diff --git a/specialists/HANDOFF-2026-04-18.md b/specialists/HANDOFF-2026-04-18.md
new file mode 100644
index 0000000..b246ede
--- /dev/null
+++ b/specialists/HANDOFF-2026-04-18.md
@@ -0,0 +1,86 @@
+# Specialist Fleet Handoff — 2026-04-18
+
+## Status at Session End
+
+Sweep was killed mid-run to conserve solar battery. State:
+
+| Gate | Tier | Status | Accuracy |
+|------|------|--------|----------|
+| verification_type | small_plus | COMPLETE | 81.4% — verdict: `scale_more` |
+| verification_type | medium | KILLED | Partial checkpoint, do not trust |
+| worker_type | — | NOT STARTED | — |
+| prereq_op | — | NOT STARTED | — |
+| automatability | — | NOT STARTED | — |
+
+## First Task Next Session
+
+From the whetstone_DSL root, run the full pilot sweep fresh:
+
+```bash
+cd /home/bill/Documents/CLionProjects/whetstone_DSL
+bash specialists/scripts/sweep_all_gates.sh --pilot-only 2>&1 | tee specialists/eval/results/sweep_run.log
+```
+
+The `--reset` flag inside `capacity_sweep.py` ensures the broken `verification_type` medium
+checkpoint from this session doesn't interfere. All 4 gates run from scratch.
+
+Expected runtime: ~25–35 minutes total (small_plus + medium × 4 gates, 3000 steps each).
+
+Results land in:
+- `specialists/eval/results/<gate>_sweep.json` — per-gate sweep table
+- `specialists/eval/results/summary.json` — combined best-tier per gate
+
+## Fixes Applied This Session (All Saved to Disk)
+
+1. **Venv path** — `sweep_all_gates.sh` now uses whetstone DSL venv:
+   `PYTHON="/home/bill/Documents/CLionProjects/whetstone_DSL/.venv/bin/python3"`
+
+2. **Venv path** — `capacity_sweep.py` + `prereq_op_binary_split.py` now use `sys.executable`
+   instead of the deleted `WhetstoneAI_Fabricate/.venv` path.
+
+3. **Eval JSON parse** — `eval_specialist_pt.py` now prints single-line JSON as last line:
+   `print(json.dumps(result))  # single line — capacity_sweep.py reads last line as JSON`
+
+4. **Large tier removed** — `sweep_all_gates.sh` defaults to `TIERS="small_plus,medium"`.
+   Large (512/4/8, 13M params) takes ~247s/block — impractical for a pilot.
+
+5. **Nested tensor slowpath** — `train_specialist_pt.py` has `enable_nested_tensor=False`
+   on TransformerEncoder. This eliminated ~40% overhead AND improved accuracy.
+
+6. **Inductor compile** — `torch.compile(mode="reduce-overhead")` enabled with TF32.
+   `python3.12-dev` is installed. Actual speedup: ~62s → ~45s/block (~25%).
+   Note: `torch.randint` dynamic sampling prevents full CUDA graph replay; partial
+   re-recording still happens. Pre-generated static batch pool would fix this but
+   wasn't implemented (one-time training cost doesn't justify complexity).
+
+## Baseline Accuracy (from prior session, before this session's fixes)
+
+| Gate | Prior Best | Labels |
+|------|-----------|--------|
+| worker_type | 88.5% | implementer, reviewer, architect, qa |
+| verification_type | 84.9% | unit, integration, schema, smoke, docs |
+| prereq_op | 69.4% | standard, needs_review, needs_approval, full_gates |
+| automatability | 69.6% | deterministic, template, specialist, slm, llm, human |
+
+Target: 98-99% (deploy_direct verdict) or 95%+ at ≤0.30 abstain rate (deploy_with_guardrails).
+
+## After the Sweep
+
+Check `specialists/eval/results/summary.json`. For any gate with verdict `scale_more`:
+- Try full 15k steps: edit capacity_sweep.py `MAX_STEPS` or run the gate individually
+- Or generate more training data — this is the higher-leverage move for low-accuracy gates
+
+Gates most likely to need more data: `prereq_op` (4-way, hard to separate) and `automatability`
+(6-way, some classes are similar). Consider a data gen script that uses an LLM to generate
+examples per label given a description.
+
+## Model Architecture (for reference)
+
+Small_plus tier: hidden=256, layers=2, heads=4 (~1.2M params)
+Medium tier:     hidden=384, layers=3, heads=6 (~3.0M params)
+
+Encoder-only transformer, mean-pool over non-padding positions, linear classification head.
+Tokenizer: whitespace split, lowercase. Seq len: 96 tokens.
+Checkpoint format: `checkpoint.pt` — contains model, optimizer, vocab, config, labels, step.
+
+Checkpoints live in: `/mnt/storage/fabricate_runs/whetstone_<gate>_<tier>/checkpoint.pt`
diff --git a/specialists/data/generated/automatability_binary_eval.tsv b/specialists/data/generated/automatability_binary_eval.tsv
new file mode 100644
index 0000000..5af28f3
--- /dev/null
+++ b/specialists/data/generated/automatability_binary_eval.tsv
@@ -0,0 +1,46 @@
+1	0	name=LibrarySymbolAdvisor
+1	0	name=SelfHostTranspileAudit
+0	0	name=TrainingDataGenerator
+1	0	name=IntentTranslator
+1	0	name=TypeSystemTranslator
+0	0	name=ContextBundleMinimizer
+1	0	name=SecurityPreservingTranslation
+1	0	name=IncrementalOptimizer
+0	0	name=BufferOpsLifecycle
+0	0	name=MigrationAcceptanceContract
+1	0	name=ApprovalEscalationPlanner
+0	0	name=Sprint163IntegrationSummary
+1	0	name=ArchitectReviewInterface
+1	0	name=MemoryModelTranslator
+1	0	name=AgentCodeGen
+0	0	name=Sprint238IntegrationSummary
+0	0	name=CppJSBindingEmitter
+1	0	name=OperationClassifier
+0	0	name=Sprint36IntegrationSummary
+0	0	name=SelfHostHarness
+1	0	name=SymbolSelectorAPI
+1	0	name=ArchitectReviewSurface
+0	0	name=Sprint111IntegrationSummary
+1	0	name=LibrarySymbolAdvisor
+1	0	name=TaskitemLibraryAnnotator
+0	0	name=SyntaxHighlighterElisp
+0	0	name=SelfHostCodebaseAudit
+1	0	name=PerTaskLibrarySelector
+0	0	name=SyntaxHighlighterGo
+1	0	name=AgentRegistry
+1	0	name=OperationClassifier
+0	0	name=WorkflowTemplates
+1	0	name=AgentMutationApproval
+1	0	name=AgentMutationPreview
+0	0	name=RustPythonBindingEmitter
+1	0	name=TransformEngine
+1	0	name=OperationClassifier
+0	0	name=CompilerPhaseSpec
+1	0	name=ArchitectReviewSurface
+1	0	name=OperationSelectorAPI
+1	0	name=AgentMutationPreview
+1	0	name=AgentMutationApproval
+1	0	name=AgentTaskStatusOverlay
+1	0	name=ScopeMilestoneDecomposer
+1	0	name=SecurityExceptionReviewBoard
+0	0	name=CompositionBuilder
diff --git a/specialists/data/generated/automatability_binary_train.tsv b/specialists/data/generated/automatability_binary_train.tsv
new file mode 100644
index 0000000..31d4bd5
--- /dev/null
+++ b/specialists/data/generated/automatability_binary_train.tsv
@@ -0,0 +1,266 @@
+1	0	name=AgentChatContextInjector
+1	0	name=ApprovalEscalationPlanner
+1	0	name=StrategyAwareOptimizer
+0	0	name=SettingsManager
+1	0	name=LibrarySymbolAdvisor
+1	0	name=TransformEngineExtended
+1	0	name=StrategyAwareOptimizer
+1	0	name=SymbolSelectorAPI
+1	0	name=ApprovalEscalationPlanner
+0	0	name=PolyApiProject
+1	0	name=MemoryModelTranslator
+1	0	name=AgentChatSessionPersistence
+1	0	name=AgentSessionRecorder
+1	0	name=IncrementalOptimizer
+1	0	name=TypeSystemTranslator
+0	0	name=MigrationTestGenerator
+0	0	name=SCIPEmitter
+1	0	name=ArchitectReviewInterface
+0	0	name=CapabilityDeclarationGenerator
+0	0	name=Sprint190IntegrationSummary
+1	0	name=SecurityExceptionReviewBoard
+0	0	name=SecurityTestSkeletonGenerator
+0	0	name=SchemaToCppGenerator
+0	0	name=JobDispatchTableGenerator
+0	0	name=Sprint85IntegrationSummary
+1	0	name=SymbolSelectorAPI
+0	0	name=ProjectAstCMakeGenerator
+0	0	name=BatchMutationAPI
+1	0	name=CanaryPromotionJudge
+1	0	name=ArchitectReviewSurface
+1	0	name=TypeAwareMappings
+1	0	name=SecurityPreservingTranslation
+1	0	name=TransformEngineExtended
+1	0	name=ArchitectReviewSurface
+0	0	name=Sprint222IntegrationSummary
+1	0	name=ArchitectReviewInterface
+1	0	name=ArchitectReviewSurface
+1	0	name=PolyglotSuiteOrchestrator
+0	0	name=Sprint265IntegrationSummary
+0	0	name=SyntaxHighlighterOrg
+1	0	name=TransformEngineExtended
+1	0	name=TypeAwareMappings
+1	0	name=AgentChatPanelModel
+1	0	name=ArchitectModuleDecomposer
+0	0	name=ContextSliceAssembler
+0	0	name=SyntaxHighlighterJavaScript
+1	0	name=TranspilationConfidence
+1	0	name=ArchitectTechStackSelector
+1	0	name=PerTaskLibrarySelector
+1	0	name=ArchitectReviewInterface
+1	0	name=SecurityExceptionReviewBoard
+0	0	name=Sprint106IntegrationSummary
+1	0	name=OperationClassifier
+0	0	name=SQLiteDataLayerGenerator
+1	0	name=SelfHostTranspileAudit
+0	0	name=Sprint27IntegrationSummary
+1	0	name=IncrementalOptimizer
+1	0	name=AgentMutationApproval
+0	0	name=Sprint98IntegrationSummary
+1	0	name=OperationSelectorAPI
+1	0	name=SelfHostTranspileAudit
