Files
whetstone_DSL/specialists/data/generated/automatability_binary_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

1.4 KiB

110name=LibrarySymbolAdvisor
210name=SelfHostTranspileAudit
300name=TrainingDataGenerator
410name=IntentTranslator
510name=TypeSystemTranslator
600name=ContextBundleMinimizer
710name=SecurityPreservingTranslation
810name=IncrementalOptimizer
900name=BufferOpsLifecycle
1000name=MigrationAcceptanceContract
1110name=ApprovalEscalationPlanner
1200name=Sprint163IntegrationSummary
1310name=ArchitectReviewInterface
1410name=MemoryModelTranslator
1510name=AgentCodeGen
1600name=Sprint238IntegrationSummary
1700name=CppJSBindingEmitter
1810name=OperationClassifier
1900name=Sprint36IntegrationSummary
2000name=SelfHostHarness
2110name=SymbolSelectorAPI
2210name=ArchitectReviewSurface
2300name=Sprint111IntegrationSummary
2410name=LibrarySymbolAdvisor
2510name=TaskitemLibraryAnnotator
2600name=SyntaxHighlighterElisp
2700name=SelfHostCodebaseAudit
2810name=PerTaskLibrarySelector
2900name=SyntaxHighlighterGo
3010name=AgentRegistry
3110name=OperationClassifier
3200name=WorkflowTemplates
3310name=AgentMutationApproval
3410name=AgentMutationPreview
3500name=RustPythonBindingEmitter
3610name=TransformEngine
3710name=OperationClassifier
3800name=CompilerPhaseSpec
3910name=ArchitectReviewSurface
4010name=OperationSelectorAPI
4110name=AgentMutationPreview
4210name=AgentMutationApproval
4310name=AgentTaskStatusOverlay
4410name=ScopeMilestoneDecomposer
4510name=SecurityExceptionReviewBoard
4600name=CompositionBuilder