Files
whetstone_DSL/specialists/data/generated/automatability_routed_eval.tsv
Bill 15125dce25 Specialist fleet: pilot sweep results + automatability decomposition
Pilot sweep (all 4 gates, small_plus + medium):
  verification_type  84.3%  (medium, no_gain_stop_scaling)
  worker_type        80.8%  (small_plus, scale_more)
  automatability     78.3%  (medium, decompose_or_relabel)
  prereq_op          72.2%  (small_plus, decompose_or_relabel)

Automatability: 2-stage decomposition resolves Directional Collapse.
  Stage 1 binary (low_entropy vs needs_routing): 100%
  Stage 2 4-way (specialist/slm/llm/human): 100%
  Combined 5-way pipeline: 100%
  Script: specialists/scripts/split_automatability_decompose.py

Worker_type: combined dataset (sprint plans + projects) improves
  implementer class from 42.9% → 75.0%, overall 80.8% → 92.2%.
  Combined train/eval TSVs added.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-19 13:44:38 -06:00

887 B

100name=LibrarySymbolAdvisor
210name=SelfHostTranspileAudit
310name=IntentTranslator
410name=TypeSystemTranslator
510name=SecurityPreservingTranslation
610name=IncrementalOptimizer
730name=ApprovalEscalationPlanner
830name=ArchitectReviewInterface
910name=MemoryModelTranslator
1020name=AgentCodeGen
1100name=OperationClassifier
1200name=SymbolSelectorAPI
1330name=ArchitectReviewSurface
1400name=LibrarySymbolAdvisor
1500name=TaskitemLibraryAnnotator
1600name=PerTaskLibrarySelector
1720name=AgentRegistry
1800name=OperationClassifier
1930name=AgentMutationApproval
2030name=AgentMutationPreview
2110name=TransformEngine
2200name=OperationClassifier
2330name=ArchitectReviewSurface
2400name=OperationSelectorAPI
2530name=AgentMutationPreview
2630name=AgentMutationApproval
2720name=AgentTaskStatusOverlay
2820name=ScopeMilestoneDecomposer
2930name=SecurityExceptionReviewBoard