+1	0	name=OperationSelectorAPI
+0	0	name=AccessibilityBaseline
+1	0	name=AgentMutationApproval
+0	0	name=TraceGenerator
+0	0	name=CostEstimator
+1	0	name=AgentPermissionPolicy
+1	0	name=AgentMutationPreview
+1	0	name=ConcurrencyTranslator
+1	0	name=SelfHostTranspileAudit
+1	0	name=ContextWindowOptimizer
+1	0	name=AgentMutationPreview
+1	0	name=IntentTranslator
+1	0	name=AgentLibraryPolicy
+0	0	name=SyntaxHighlighterPython
+0	0	name=JobDispatchTableGenerator
+0	0	name=EditorModePolicy
+1	0	name=LibrarySymbolAdvisor
+1	0	name=AgentMarketplace
+1	0	name=TranspilationConfidence
+0	0	name=SwarmStatusPanelModel
+1	0	name=ApprovalEscalationPlanner
+1	0	name=TransformEngine
+0	0	name=SyntaxHighlighter
+1	0	name=ArchitectIntakeProcessor
+1	0	name=PolyglotOrchestrator
+1	0	name=AgentTaskStatusOverlay
+1	0	name=ArchitectReviewInterface
+1	0	name=OperationSelectorAPI
+1	0	name=LibrarySymbolAdvisor
+0	0	name=Sprint184IntegrationSummary
+1	0	name=SecurityExceptionReviewBoard
+0	0	name=Sprint36aIntegration
+1	0	name=ArchitectReviewInterface
+0	0	name=SyntaxHighlighterPython
+0	0	name=SearchUtils
+0	0	name=Diagnostics
+0	0	name=TestPlanGenerator
+1	0	name=SecurityExceptionReviewBoard
+0	0	name=InferenceJobGenerator
+1	0	name=ArchitectProblemParser
+0	0	name=LSPSymbolExtractor
+1	0	name=SymbolSelectorAPI
+1	0	name=ArchitectProjectPipeline
+1	0	name=PerTaskLibrarySelector
+1	0	name=AgentToolCallVisualization
+0	0	name=ProjectSkeletonGenerator
+1	0	name=TaskitemLibraryAnnotator
+1	0	name=CanaryPromotionJudge
+1	0	name=SecurityExceptionReviewBoard
+1	0	name=OperationSelectorAPI
+0	0	name=LanguageGeneratorPluginManifest
+1	0	name=TransformEngine
+1	0	name=OnCallCoveragePlanner
+1	0	name=TaskitemLibraryAnnotator
+1	0	name=TaskitemLibraryAnnotator
+1	0	name=AgentMutationPreview
+1	0	name=AgentChatSessionPersistence
+0	0	name=CHeaderEmitter
+0	0	name=Sprint49IntegrationSummary
+1	0	name=ContextWindowOptimizer
+1	0	name=PerTaskLibrarySelector
+1	0	name=ArchitectMultiLanguageOrchestrator
+0	0	name=MCPWorkflowPrompts
+1	0	name=TranspilationRPC
+1	0	name=ContextWindowOptimizer
+1	0	name=OperationSelectorAPI
+0	0	name=Sprint198IntegrationSummary
+1	0	name=ArchitectScaffoldGenerator
+0	0	name=GoCppBindingEmitter
+0	0	name=AnimationUtils
+0	0	name=SelfHostAnnotationAudit
+1	0	name=ArchitectIntakeProcessor
+1	0	name=AgentMarketplace
+1	0	name=TranspilationConfidence
+1	0	name=ArchitectReviewSurface
+0	0	name=SecureByDefaultGenerator
+1	0	name=OperationSelectorAPI
+1	0	name=CanaryPromotionJudge
+1	0	name=TaskitemLibraryAnnotator
+1	0	name=AgentChatPanelModel
+1	0	name=LibrarySymbolAdvisor
+1	0	name=SecurityPreservingTranslation
+0	0	name=APIBoundaryPreserver
+1	0	name=ApprovalEscalationPlanner
+1	0	name=TypeSystemTranslator
+1	0	name=StrategyAwareOptimizer
+1	0	name=TransformEngineExtended
+0	0	name=SyntaxHighlighterRust
+1	0	name=AgentSessionRecorder
+0	0	name=Sprint136IntegrationSummary
+0	0	name=OperationTaxonomy
+1	0	name=ArchitectTechStackSelector
+0	0	name=AnnotationConflict
+1	0	name=CanaryPromotionJudge
+1	0	name=ApprovalEscalationPlanner
+0	0	name=Sprint286IntegrationSummary
+0	0	name=MigrationPlanGenerator
+0	0	name=Sprint261IntegrationSummary
+0	0	name=TrainingDataGenerator
+0	0	name=RustPythonBindingEmitter
+1	0	name=AgentTaskSlots
+1	0	name=AgentCodeGen
+0	0	name=Sprint74IntegrationSummary
+0	0	name=ArchitectTemplates
+1	0	name=SymbolSelectorAPI
+1	0	name=TaskitemLibraryAnnotator
+1	0	name=ApprovalEscalationPlanner
+1	0	name=CanaryPromotionJudge
+1	0	name=AgentMutationApproval
+0	0	name=SyntaxHighlighterJava
+1	0	name=AgentMutationPreview
+1	0	name=AgentMutationPreview
+0	0	name=SQLiteDataLayerGenerator
+1	0	name=AgentTaskSlots
+1	0	name=AgentRPCHandler
+1	0	name=MemoryModelTranslator
+1	0	name=ConcurrencyTranslator
+1	0	name=ArchitectReviewSurface
+1	0	name=AgentToolCallVisualization
+1	0	name=SecurityExceptionReviewBoard
+0	0	name=RustGoBindingEmitter
+0	0	name=Sprint58IntegrationSummary
+1	0	name=IncrementalOptimizer
+0	0	name=Sprint239IntegrationSummary
+0	0	name=SyntaxHighlighterElisp
+0	0	name=PlatformCMakeTargetGenerator
+1	0	name=ApprovalEscalationPlanner
+0	0	name=MqttBoilerplateGenerator
+1	0	name=PerTaskLibrarySelector
+1	0	name=IntentTranslator
+1	0	name=SecurityExceptionReviewBoard
+0	0	name=KeySymbolRenderer
+1	0	name=OperationSelectorAPI
+1	0	name=MemoryModelTranslator
+1	0	name=ArchitectReviewInterface
+0	0	name=ArchitectSkeletonGenerator
+1	0	name=OperationClassifier
+1	0	name=ApprovalEscalationPlanner
+1	0	name=OperationClassifier
+0	0	name=PackageScriptGenerator
+1	0	name=TaskitemLibraryAnnotator
+1	0	name=TypeAwareMappings
+1	0	name=ArchitectReviewInterface
+0	0	name=GoCppBindingEmitter
+1	0	name=AgentMutationApproval
+0	0	name=CHeaderEmitter
+0	0	name=SyntaxHighlighterOrg
+0	0	name=TaskitemGeneratorV2
+0	0	name=Sprint96IntegrationSummary
+0	0	name=ScoreClampUtil
+1	0	name=AgentRPCHandler
+1	0	name=ArchitectScaffoldGenerator
+1	0	name=ScopeMilestoneDecomposer
+1	0	name=AgentMutationApproval
+1	0	name=AgentMutationPreview
+1	0	name=AgentPermissionPolicy
+1	0	name=PerTaskLibrarySelector
+0	0	name=ConstrainedRoutingRulesetExtension
+0	0	name=LanguageGeneratorPluginManifest
+1	0	name=ArchitectReviewSurface
+0	0	name=WorkItem
+1	0	name=TaskitemLibraryAnnotator
+1	0	name=CanaryPromotionJudge
+1	0	name=AgentMutationApproval
+1	0	name=LibrarySymbolAdvisor
+1	0	name=ConcurrencyTranslator
+1	0	name=CanaryPromotionJudge
+1	0	name=WorkflowOrchestrator
+0	0	name=InferenceJobGenerator
+1	0	name=TranspilationRPC
+1	0	name=AgentLibraryPolicy
+0	0	name=Sprint272IntegrationSummary
+1	0	name=TransformEngine
+1	0	name=TranspilationRPC
+1	0	name=OnCallCoveragePlanner
+1	0	name=SymbolSelectorAPI
+1	0	name=PolyglotOrchestrator
+1	0	name=OperationClassifier
+0	0	name=RefactorActions
+1	0	name=LibrarySymbolAdvisor
+1	0	name=IntentTranslator
+1	0	name=PerTaskLibrarySelector
+1	0	name=WorkflowOrchestrator
+1	0	name=AgentChatContextInjector
+1	0	name=AgentAnnotationAssistant
+1	0	name=AgentMutationApproval
+1	0	name=SymbolSelectorAPI
+1	0	name=ArchitectReviewInterface
+0	0	name=SyntaxHighlighterCpp
+1	0	name=ArchitectMultiLanguageOrchestrator
+0	0	name=APIDocGenerator
+1	0	name=ArchitectProblemParser
+1	0	name=StrategyAwareOptimizer
+1	0	name=AgentAnnotationAssistant
+0	0	name=PackageScriptGenerator
+1	0	name=AgentRegistry
+1	0	name=ArchitectModuleDecomposer
+0	0	name=Sprint249IntegrationSummary
+1	0	name=SecurityPreservingTranslation
+1	0	name=ArchitectProjectPipeline
+0	0	name=WorkerDispatchValidator
+1	0	name=ContextWindowOptimizer
+1	0	name=PolyglotSuiteOrchestrator
+1	0	name=AgentMutationPreview
+1	0	name=TypeSystemTranslator
diff --git a/specialists/data/generated/automatability_routed_eval.tsv b/specialists/data/generated/automatability_routed_eval.tsv
new file mode 100644
index 0000000..77d002a
--- /dev/null
+++ b/specialists/data/generated/automatability_routed_eval.tsv
@@ -0,0 +1,29 @@
+0	0	name=LibrarySymbolAdvisor
+1	0	name=SelfHostTranspileAudit
+1	0	name=IntentTranslator
+1	0	name=TypeSystemTranslator
+1	0	name=SecurityPreservingTranslation
+1	0	name=IncrementalOptimizer
+3	0	name=ApprovalEscalationPlanner
+3	0	name=ArchitectReviewInterface
+1	0	name=MemoryModelTranslator
+2	0	name=AgentCodeGen
+0	0	name=OperationClassifier
+0	0	name=SymbolSelectorAPI
+3	0	name=ArchitectReviewSurface
+0	0	name=LibrarySymbolAdvisor
+0	0	name=TaskitemLibraryAnnotator
+0	0	name=PerTaskLibrarySelector
+2	0	name=AgentRegistry
+0	0	name=OperationClassifier
+3	0	name=AgentMutationApproval
+3	0	name=AgentMutationPreview
+1	0	name=TransformEngine
+0	0	name=OperationClassifier
+3	0	name=ArchitectReviewSurface
+0	0	name=OperationSelectorAPI
+3	0	name=AgentMutationPreview
+3	0	name=AgentMutationApproval
+2	0	name=AgentTaskStatusOverlay
+2	0	name=ScopeMilestoneDecomposer
+3	0	name=SecurityExceptionReviewBoard
diff --git a/specialists/data/generated/automatability_routed_train.tsv b/specialists/data/generated/automatability_routed_train.tsv
new file mode 100644
index 0000000..cfed1fa
--- /dev/null
+++ b/specialists/data/generated/automatability_routed_train.tsv
@@ -0,0 +1,179 @@
+2	0	name=AgentChatContextInjector
+3	0	name=ApprovalEscalationPlanner
+1	0	name=StrategyAwareOptimizer
+0	0	name=LibrarySymbolAdvisor
+1	0	name=TransformEngineExtended
+1	0	name=StrategyAwareOptimizer
