Evidence records
The Goodhart hump located from a base-policy tail index
Store key
campaign.adjudication.HUMP The reading
- H-hump-exists inconclusive
- H-hump-loc inconclusive
registered
- card
- HUMP
- status
- inconclusive
- reason
- missing intermediate: no intermediate 'campaign.recorder.drift' for roster_key='policy-qwen25-1.5b' slice='hump-prompts'; 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
- HUMP
- spec
- campaign-hump
- 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-hump-exists
- 1
- H-hump-loc
- 0.5
comparators
- H-hump-exists
- ==
- H-hump-loc
- <
kill_thresholds
- K-hump
- 1
kill_comparators
- K-hump
- >
killed_by
No rows returned.
overlay_notes
No rows returned.
Provenance
- git_sha
- f93f4b5578c221d3d2665f9b305f3e86759be862+dirty
- study
- study:campaign-hump@v1#ec094a50
- 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:02a1669641150750737afc8291255bf9