Benign Overfitting in Linear Regression
Effective-rank characterization of when interpolation generalizes. The lab found boundary cases its eigenvalue-rank inequality chain does not cover — two falsifications with passing controls.
0supported
2falsified
0inconclusive
4not audited
3model calls
2tool runs
1.6wall min
0failures kept
claims
2 audited · click a claim to open the auditor's own summary — metrics, notes, control status
auditor's noteConditions not met. Cond1 (Benign low): False, Cond2 (Non-benign high): False, Cond3 (Non-benign high): False.
case1_risk0.6657
case2_risk0.3217
case3_risk0.3574
control_risk0.1141
control_passtrue
threshold0.5000
no per-claim summary in this registry snapshot — verdict preserved from the prior run.
no per-claim summary in this registry snapshot — verdict preserved from the prior run.
no per-claim summary in this registry snapshot — verdict preserved from the prior run.
no per-claim summary in this registry snapshot — verdict preserved from the prior run.
auditor's note4 violations found out of 36 checks.
total_checks36.00
violations4.000
control_passTrue
identity_error0.000
ctrl_ineq_passTrue
figure evidence
the trail
3 model calls · 2 tool runs · 1.6 min wall · append-only, failures preserved
0:00