+0	0	name=SymbolSelectorAPI
+3	0	name=ApprovalEscalationPlanner
+1	0	name=MemoryModelTranslator
+2	0	name=AgentChatSessionPersistence
+2	0	name=AgentSessionRecorder
+1	0	name=IncrementalOptimizer
+1	0	name=TypeSystemTranslator
+3	0	name=ArchitectReviewInterface
+3	0	name=SecurityExceptionReviewBoard
+0	0	name=SymbolSelectorAPI
+0	0	name=CanaryPromotionJudge
+3	0	name=ArchitectReviewSurface
+1	0	name=TypeAwareMappings
+1	0	name=SecurityPreservingTranslation
+1	0	name=TransformEngineExtended
+3	0	name=ArchitectReviewSurface
+3	0	name=ArchitectReviewInterface
+3	0	name=ArchitectReviewSurface
+2	0	name=PolyglotSuiteOrchestrator
+1	0	name=TransformEngineExtended
+1	0	name=TypeAwareMappings
+2	0	name=AgentChatPanelModel
+2	0	name=ArchitectModuleDecomposer
+1	0	name=TranspilationConfidence
+2	0	name=ArchitectTechStackSelector
+0	0	name=PerTaskLibrarySelector
+3	0	name=ArchitectReviewInterface
+3	0	name=SecurityExceptionReviewBoard
+0	0	name=OperationClassifier
+1	0	name=SelfHostTranspileAudit
+1	0	name=IncrementalOptimizer
+3	0	name=AgentMutationApproval
+0	0	name=OperationSelectorAPI
+1	0	name=SelfHostTranspileAudit
+0	0	name=OperationSelectorAPI
+3	0	name=AgentMutationApproval
+2	0	name=AgentPermissionPolicy
+3	0	name=AgentMutationPreview
+1	0	name=ConcurrencyTranslator
+1	0	name=SelfHostTranspileAudit
+1	0	name=ContextWindowOptimizer
+3	0	name=AgentMutationPreview
+1	0	name=IntentTranslator
+2	0	name=AgentLibraryPolicy
+0	0	name=LibrarySymbolAdvisor
+2	0	name=AgentMarketplace
+1	0	name=TranspilationConfidence
+3	0	name=ApprovalEscalationPlanner
+1	0	name=TransformEngine
+2	0	name=ArchitectIntakeProcessor
+2	0	name=PolyglotOrchestrator
+2	0	name=AgentTaskStatusOverlay
+3	0	name=ArchitectReviewInterface
+0	0	name=OperationSelectorAPI
+0	0	name=LibrarySymbolAdvisor
+3	0	name=SecurityExceptionReviewBoard
+3	0	name=ArchitectReviewInterface
+3	0	name=SecurityExceptionReviewBoard
+2	0	name=ArchitectProblemParser
+0	0	name=SymbolSelectorAPI
+2	0	name=ArchitectProjectPipeline
+0	0	name=PerTaskLibrarySelector
+2	0	name=AgentToolCallVisualization
+0	0	name=TaskitemLibraryAnnotator
+0	0	name=CanaryPromotionJudge
+3	0	name=SecurityExceptionReviewBoard
+0	0	name=OperationSelectorAPI
+1	0	name=TransformEngine
+2	0	name=OnCallCoveragePlanner
+0	0	name=TaskitemLibraryAnnotator
+0	0	name=TaskitemLibraryAnnotator
+3	0	name=AgentMutationPreview
+2	0	name=AgentChatSessionPersistence
+1	0	name=ContextWindowOptimizer
+0	0	name=PerTaskLibrarySelector
+2	0	name=ArchitectMultiLanguageOrchestrator
+1	0	name=TranspilationRPC
+1	0	name=ContextWindowOptimizer
+0	0	name=OperationSelectorAPI
+2	0	name=ArchitectScaffoldGenerator
+2	0	name=ArchitectIntakeProcessor
+2	0	name=AgentMarketplace
+1	0	name=TranspilationConfidence
+3	0	name=ArchitectReviewSurface
+0	0	name=OperationSelectorAPI
+0	0	name=CanaryPromotionJudge
+0	0	name=TaskitemLibraryAnnotator
+2	0	name=AgentChatPanelModel
+0	0	name=LibrarySymbolAdvisor
+1	0	name=SecurityPreservingTranslation
+3	0	name=ApprovalEscalationPlanner
+1	0	name=TypeSystemTranslator
+1	0	name=StrategyAwareOptimizer
+1	0	name=TransformEngineExtended
+2	0	name=AgentSessionRecorder
+2	0	name=ArchitectTechStackSelector
+0	0	name=CanaryPromotionJudge
+3	0	name=ApprovalEscalationPlanner
+2	0	name=AgentTaskSlots
+2	0	name=AgentCodeGen
+0	0	name=SymbolSelectorAPI
+0	0	name=TaskitemLibraryAnnotator
+3	0	name=ApprovalEscalationPlanner
+0	0	name=CanaryPromotionJudge
+3	0	name=AgentMutationApproval
+3	0	name=AgentMutationPreview
+3	0	name=AgentMutationPreview
+2	0	name=AgentTaskSlots
+2	0	name=AgentRPCHandler
+1	0	name=MemoryModelTranslator
+1	0	name=ConcurrencyTranslator
+3	0	name=ArchitectReviewSurface
+2	0	name=AgentToolCallVisualization
+3	0	name=SecurityExceptionReviewBoard
+1	0	name=IncrementalOptimizer
+3	0	name=ApprovalEscalationPlanner
+0	0	name=PerTaskLibrarySelector
+1	0	name=IntentTranslator
+3	0	name=SecurityExceptionReviewBoard
+0	0	name=OperationSelectorAPI
+1	0	name=MemoryModelTranslator
+3	0	name=ArchitectReviewInterface
+0	0	name=OperationClassifier
+3	0	name=ApprovalEscalationPlanner
+0	0	name=OperationClassifier
+0	0	name=TaskitemLibraryAnnotator
+1	0	name=TypeAwareMappings
+3	0	name=ArchitectReviewInterface
+3	0	name=AgentMutationApproval
+2	0	name=AgentRPCHandler
+2	0	name=ArchitectScaffoldGenerator
+2	0	name=ScopeMilestoneDecomposer
+3	0	name=AgentMutationApproval
+3	0	name=AgentMutationPreview
+2	0	name=AgentPermissionPolicy
+0	0	name=PerTaskLibrarySelector
+3	0	name=ArchitectReviewSurface
+0	0	name=TaskitemLibraryAnnotator
+0	0	name=CanaryPromotionJudge
+3	0	name=AgentMutationApproval
+0	0	name=LibrarySymbolAdvisor
+1	0	name=ConcurrencyTranslator
+0	0	name=CanaryPromotionJudge
+2	0	name=WorkflowOrchestrator
+1	0	name=TranspilationRPC
+2	0	name=AgentLibraryPolicy
+1	0	name=TransformEngine
+1	0	name=TranspilationRPC
+2	0	name=OnCallCoveragePlanner
+0	0	name=SymbolSelectorAPI
+2	0	name=PolyglotOrchestrator
+0	0	name=OperationClassifier
+0	0	name=LibrarySymbolAdvisor
+1	0	name=IntentTranslator
+0	0	name=PerTaskLibrarySelector
+2	0	name=WorkflowOrchestrator
+2	0	name=AgentChatContextInjector
+2	0	name=AgentAnnotationAssistant
+3	0	name=AgentMutationApproval
+0	0	name=SymbolSelectorAPI
+3	0	name=ArchitectReviewInterface
+2	0	name=ArchitectMultiLanguageOrchestrator
+2	0	name=ArchitectProblemParser
+1	0	name=StrategyAwareOptimizer
+2	0	name=AgentAnnotationAssistant
+2	0	name=AgentRegistry
+2	0	name=ArchitectModuleDecomposer
+1	0	name=SecurityPreservingTranslation
+2	0	name=ArchitectProjectPipeline
+1	0	name=ContextWindowOptimizer
+2	0	name=PolyglotSuiteOrchestrator
+3	0	name=AgentMutationPreview
+1	0	name=TypeSystemTranslator
diff --git a/specialists/data/generated/worker_type_combined_eval.tsv b/specialists/data/generated/worker_type_combined_eval.tsv
new file mode 100644
index 0000000..ca732b3
--- /dev/null
+++ b/specialists/data/generated/worker_type_combined_eval.tsv
@@ -0,0 +1,115 @@
+0	0	Snapshot persistence (sidecar integration)
+1	0	`whetstone_preview_regeneration_diff_generic` MCP tool
+2	0	Phase 25a Integration
+3	0	Sprint 116 integration summary + regression
+0	0	Debug assist packet bundle model
+1	0	`whetstone_score_failure_triage` MCP tool
+3	0	Regression watchlist for promoted pairs
+2	0	Architecture Templates
+3	0	Phase 10d Integration Tests
+2	0	Phase 21a Integration
+2	0	Result Acceptance Protocol
+2	0	Guided transpilation exercise framework
+0	0	Patch proposal schema and provenance model
+2	0	`whetstone_publish_roadmap_epoch` MCP tool
+0	0	Compliance policy binding engine
+2	0	Workflow Session Protocol
+3	0	Sprint 181 Integration Summary
+2	0	Language-specific method body scaffolding for core patterns
+0	0	Sprint 27 Integration + Summary
+3	0	Phase 15b Integration — Full Protocol Test
+0	0	Long-range edit graph planner
+3	0	Sprint 120 integration summary + regression
+0	0	Federated governance report generator
+3	0	Sprint 66 integration summary + regression
+3	0	Sprint 204 Integration Summary
+2	0	Phase 27a Integration
+1	0	Review Gates
+3	0	Sprint 55 integration summary + regression
+0	0	LTS baseline criteria schema
+0	0	Replay comparison and divergence classification runtime model
+3	0	Sprint 101 integration summary + regression
+2	0	Retry/Escalation Protocol for Constraint Failures
+0	0	Compatibility policy profiles by interface criticality
+0	0	Language support tiers + gates
+2	0	Phase 13d Integration + Sprint 13 Summary
+1	0	Deterministic triage queue planner model
+1	0	Unmappable semantic blocklist + mandatory review gate
+2	0	Phase 23a Integration
+1	0	`whetstone_preview_text_ast_merge_generic` MCP tool
+3	0	Sprint 132 integration summary + regression
+2	0	Phase 27a Integration
+3	0	Sprint 71 integration summary + regression
+2	0	Phase 14b Integration
+0	0	Epoch-2 workstream schema and ownership map
+3	0	Sprint 141 integration summary + regression
+3	0	AST-native projection benchmark suite
+0	0	Certification evidence archive format v2
+2	0	Phase 29a Integration
+0	0	Tier promotion engine (beta->stable)
+1	0	Quarterly lock/review cadence policy
+1	0	Diagnostic normalization runtime implementation model
+2	0	Phase 22a Integration
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Plan Build a streaming join worker correlating click and | Build a streaming join worker correlating click and conversion events with watermark logic.
