered on
ev:14bc4c666b5b115cf1fd2c86cf209f01