H
Howardism
Howardism · Vol. 03Plate I · No. 01

Evaluation Methodology, tagged.

Notes27TagEvaluation MethodologyOldest9 Jul 2026Newest1 Oct 2026

Every article tagged evaluation methodology, newest first.

  1. C01
    Benchmark Task Defects (Spec–Test Mismatch)
    BenchmarksBenchmark IntegrityConstruct Validity+2
    · 13′
  2. C02
    The Price of Fixed Capability
    Inference CostBenchmarksEvaluation Methodology+2
    · 15′
  3. C03
    Statement Drift
    Formal MethodsAI For MathematicsEvaluation Methodology+1
    · 19′
  4. C04
    Benchmark Convergent and Discriminant Validity
    BenchmarksEvaluation MethodologyConstruct Validity+3
    · 20′
  5. C05
    Recurring Production Agent Evaluation
    BenchmarksEvaluation MethodologyCapability Evaluation+3
    · 13′
  6. C06
    Discovery Certification Protocol (DCP)
    Evaluation MethodologyAI RdBenchmark Validity+2
    · 10′
  7. C07
    Cognitive Capability Profiling for Task Suitability
    Evaluation MethodologyPsychometricsCapability Evaluation+3
    · 35′
  8. C08
    Kernel-Level Proof Auditing
    Formal MethodsEvaluation MethodologyAI For Mathematics+1
    · 35′
  9. C09
    OEIS Open Benchmark
    BenchmarksEvaluation MethodologyAI For Mathematics+1
    · 31′
  10. C10
    Economic Benchmark Construct Validity
    BenchmarksEvaluation MethodologyConstruct Validity+3
    · 27′
  11. C11
    Item Response Theory for LLM Benchmarks
    BenchmarksEvaluation MethodologyPsychometrics+2
    · 36′
  12. C12
    Shared-Budget Compute Allocation
    Test Time ComputeReasoning ModelsMetacognition+2
    · 21′
  13. C13
    FrontierMath Erdős Benchmark
    BenchmarksEvaluation MethodologyAI For Mathematics+1
    · 40′
  14. C14
    Harness Activation and Adherence
    Agent EngineeringHarnessSkills+2
    · 30′
  15. C15
    Headroom-Closed Index (HCI)
    BenchmarksEvaluation MethodologyCapability Trajectory+2
    · 19′
  16. C16
    RSI Autonomy Levels (B0–L5)
    Recursive Self ImprovementCapability TrajectoryTaxonomy+2
    · 32′
  17. C17
    Adaptive Stopping in Evaluation Sampling
    Capability EvaluationBenchmarksEvaluation Methodology+3
    · 24′
  18. C18
    Evaluation-Time Answer Leakage
    BenchmarksEvaluation MethodologyConstruct Validity+3
    · 44′
  19. C19
    Aggregate Cancellation
    Evaluation MethodologyConstruct ValidityBenchmarks+1
    · 13′
  20. C20
    Expenditure Horizon
    BenchmarksCapability EvaluationEvaluation Methodology+3
    · 30′
  21. C21
    Harness-Induced Belief Divergence
    Agent EngineeringHarnessEvaluation+2
    · 21′
  22. C22
    Matched Comparisons for Memorization Claims
    Evaluation MethodologyMeasurement ValidityData Contamination+3
    · 23′
  23. C23
    Orchestration-Plan Simulation
    BenchmarksEvaluation MethodologyMulti Agent+2
    · 25′
  24. C24
    Benchmark Contamination and Decontamination
    LLM ArchitectureCapability EvaluationBenchmarks+4
    · 30′
  25. C25
    Benchmark Score Redundancy
    LLM ArchitectureCapability EvaluationBenchmarks+3
    · 49′
  26. C26
    Measuring Beyond Accuracy Saturation
    LLM ArchitectureCapability EvaluationBenchmarks+3
    · 62′
  27. C27
    Compute-Controlled Benchmarking
    LLM ArchitectureCapability EvaluationBenchmarks+2
    · 82′