+0	0	Define verification and readiness surface | Build a live notifications hub with subscription filters, fanout, and reconnect replay support.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build a secrets rotation scheduler with lease tracking, retry plans, and notifications.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+0	0	Define verification and readiness surface | Build kanban API with boards, columns, cards, drag reorder, and activity history.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Plan Build an IoT telemetry gateway supporting MQTT ingestion | Build an IoT telemetry gateway supporting MQTT ingestion, validation, and stream forwarding.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a CLI todo manager with add/list/done/delete commands and JSON file storage.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a whiteboard sync backend with operational ordering and conflict-safe patch application.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+0	0	Define verification and readiness surface | Build an image conversion CLI with resize, format conversion, and batch mode support.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Plan Split monolithic endpoint into read/write paths while preserving | Split monolithic endpoint into read/write paths while preserving latency and memory budgets and updating observability d
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+3	0	Define verification and readiness surface | Build portfolio tracker with holdings, transactions, PnL snapshots, and benchmark comparison.
+0	0	Define verification and readiness surface | Build checkout backend coordinating address, shipping options, totals, and payment intent creation.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+0	0	Define verification and readiness surface | Build chat bot backend with slash commands, permission checks, and scheduled digests.
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build a contacts service with import/export, deduplication, and fuzzy name search.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Define verification and readiness surface | Build realtime polling backend with vote dedupe, room join, and result broadcast.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+0	0	Plan Upgrade API contract from v1 to v2 backend | Upgrade API contract from v1 to v2: backend handlers, OpenAPI schema, generated client SDK, frontend integration, and co
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+0	0	Plan Build a streaming detector with keyed state windows | Build a streaming detector with keyed state windows, out-of-order event handling, watermark policy, and deterministic re
+0	0	Define verification and readiness surface | Build a release notes generator from commits, PR labels, and issue references.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+0	0	Define verification and readiness surface | Build a change-data-capture processor that applies upserts/deletes and checkpoints offsets.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Define verification and readiness surface | Build a model registry API supporting stages, approvals, rollback, and signed artifact links.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
diff --git a/specialists/data/generated/worker_type_combined_train.tsv b/specialists/data/generated/worker_type_combined_train.tsv
new file mode 100644
index 0000000..6e61f58
--- /dev/null
+++ b/specialists/data/generated/worker_type_combined_train.tsv
@@ -0,0 +1,661 @@
+1	0	`whetstone_get_sync_diagnostics` MCP tool
+3	0	Regression fixtures for under-constrained vs capability-limited cases
+3	0	Sprint 83 integration summary + regression
+1	0	Audit trail and inspection
+3	0	Sprint 99 integration summary + regression
+3	0	Security Testing Skeleton Generation
+2	0	Phase 25b Integration
+3	0	Sprint 115 integration summary + regression
+0	0	Feedback Loop — Rejection Re-Routing
+2	0	Long-horizon roadmap planning engine v2
+2	0	Retry/Escalation Protocol for Constraint Failures
+0	0	`BuildErrorRecord` schema
+2	0	Phase 26a Integration
+3	0	Sprint 179 Integration Summary
+0	0	Policy-compliance auto-checkpoint integration
+2	0	Refactor grammar generator to use normalized schema IR
+3	0	Intake-to-Queue Simulation Harness
+3	0	Sprint 50 integration summary + regression
+1	0	Human review queue generator from ambiguities
+2	0	Scaffold File Generation
+3	0	Sprint 85 integration summary + regression
+0	0	`whetstone_get_swarm_maintenance_status` MCP tool
+3	0	Sprint 157 integration summary + regression
+3	0	Full historical regression + post-release checklist
+1	0	`whetstone_normalize_diagnostics` runtime implementation
+3	0	End-to-end — Python PriorityQueue → C++, Rust, Go
+2	0	Phase 12d Integration + Sprint 12 Summary
+1	0	False-green diagnostic class
+3	0	Sprint 86 integration summary + regression
+3	0	Sprint 64 integration summary + regression
+3	0	Sprint 142 integration summary + regression
+1	0	Priority-focused review queue shaping engine
+1	0	Efficiency diagnostics and trend report
+0	0	Context slice canonicalization for handoffs
+0	0	Context Bundle Format
+3	0	Reference implementation harness for IR/evidence specs
+1	0	Constraint completeness diagnostics
+1	0	Porting review board model
+0	0	Maintenance demand estimator
+0	0	`whetstone_get_program_kpis` MCP tool
+1	0	Tool-surface diagnostics report artifact
+3	0	Rust runner adapter for harness
+2	0	`whetstone_verify_architecture_consistency` MCP tool
+1	0	Security scan orchestrator for generated targets
+1	0	Strictness audit utility and baseline report
+0	0	Sprint pipeline summary enrichment
+0	0	C Parser — Functions, Structs, Enums
+1	0	Call Stack and Frame Inspector
+3	0	Sprint 74 integration summary + regression
+2	0	Phase 25b Integration
+0	0	Binary/interface diff engine integration
+3	0	Sprint 125 integration summary + regression
+1	0	Reviewer quorum policy model for critical approvals
+1	0	Conflict preview and impact estimator model
+3	0	Test failure classifier
+3	0	Benchmark ingestion support for projection schema
+0	0	Artifact quality scoring and ranking engine
+3	0	Sprint 47 integration summary + regression
+0	0	`whetstone_assemble_context` MCP tool
+0	0	Legacy modernization dossier generator
+0	0	Step Engine
+1	0	Agent role contract schema (`analyzer`, `patcher`, `verifier`, `reviewer`)
+0	0	`whetstone_trigger_porting_incident_drill` MCP tool
+1	0	Lint diagnostics normalization
+1	0	AST mutation preview
+2	0	Burn-down planning optimizer
+1	0	KPI delta analysis engine for block review
+2	0	Long-horizon roadmap planning engine v2
+0	0	`whetstone_rollback_constructive_transaction` MCP tool
+2	0	Deterministic blocker taxonomy
+1	0	Docking Reliability Audit + Deterministic Layout Rules
+0	0	`whetstone_run_build_iteration` MCP tool
+1	0	Divergence triage model for interop failures
+2	0	Phase 36a Integration
+0	0	Language capability conformance report artifact
+3	0	`whetstone_run_pair_benchmark` MCP tool
+1	0	`whetstone_optimize_review_queue` MCP tool
+3	0	Sprint 205 Integration Summary
+1	0	Loop summary contract diagnostics
+2	0	Phase 13a Integration — Layout Persistence
+3	0	Sprint 189 Integration Summary
+2	0	Continuity drill framework and scoring
+2	0	Deterministic blocker taxonomy extension
+3	0	Cross-team benchmark comparator
+0	0	VB.NET lowering/raising adapters
+1	0	Review-Gate Policy Refinement
+2	0	Phase 14d Integration + Sprint 14 Summary
+0	0	Multi-language compile gate executor
+1	0	Dependency and supply-chain audit packet
+1	0	Reviewer-focused semantic diff summarizer
+1	0	Architect Review Surface for Intake
+2	0	Phase 24a Integration
+2	0	Long-range blocker taxonomy
+2	0	Result Acceptance Protocol
+1	0	Patch proposal review report artifact
+1	0	Parity diagnostics export
+3	0	Debug benchmark harness for fixture suites
+1	0	Triage packet bundle model
+1	0	Incremental sync diagnostics model
+2	0	Swarm maintenance job decomposition model
+0	0	Epoch kickoff report artifact
+3	0	Sprint 96 integration summary + regression
+2	0	Phase 32a Integration
+2	0	Self-Hosting Progress Report + Phase Integration
+2	0	Phase 13a Integration — Layout Persistence
+0	0	Sprint 28 Integration + Summary
+2	0	Migration Plan Generator
+2	0	Phase 20a Integration
+3	0	End-to-end replay + rollback scenario suite
+3	0	C++ runner adapter for harness
+1	0	Safety Audit via Annotations
+2	0	Phase 33a Integration
+3	0	Sprint 79 integration summary + regression
+0	0	Lisp lowering/raising adapters
+0	0	`whetstone_run_porting_gates` MCP tool
+1	0	Explainability compression model for rapid review
+2	0	Phase 32a Integration
+3	0	Sprint 51 integration summary + regression
+3	0	Sprint 175 Integration Summary
+3	0	Sprint 146 integration summary + regression
+2	0	Deterministic blocker taxonomy extension
+3	0	Sprint 139 integration summary + regression
+3	0	Sprint 90 integration summary + full-program regression
+3	0	Benchmark publication bundle
+2	0	Transpilation failure taxonomy schema
+3	0	Sprint 138 integration summary + regression
+1	0	Architect Review Interface
+1	0	Real adapter diagnostics in status tool
+0	0	Kotlin Parser
+1	0	Remediation router from gate diagnostics to tool actions
+0	0	Family promotion checks (experimental->beta)
+2	0	Phase 16a Integration
