Evidence records
Does the process reward model verify or style-read
Store key
campaign.adjudication.VERIF-PRM The reading
- H-verif-loc refuted
- H-verif-style confirmed
registered
- card
- VERIF-PRM
- status
- adjudicated
- reason
- not measured
- killed
- true
- 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
- VERIF-PRM
- spec
- campaign-verif-prm
- 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
- dense_localization_auc
- 0.2821
- style_share
- -0.4268
- verification_score
- 0.8335
thresholds
- H-verif-loc
- 0.7
- H-verif-style
- 0.5
comparators
- H-verif-loc
- >
- H-verif-style
- <
kill_thresholds
- K-verif
- 0.55
kill_comparators
- K-verif
- <
killed_by
- 0
- K-verif
overlay_notes
No rows returned.
Provenance
- git_sha
- f93f4b5578c221d3d2665f9b305f3e86759be862+dirty
- study
- study:campaign-verif-prm@v1#616bec72
- 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
-
- ev:9e05780931b4ae9d9f18c6d8a0622519
Rendered on
ev:46e1500c4d39f9821c137ae0b00ac0da