+3	0	Sprint 73 integration summary + regression
+2	0	Phase 13d Integration + Sprint 13 Summary
+0	0	AnnotationValidator — Subject 5-8 Rules
+0	0	Deterministic replay pack composer
+1	0	Assurance review dossier template
+3	0	Auto-tuning proposal generator from benchmark deltas
+1	0	`whetstone_get_distributed_triage_queue` MCP tool
+1	0	KPI anomaly triage model
+2	0	Phase 36a Integration
+2	0	Module Decomposition Engine
+1	0	Scope ambiguity diagnostics
+2	0	Phase 38a Integration
+1	0	Governance and audit report bundle
+2	0	Phase 13b Integration — Visual Consistency
+3	0	CI integration in build/test flow
+0	0	Zero-trust policy model for execution surfaces
+1	0	Patch execution audit bundle
+2	0	Phase 30a Integration
+1	0	Drift audit report artifact
+0	0	`whetstone_marketplace_search` MCP tool
+3	0	Cross-language class emission parity tests
+3	0	Test output parser — gtest format
+0	0	`whetstone_get_debug_campaign_status` MCP tool
+1	0	Dynamic family acceptance report + review queue wiring
+3	0	Sprint 191 Integration Summary
+2	0	Generator Updates + Phase 11c Integration
+1	0	Review effort estimator from ambiguity/risk packets
+3	0	Sprint 152 integration summary + regression
+2	0	Candidate generation engine from failure taxonomy
+0	0	Ambiguity packet model (`assumed`, `unknown`, `conflict`)
+3	0	Sprint 198 Integration Summary
+1	0	Memory Inspector UI Model
+0	0	Argument/result canonicalizer model
+3	0	Sprint 89 integration summary + regression
+1	0	Divergence classification and triage model
+0	0	`whetstone_run_constructive_loop` MCP tool
+1	0	Dependency Audit Annotations
+3	0	Benchmark runner and metrics export
+3	0	Sprint 62 integration summary + regression
+1	0	Review Comparison View
+1	0	Review SLA policy integration
+0	0	Failure injection and safety validation model
+1	0	Intent drift diagnostics export
+3	0	Sprint 186 Integration Summary
+0	0	Auto Type Deduction
+2	0	Scope and Milestone Decomposer
+2	0	Phase 25a Integration
+1	0	Constraint Violation Diagnostics
+2	0	Refactor pattern schema and metadata model
+1	0	`whetstone_normalize_diagnostics` MCP tool
+0	0	Replay/transaction reliability report artifact
+1	0	Reviewer effectiveness report artifact
+1	0	Post-incident continuity audit report model
+1	0	Entropy scanner — editor-side
+2	0	Phase 13c Integration — Keyboard Shortcuts Help Panel
+3	0	Test gate runner and minimal harness injection
+2	0	Backend framework adapter hooks
+0	0	Enhanced evidence requirements engine
+1	0	`whetstone_preview_regenerated_diff` MCP tool
+1	0	Hint safety guardrails and audit fields
+2	0	Refactor intent annotation model
+3	0	Sprint 137 integration summary + regression
+1	0	Reporting templates for C++ review teams
+0	0	Generic/monomorphization intent model
+0	0	`whetstone_compare_mcp_replays` MCP tool
+0	0	Memory Model Translation
+0	0	Schema evolution compatibility checker
+0	0	Closeout consistency gate
+0	0	Real-time constraint model (`deadline`, `jitter`, `period`)
+2	0	Workflow Session Protocol
+0	0	Include/import ordering normalization model
+2	0	Deprecation/succession lifecycle framework
+0	0	Trace Timeline Model
+1	0	Decision consistency analyzer across reviewers
+1	0	Profile compliance auditor integration
+0	0	`whetstone_plan_rollout_stage` MCP tool
+0	0	Top-level strictness gate
+0	0	Strict queue gate for execution contracts
+3	0	Sprint 58 integration summary + regression
+3	0	Sprint 48 integration summary + regression
+0	0	`whetstone_detect_text_ast_conflicts_generic` MCP tool
+2	0	Phase 19a Integration
+1	0	`whetstone_get_review_load_status` MCP tool
+3	0	Phase 19b Integration + Sprint Summary
+3	0	Sprint 200 Integration Summary
+0	0	Async/await state intent lowering
+1	0	Failure triage score model
+0	0	Plan fingerprinting and replay checks
+1	0	MCP replay diagnostics artifact
+0	0	Plugin compatibility resolver (core/API/version)
+1	0	Diagnostic normalization canonical model
+3	0	Test-to-source locator
+0	0	Debug action budget model
+2	0	Scaffold File Generation
+1	0	Canonical diagnostic normalization from provider/LSP output
+2	0	Backend framework adapter hooks
+3	0	Sprint 162 Integration Summary
+2	0	Phase 39a Integration
+0	0	ADT + pattern matching canonical lowering
+2	0	Verification gate integration for architecture artifacts
+0	0	Modernization RPC + MCP
+2	0	Phase 19a Integration
+3	0	Convention Extractor + Validator (tests: unit, negative, regression)
+1	0	`whetstone_preview_text_ast_merge` MCP tool
+0	0	ABI gate bindings to tier promotions
+2	0	Architecture claim linkage engine
+0	0	Permission conformance report artifact
+2	0	Phase 20a Integration
+2	0	Governance model refresh framework
+1	0	Sync diagnostics normalization model
+3	0	Sprint 63 integration summary + regression
+0	0	`whetstone_suggest_build_fix` MCP tool
+3	0	A/B + benchmark validation artifact update
+0	0	`whetstone_plan_tool_migrations` MCP tool
+3	0	Full regression + architecture gate
+0	0	C interop adapter deepening
+3	0	Phase 10e Integration Tests
+2	0	Phase 29a Integration
+2	0	Scope and Milestone Decomposer
+0	0	Multi-check gate orchestrator model
+1	0	Lint executor integration
+3	0	Sprint 118 integration summary + regression
+1	0	Dropped-content diagnostics packet
+0	0	Execution trace and recovery packet export
+2	0	Phase 18a Integration
+3	0	Sprint 45 Integration Summary
+2	0	Deterministic blocker taxonomy
+2	0	Refactor pattern schema and metadata model
+1	0	Reviewer decision ledger integration
+2	0	Phase 28a Integration
+2	0	Phase 37a Integration
+3	0	Sprint 114 integration summary + regression
+2	0	`whetstone_publish_roadmap_epoch` MCP tool
+1	0	`whetstone_review_porting_decision` MCP tool
+2	0	Language-specific method body scaffolding for core patterns
+1	0	Audit trail completeness checker
+1	0	C++ include fixer from gate diagnostics
+3	0	End-to-end capability inventory and gap scan
+1	0	Static registry scanner for `register*Tools` blocks
+2	0	Phase 31a Integration
+1	0	`whetstone_rank_failure_triage_actions` MCP tool
+3	0	Timing regression runner integration
+2	0	Phase 40a Integration
+1	0	Reviewer load and fatigue model
+2	0	Swarm maintenance job decomposition model
+2	0	Target projection blocker taxonomy
+0	0	Annotate Whetstone's Own Code
+2	0	Phase 15c Integration + Sprint 15 Summary
+0	0	Epoch block health re-baseline model
+3	0	Sprint 159 integration summary + regression
+1	0	Human Review Interface via MCP
+0	0	Transpile Whetstone Modules
+0	0	Capability matrix model
+2	0	Phase 14d Integration + Sprint 14 Summary
+3	0	Prior-Step Context Injector (tests: unit, integration)
+0	0	Unsafe-practice detection and quarantine
+3	0	Sprint 127 integration summary + regression
+1	0	`TaskitemQualityAuditor` — batch report
+3	0	Systemic regression detector
+0	0	Debug campaign spec model
+3	0	`whetstone_get_execution_attestation` MCP tool
+3	0	Sprint 72 integration summary + regression
+2	0	Self-Hosting Progress Report + Phase Integration
+0	0	C# Parser
+1	0	Ambiguity triage UI model and API
+0	0	F# Parser
+0	0	Result-to-ObservationRecord mapper
+0	0	Self-service escalation handoff hooks
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build job queue service with delayed jobs, retries, visibility timeout, and metrics.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Define verification and readiness surface | Build a CLI password vault with encrypted local storage and master-key unlock.
+0	0	Define verification and readiness surface | Build order management with status machine, cancellation rules, and shipment events.
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build a registry mirror service with digest verification, cache pruning, and pull-through.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+0	0	Define verification and readiness surface | Build a websocket chat server with rooms, presence, typing indicators, and message history.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+0	0	Define verification and readiness surface | Build subscription billing engine with proration, trials, coupons, and failed-payment retries.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+0	0	Define verification and readiness surface | Build invoice generator with tax calculation, due schedules, and PDF export metadata.
+0	0	Define verification and readiness surface | Build a webhook dispatcher with retries, signature verification, dead-letter queue, and backoff.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Plan Build a ticker stream service with topic subscriptions | Build a ticker stream service with topic subscriptions and throttled update delivery.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a CLI log tailer with multi-file follow, regex filters, and output highlighting.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a CSV analyzer CLI with schema inference, summary stats, and filter expressions.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build returns API with RMA creation, restock policy, and refund eligibility checks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a service monitor that runs health checks, tracks SLO windows, and pages on breaches.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build expense backend with receipt OCR placeholders, category budgets, and recurring expenses.
+0	0	Define verification and readiness surface | Build a harness that transpiles class-heavy source modules across multiple target languages and validates class/method p
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+0	0	Define verification and readiness surface | Build matchmaking service with queue buckets, skill-based pairing, and timeout fallback.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+0	0	Plan Build an incremental snapshot builder that compacts event | Build an incremental snapshot builder that compacts event logs into query-optimized state.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+0	0	Define verification and readiness surface | Build a REST Todo API with CRUD, pagination, filtering by status, and SQLite persistence.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+0	0	Plan Add normalized address schema migrate legacy rows with | Add normalized address schema, migrate legacy rows with backfill job, dual-read/write transition, and rollback script.
+0	0	Define verification and readiness surface | Build a log enrichment batch job joining geo data and user agents with partitioned output.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+0	0	Define verification and readiness surface | Build a URL shortener API with custom aliases, redirect tracking, and expiration support.
+0	0	Define verification and readiness surface | Build meeting notes API with templates, attendee action items, and follow-up reminders.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build cart service with item merge, discount application, and inventory reservation integration.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build session store service with token revocation, idle timeout, and concurrent login policy.
+0	0	Define verification and readiness surface | Build a secret rotation controller with staged rollout, canary verification, rollback triggers, and explicit blast-radiu
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Plan shared sync core plus Android/Desktop/Web projections with platform-specific | Implement shared sync core plus Android/Desktop/Web projections with platform-specific persistence and transport adapter
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Define verification and readiness surface | Build LLM guardrail service for policy checks, PII filtering, and response classification.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a multi-tenant limiter with token bucket + sliding window hybrid policy, burst fairness guarantees, and lock-free 
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a Kubernetes manifest linter enforcing probes, limits, and namespace policy.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+0	0	Define verification and readiness surface | Build an API for file metadata indexing, search by attributes, and soft delete recovery.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build experiment tracking backend storing params, metrics, artifacts, and compare queries.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build user profile service with avatars, privacy settings, and profile completeness scoring.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+0	0	Define verification and readiness surface | Build batch inference pipeline reading partitions, loading model, and writing scored outputs.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build a JWT auth service with register, login, refresh token rotation, and password hashing.
+0	0	Define verification and readiness surface | Build notification preferences API with channel rules, quiet hours, and topic subscriptions.
+0	0	Plan Build a CI orchestrator service triggering jobs tracking | Build a CI orchestrator service triggering jobs, tracking states, and emitting summaries.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build a harness that transpiles class-heavy source modules across multiple target languages and validates class/method p
+0	0	Plan telemetry agent for linux arduino targets using shared | Implement telemetry agent for linux + arduino targets using shared serialization core and target-specific runtime wrappe
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build prompt evaluation runner with rubric scoring, aggregate metrics, and reproducible reports.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a feature store service with online/offline reads and point-in-time correctness.
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build wiki backend with page versions, backlinks, and markdown rendering pipeline hooks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build drift detection worker comparing live feature distributions against reference baselines.
+0	0	Define verification and readiness surface | Build form builder backend with schema validation, submissions, and analytics counters.
+0	0	Define verification and readiness surface | Build email campaign manager with lists, segmentation, scheduling, and bounce tracking.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Define verification and readiness surface | Build an access gateway that evaluates hierarchical allow/deny policies with shadow rules, policy versioning, and explai
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a presence tracker with heartbeat timeout, status transitions, and shard-safe updates.
+0	0	Define verification and readiness surface | Build payments API with idempotency keys, ledger-safe transfers, and webhook callbacks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Plan Build a task runner CLI that reads YAML | Build a task runner CLI that reads YAML tasks and executes dependency-aware command graphs.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build configuration service with versioned configs, staged rollout, and validation checks.
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+0	0	Define verification and readiness surface | Build warehouse picking service with wave assignment, pick confirmation, and shortage handling.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build shipping label worker integrating carrier rates, label generation, and tracking updates.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a metrics aggregation worker with tumbling windows, late data handling, and rollups.
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build backup retention manager with policy tiers, legal hold support, and deletion safety checks.
+0	0	Plan Build reconciliation service matching ledger entries to bank | Build reconciliation service matching ledger entries to bank statements with mismatch reporting.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build an ETL pipeline that ingests orders CSV, validates schema, and loads curated tables.
+0	0	Define verification and readiness surface | Build search suggest API with prefix index, typo tolerance, and popularity boosting.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build a feature flag API with environments, targeting rules, and rollout percentages.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+0	0	Plan Replace search ranking pipeline behind feature flag with | Replace search ranking pipeline behind feature flag with staged rollout, telemetry checks, and automatic abort trigger.
+0	0	Define verification and readiness surface | Build a training scheduler with queue priorities, resource quotas, and retry policies.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+0	0	Define verification and readiness surface | Build a gateway that validates incoming payloads against versioned contracts, performs semantic constraint checks, and e
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a backup CLI with include/exclude rules, incremental snapshots, and restore command.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+0	0	Define verification and readiness surface | Build pricing engine with currency handling, promotions, and time-bound campaign rules.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+0	0	Define verification and readiness surface | Build an event deduplicator using idempotency keys, time windows, and replay-safe writes.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Define verification and readiness surface | Build dataset version management with lineage metadata, immutable snapshots, and diff operations.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+0	0	Define verification and readiness surface | Build tax report backend aggregating gains/losses and generating filing-year summaries.
+0	0	Define verification and readiness surface | Build distributed rate limiter with fixed/sliding window modes and policy APIs.
+0	0	Define verification and readiness surface | Build telemetry collector with trace/span ingestion, sampling, and export adapters.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | Build a CRDT-based collaborative notes backend with causal metadata, merge convergence proofs, tombstone compaction, and
+0	0	Define verification and readiness surface | Build a loader from object storage to warehouse with schema evolution and retry checkpoints.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+0	0	Define verification and readiness surface | Build access control service with RBAC roles, permissions, and resource-scoped grants.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+3	0	Define verification and readiness surface | Refactor billing pipeline to introduce idempotency keys and rollback checkpoints across ledger service, queue worker, re
+0	0	Define verification and readiness surface | Build a CDC replication worker that handles schema evolution, backfill merges, checkpoint consistency, and deterministic
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+0	0	Plan Build drift detection comparing desired and observed infra | Build drift detection comparing desired and observed infra states with actionable diff reports.
+1	0	Define verification and readiness surface | Build a ledger reconciliation service with strict double-entry invariants, idempotent replay, rollback checkpoints, and 
+0	0	Define verification and readiness surface | Build product catalog API with variants, facets, search indexing hooks, and soft delete.
+0	0	Define verification and readiness surface | Build a realtime log viewer backend with tail sessions, regex filters, and backpressure.
+1	0	Define verification and readiness surface | Build audit log service with immutable events, filtering, export, and retention policies.
+1	0	Define verification and readiness surface | Build localization service with key bundles, fallback locales, and missing-key diagnostics.
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a realtime cursor service broadcasting positions with rate limiting and stale cleanup.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+0	0	Define verification and readiness surface | Build a text diff CLI with unified output, word-level mode, and ignore-whitespace option.
+0	0	Define verification and readiness surface | Build calendar backend with events, recurrence rules, reminders, and timezone normalization.
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build inventory endpoints with stock reservation, release, and low-stock alerts.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+0	0	Define verification and readiness surface | Build an inference API with model loading, request validation, and batch prediction endpoint.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+0	0	Define verification and readiness surface | Build recommendation API combining collaborative and rule-based fallback candidate generation.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build an order saga orchestrator with compensating actions, timeout escalation, exactly-once message handling, and deter
+2	0	Plan Introduce deny-by-default RBAC policy and propagate through backend | Introduce deny-by-default RBAC policy and propagate through backend auth middleware, endpoint guards, frontend route gua
+2	0	Plan Build a generator that scaffolds Terraform modules with | Build a generator that scaffolds Terraform modules with inputs, outputs, and policy checks.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build a .env manager CLI with profile switch, validation, and secure redaction in output.
+1	0	Define verification and readiness surface | Build fraud rules engine with rule evaluation graph, score thresholds, and audit trails.
+0	0	Define verification and readiness surface | Build a CMS backend with posts, tags, draft/publish workflow, and role-based access control.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+1	0	Define verification and readiness surface | Build review moderation with profanity checks, spam heuristics, and moderation queue endpoints.
+0	0	Define verification and readiness surface | Build a log shipping agent with offset persistence, multiline parsing, and retries.
+0	0	Define verification and readiness surface | Build a data quality checker with null, range, uniqueness, and referential integrity rules.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+0	0	Define verification and readiness surface | Build payout scheduler with settlement windows, minimum thresholds, and retry-safe processing.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
+2	0	Align docs with bootstrap architecture | Build KYC workflow with document checks, status transitions, and reviewer assignment queues.
+1	0	Define verification and readiness surface | Build a distributed scheduler with per-resource mutex locks, lease renewal, deadlock avoidance ordering, and determinist
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+1	0	Define verification and readiness surface | Build an incremental build executor over a DAG with content-hash invalidation, topological scheduling, cycle diagnostics
+2	0	Align docs with bootstrap architecture | Build document search service with indexing, permissions filtering, and ranking features.
+3	0	Define verification and readiness surface | Build a CRDT-based collaborative notes backend with causal metadata, merge convergence proofs, tombstone compaction, and
+0	0	Define verification and readiness surface | Build a notes sync API with optimistic concurrency, conflict detection, and change feed endpoints.
+0	0	Define verification and readiness surface | Build OCR queue processor with job retries, dead-letter handling, and extraction status API.
+0	0	Define verification and readiness surface | Build shared core and projections but omit projection contract fields intentionally.
+1	0	Define verification and readiness surface | Build a PII redaction pipeline masking emails, phones, and IDs with audit logging.
+3	0	Define verification and readiness surface | All core features implemented Tests passing
diff --git a/specialists/eval/results/automatability_decompose.json b/specialists/eval/results/automatability_decompose.json
new file mode 100644
index 0000000..434beaa
--- /dev/null
+++ b/specialists/eval/results/automatability_decompose.json
@@ -0,0 +1,165 @@
+{
+  "gate": "automatability",
+  "flat_6way_baseline": {
+    "small_plus": 69.6,
+    "medium": 78.3
+  },
+  "decomposed": {
+    "stage1_binary": {
+      "overall_accuracy": 100.0,
+      "n_eval": 46,
+      "per_class": {
+        "low_entropy": {
+          "acc": 100.0,
+          "n": 17
+        },
+        "needs_routing": {
+          "acc": 100.0,
+          "n": 29
+        }
+      },
+      "confusion_summary": [],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        }
+      ],
+      "guardrail_threshold": 0.5,
+      "guardrail_abstain_rate": 0.0,
+      "eval_latency_ms_per_example": 5.294,
+      "model_config": {
+        "hidden_dim": 256,
+        "layers": 2,
+        "heads": 4,
+        "n_labels": 2,
+        "seq_len": 96,
+        "vocab_size": 133
+      },
+      "verdict": "deploy_direct"
+    },
+    "stage2_4way": {
+      "overall_accuracy": 100.0,
+      "n_eval": 29,
+      "per_class": {
+        "specialist": {
+          "acc": 100.0,
+          "n": 9
+        },
+        "slm": {
+          "acc": 100.0,
+          "n": 7
+        },
+        "llm": {
+          "acc": 100.0,
+          "n": 4
+        },
+        "human": {
+          "acc": 100.0,
+          "n": 9
+        }
+      },
+      "confusion_summary": [],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 29,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 29,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 29,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 29,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 29,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 100.0
+        }
+      ],
+      "guardrail_threshold": 0.5,
+      "guardrail_abstain_rate": 0.0,
+      "eval_latency_ms_per_example": 8.796,
+      "model_config": {
+        "hidden_dim": 256,
+        "layers": 2,
+        "heads": 4,
+        "n_labels": 4,
+        "seq_len": 96,
+        "vocab_size": 55
+      },
+      "verdict": "deploy_direct"
+    },
+    "combined": {
+      "method": "2stage_decomposed",
+      "routing_accuracy": 100.0,
+      "accuracy_5way": 100.0,
+      "n_eval": 46,
+      "per_class_5way": {
+        "low_entropy": {
+          "acc": 100.0,
+          "n": 17
+        },
+        "specialist": {
+          "acc": 100.0,
+          "n": 9
+        },
+        "slm": {
+          "acc": 100.0,
+          "n": 7
+        },
+        "llm": {
+          "acc": 100.0,
+          "n": 4
+        },
+        "human": {
+          "acc": 100.0,
+          "n": 9
+        }
+      },
+      "top_errors": [],
+      "note": "low_entropy bucket = {deterministic, template} merged; 5-way is the effective label space"
+    }
+  }
+}
\ No newline at end of file
diff --git a/specialists/eval/results/automatability_sweep.json b/specialists/eval/results/automatability_sweep.json
new file mode 100644
index 0000000..d7aa861
--- /dev/null
+++ b/specialists/eval/results/automatability_sweep.json
@@ -0,0 +1,178 @@
+{
+  "gate": "automatability",
+  "labels": "deterministic,template,specialist,slm,llm,human",
+  "train": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/generated/automatability_train.tsv",
+  "eval": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/generated/automatability_eval.tsv",
+  "tiers": [
+    {
+      "tier": "small_plus",
+      "hidden": 256,
+      "layers": 2,
+      "heads": 4,
+      "model_size_approx": "~1M params",
+      "pilot_accuracy": 69.6,
+      "pilot_time_s": 150.0,
+      "eval_accuracy": 69.6,
+      "per_class": {
+        "deterministic": {
+          "acc": 0.0,
+          "n": 10
+        },
+        "template": {
+          "acc": 42.857142857142854,
+          "n": 7
+        },
+        "specialist": {
+          "acc": 100.0,
+          "n": 9
+        },
+        "slm": {
+          "acc": 100.0,
+          "n": 7
+        },
+        "llm": {
+          "acc": 100.0,
+          "n": 4
+        },
+        "human": {
+          "acc": 100.0,
+          "n": 9
+        }
+      },
+      "confusion_summary": [
+        {
+          "gt": "deterministic",
+          "pred": "llm",
+          "count": 10,
+          "gt_total": 10
+        },
+        {
+          "gt": "template",
+          "pred": "llm",
+          "count": 4,
+          "gt_total": 7
+        }
+      ],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 69.6
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 69.6
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 69.6
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 69.6
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 32,
+          "abstain_rate": 0.304,
+          "accepted_accuracy": 100.0
+        }
+      ],
+      "guardrail_threshold": 0.9,
+      "guardrail_abstain_rate": 0.304,
+      "eval_latency_ms": 5.137,
+      "verdict": "decompose_or_relabel",
+      "action": "decompose_or_relabel",
+      "eval_result_path": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/eval/results/automatability_small_plus.json"
+    },
+    {
+      "tier": "medium",
+      "hidden": 384,
+      "layers": 3,
+      "heads": 6,
+      "model_size_approx": "~5M params",
+      "pilot_accuracy": 78.3,
+      "pilot_time_s": 390.0,
+      "eval_accuracy": 78.3,
+      "per_class": {
+        "deterministic": {
+          "acc": 0.0,
+          "n": 10
+        },
+        "template": {
+          "acc": 100.0,
+          "n": 7
+        },
+        "specialist": {
+          "acc": 100.0,
+          "n": 9
+        },
+        "slm": {
+          "acc": 100.0,
+          "n": 7
+        },
+        "llm": {
+          "acc": 100.0,
+          "n": 4
+        },
+        "human": {
+          "acc": 100.0,
+          "n": 9
+        }
+      },
+      "confusion_summary": [
+        {
+          "gt": "deterministic",
+          "pred": "template",
+          "count": 10,
+          "gt_total": 10
+        }
+      ],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 78.3
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 78.3
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 78.3
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 78.3
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 46,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 78.3
+        }
+      ],
+      "guardrail_threshold": null,
+      "guardrail_abstain_rate": null,
+      "eval_latency_ms": 5.345,
+      "verdict": "decompose_or_relabel",
+      "action": "decompose_or_relabel",
+      "eval_result_path": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/eval/results/automatability_medium.json"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/specialists/eval/results/prereq_op_sweep.json b/specialists/eval/results/prereq_op_sweep.json
new file mode 100644
index 0000000..e642905
--- /dev/null
+++ b/specialists/eval/results/prereq_op_sweep.json
@@ -0,0 +1,116 @@
+{
+  "gate": "prereq_op",
+  "labels": "standard,needs_review,needs_approval,full_gates",
+  "train": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/combined/prereq_op_train.tsv",
+  "eval": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/combined/prereq_op_eval.tsv",
+  "tiers": [
+    {
+      "tier": "small_plus",
+      "hidden": 256,
+      "layers": 2,
+      "heads": 4,
+      "model_size_approx": "~1M params",
+      "pilot_accuracy": 75.0,
+      "pilot_time_s": 152.0,
+      "eval_accuracy": 72.2,
+      "per_class": {
+        "standard": {
+          "acc": 37.5,
+          "n": 8
+        },
+        "needs_review": {
+          "acc": 80.0,
+          "n": 10
+        },
+        "needs_approval": {
+          "acc": 66.66666666666666,
+          "n": 9
+        },
+        "full_gates": {
+          "acc": 100.0,
+          "n": 9
+        }
+      },
+      "confusion_summary": [
+        {
+          "gt": "standard",
+          "pred": "needs_approval",
+          "count": 4,
+          "gt_total": 8
+        },
+        {
+          "gt": "needs_approval",
+          "pred": "needs_review",
+          "count": 2,
+          "gt_total": 9
+        },
+        {
+          "gt": "standard",
+          "pred": "needs_review",
+          "count": 1,
+          "gt_total": 8
+        },
+        {
+          "gt": "needs_review",
+          "pred": "standard",
+          "count": 1,
+          "gt_total": 10
+        },
+        {
+          "gt": "needs_review",
+          "pred": "needs_approval",
+          "count": 1,
+          "gt_total": 10
+        }
+      ],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 36,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 72.2
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 34,
+          "abstain_rate": 0.056,
+          "accepted_accuracy": 76.5
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 34,
+          "abstain_rate": 0.056,
+          "accepted_accuracy": 76.5
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 34,
+          "abstain_rate": 0.056,
+          "accepted_accuracy": 76.5
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 33,
+          "abstain_rate": 0.083,
+          "accepted_accuracy": 78.8
+        }
+      ],
+      "guardrail_threshold": null,
+      "guardrail_abstain_rate": null,
+      "eval_latency_ms": 6.008,
+      "verdict": "decompose_or_relabel",
+      "action": "decompose_or_relabel",
+      "eval_result_path": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/eval/results/prereq_op_small_plus.json"
+    },
+    {
+      "tier": "medium",
+      "hidden": 384,
+      "layers": 3,
+      "heads": 6,
+      "model_size_approx": "~5M params",
+      "pilot_accuracy": 66.7,
+      "pilot_time_s": 388.0,
+      "action": "no_gain_stop_scaling"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/specialists/eval/results/verification_type_sweep.json b/specialists/eval/results/verification_type_sweep.json
new file mode 100644
index 0000000..7c869b5
--- /dev/null
+++ b/specialists/eval/results/verification_type_sweep.json
@@ -0,0 +1,120 @@
+{
+  "gate": "verification_type",
+  "labels": "unit,integration,schema,smoke,docs",
+  "train": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/generated/verification_type_train.tsv",
+  "eval": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/generated/verification_type_eval.tsv",
+  "tiers": [
+    {
+      "tier": "small_plus",
+      "hidden": 256,
+      "layers": 2,
+      "heads": 4,
+      "model_size_approx": "~1M params",
+      "pilot_accuracy": 83.7,
+      "pilot_time_s": 186.0,
+      "eval_accuracy": 83.7,
+      "per_class": {
+        "unit": {
+          "acc": 75.75757575757575,
+          "n": 33
+        },
+        "integration": {
+          "acc": 76.47058823529412,
+          "n": 34
+        },
+        "schema": {
+          "acc": 76.47058823529412,
+          "n": 34
+        },
+        "smoke": {
+          "acc": 93.75,
+          "n": 32
+        },
+        "docs": {
+          "acc": 94.87179487179486,
+          "n": 39
+        }
+      },
+      "confusion_summary": [
+        {
+          "gt": "unit",
+          "pred": "schema",
+          "count": 5,
+          "gt_total": 33
+        },
+        {
+          "gt": "integration",
+          "pred": "unit",
+          "count": 5,
+          "gt_total": 34
+        },
+        {
+          "gt": "schema",
+          "pred": "unit",
+          "count": 4,
+          "gt_total": 34
+        },
+        {
+          "gt": "schema",
+          "pred": "integration",
+          "count": 4,
+          "gt_total": 34
+        },
+        {
+          "gt": "unit",
+          "pred": "integration",
+          "count": 3,
+          "gt_total": 33
+        }
+      ],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 172,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 83.7
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 171,
+          "abstain_rate": 0.006,
+          "accepted_accuracy": 83.6
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 170,
+          "abstain_rate": 0.012,
+          "accepted_accuracy": 83.5
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 164,
+          "abstain_rate": 0.047,
+          "accepted_accuracy": 84.8
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 160,
+          "abstain_rate": 0.07,
+          "accepted_accuracy": 85.0
+        }
+      ],
+      "guardrail_threshold": null,
+      "guardrail_abstain_rate": null,
+      "eval_latency_ms": 4.976,
+      "verdict": "scale_more",
+      "action": "scale_more",
+      "eval_result_path": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/eval/results/verification_type_small_plus.json"
+    },
+    {
+      "tier": "medium",
+      "hidden": 384,
+      "layers": 3,
+      "heads": 6,
+      "model_size_approx": "~5M params",
+      "pilot_accuracy": 84.3,
+      "pilot_time_s": 402.0,
+      "action": "no_gain_stop_scaling"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/specialists/eval/results/worker_type_combined_sweep.json b/specialists/eval/results/worker_type_combined_sweep.json
new file mode 100644
index 0000000..39a41a6
--- /dev/null
+++ b/specialists/eval/results/worker_type_combined_sweep.json
@@ -0,0 +1,116 @@
+{
+  "gate": "worker_type_combined",
+  "labels": "implementer,reviewer,architect,qa",
+  "train": "specialists/data/generated/worker_type_combined_train.tsv",
+  "eval": "specialists/data/generated/worker_type_combined_eval.tsv",
+  "tiers": [
+    {
+      "tier": "small_plus",
+      "hidden": 256,
+      "layers": 2,
+      "heads": 4,
+      "model_size_approx": "~1M params",
+      "pilot_accuracy": 92.2,
+      "pilot_time_s": 155.0,
+      "eval_accuracy": 91.3,
+      "per_class": {
+        "implementer": {
+          "acc": 75.0,
+          "n": 32
+        },
+        "reviewer": {
+          "acc": 100.0,
+          "n": 29
+        },
+        "architect": {
+          "acc": 100.0,
+          "n": 29
+        },
+        "qa": {
+          "acc": 92.0,
+          "n": 25
+        }
+      },
+      "confusion_summary": [
+        {
+          "gt": "implementer",
+          "pred": "reviewer",
+          "count": 6,
+          "gt_total": 32
+        },
+        {
+          "gt": "implementer",
+          "pred": "architect",
+          "count": 1,
+          "gt_total": 32
+        },
+        {
+          "gt": "implementer",
+          "pred": "qa",
+          "count": 1,
+          "gt_total": 32
+        },
+        {
+          "gt": "qa",
+          "pred": "implementer",
+          "count": 1,
+          "gt_total": 25
+        },
+        {
+          "gt": "qa",
+          "pred": "architect",
+          "count": 1,
+          "gt_total": 25
+        }
+      ],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 115,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 91.3
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 113,
+          "abstain_rate": 0.017,
+          "accepted_accuracy": 92.0
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 111,
+          "abstain_rate": 0.035,
+          "accepted_accuracy": 91.9
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 109,
+          "abstain_rate": 0.052,
+          "accepted_accuracy": 91.7
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 109,
+          "abstain_rate": 0.052,
+          "accepted_accuracy": 91.7
+        }
+      ],
+      "guardrail_threshold": null,
+      "guardrail_abstain_rate": null,
+      "eval_latency_ms": 1.993,
+      "verdict": "scale_more",
+      "action": "scale_more",
+      "eval_result_path": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/eval/results/worker_type_combined_small_plus.json"
+    },
+    {
+      "tier": "medium",
+      "hidden": 384,
+      "layers": 3,
+      "heads": 6,
+      "model_size_approx": "~5M params",
+      "pilot_accuracy": 89.6,
+      "pilot_time_s": 393.0,
+      "action": "no_gain_stop_scaling"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/specialists/eval/results/worker_type_sweep.json b/specialists/eval/results/worker_type_sweep.json
new file mode 100644
index 0000000..244c27c
--- /dev/null
+++ b/specialists/eval/results/worker_type_sweep.json
@@ -0,0 +1,104 @@
+{
+  "gate": "worker_type",
+  "labels": "implementer,reviewer,architect,qa",
+  "train": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/generated/worker_type_train.tsv",
+  "eval": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/data/generated/worker_type_eval.tsv",
+  "tiers": [
+    {
+      "tier": "small_plus",
+      "hidden": 256,
+      "layers": 2,
+      "heads": 4,
+      "model_size_approx": "~1M params",
+      "pilot_accuracy": 80.8,
+      "pilot_time_s": 154.0,
+      "eval_accuracy": 80.8,
+      "per_class": {
+        "implementer": {
+          "acc": 42.857142857142854,
+          "n": 14
+        },
+        "reviewer": {
+          "acc": 100.0,
+          "n": 8
+        },
+        "architect": {
+          "acc": 100.0,
+          "n": 16
+        },
+        "qa": {
+          "acc": 85.71428571428571,
+          "n": 14
+        }
+      },
+      "confusion_summary": [
+        {
+          "gt": "implementer",
+          "pred": "reviewer",
+          "count": 5,
+          "gt_total": 14
+        },
+        {
+          "gt": "implementer",
+          "pred": "architect",
+          "count": 3,
+          "gt_total": 14
+        },
+        {
+          "gt": "qa",
+          "pred": "architect",
+          "count": 2,
+          "gt_total": 14
+        }
+      ],
+      "threshold_analysis": [
+        {
+          "threshold": 0.5,
+          "accepted": 52,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 80.8
+        },
+        {
+          "threshold": 0.6,
+          "accepted": 52,
+          "abstain_rate": 0.0,
+          "accepted_accuracy": 80.8
+        },
+        {
+          "threshold": 0.7,
+          "accepted": 51,
+          "abstain_rate": 0.019,
+          "accepted_accuracy": 82.4
+        },
+        {
+          "threshold": 0.8,
+          "accepted": 51,
+          "abstain_rate": 0.019,
+          "accepted_accuracy": 82.4
+        },
+        {
+          "threshold": 0.9,
+          "accepted": 48,
+          "abstain_rate": 0.077,
+          "accepted_accuracy": 85.4
+        }
+      ],
+      "guardrail_threshold": null,
+      "guardrail_abstain_rate": null,
+      "eval_latency_ms": 4.296,
+      "verdict": "scale_more",
+      "action": "scale_more",
+      "eval_result_path": "/home/bill/Documents/CLionProjects/whetstone_DSL/specialists/eval/results/worker_type_small_plus.json"
+    },
+    {
+      "tier": "medium",
+      "hidden": 384,
+      "layers": 3,
+      "heads": 6,
+      "model_size_approx": "~5M params",
+      "pilot_accuracy": 78.8,
+      "pilot_time_s": 393.0,
+      "action": "no_gain_stop_scaling"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/specialists/scripts/split_automatability_decompose.py b/specialists/scripts/split_automatability_decompose.py
new file mode 100644
index 0000000..29313c3
--- /dev/null
+++ b/specialists/scripts/split_automatability_decompose.py
@@ -0,0 +1,332 @@
+#!/usr/bin/env python3
+"""
+split_automatability_decompose.py
+
+Tests whether automatability benefits from a 2-stage decomposition:
+
+  Stage 1 (binary): low_entropy {deterministic, template} vs needs_routing {specialist, slm, llm, human}
+  Stage 2 (4-way):  specialist / slm / llm / human  (only for items routed past stage 1)
+
+The flat 6-way model confuses deterministic↔template because the text features
+that distinguish them aren't present in taskitem titles. This decomposition
+isolates that gap — stage 1 correctly routes low-entropy items out, stage 2
+handles the routed set cleanly.
+
+Outputs combined accuracy as a 5-way result (low_entropy, specialist, slm, llm, human)
+where deterministic/template are merged into one bucket, plus routing accuracy alone.
+
+Usage:
+    python3 specialists/scripts/split_automatability_decompose.py \\
+        --data-dir  specialists/data/generated \\
+        --runs-dir  /mnt/storage/fabricate_runs \\
+        --results-out specialists/eval/results/automatability_decompose.json
+"""
+
+import argparse
+import json
+import subprocess
+import sys
+from collections import Counter
+from pathlib import Path
+
+
+# Must be at module level so torch.load can find __main__.Vocab when unpickling checkpoints
+class Vocab:
+    PAD, UNK = 0, 1
+
+    def __init__(self):
+        self.str_to_id = {"<pad>": 0, "<unk>": 1}
+        self.id_to_str = ["<pad>", "<unk>"]
+
+    def encode(self, text, seq_len):
+        ids = [self.str_to_id.get(t, self.UNK) for t in text.lower().split()]
+        ids = ids[:seq_len]
+        ids += [self.PAD] * (seq_len - len(ids))
+        return ids
+
+    def __len__(self):
+        return len(self.id_to_str)
+
+
+ROOT         = Path(__file__).parent.parent.parent
+VENV_PYTHON  = sys.executable
+TRAIN_SCRIPT = ROOT / "specialists" / "scripts" / "train_specialist_pt.py"
+EVAL_SCRIPT  = ROOT / "specialists" / "eval" / "eval_specialist_pt.py"
+
+# Original 6-way label order: deterministic(0), template(1), specialist(2), slm(3), llm(4), human(5)
+LABEL_NAMES_6 = ["deterministic", "template", "specialist", "slm", "llm", "human"]
+
+# Stage 1: low_entropy = {0, 1}, needs_routing = {2, 3, 4, 5}
+LOW_ENTROPY = {0, 1}
+
+# Stage 2: remap {2→0, 3→1, 4→2, 5→3}
+STAGE2_LABELS = ["specialist", "slm", "llm", "human"]
+STAGE2_REMAP  = {2: 0, 3: 1, 4: 2, 5: 3}
+
+
+def split_binary(src: Path, out: Path):
+    """6-way TSV → binary TSV: low_entropy=0, needs_routing=1."""
+    rows = []
+    with open(src) as f:
+        for line in f:
+            parts = line.strip().split("\t", 2)
+            if len(parts) < 3:
+                continue
+            orig = int(parts[0])
+            rows.append(f"{'0' if orig in LOW_ENTROPY else '1'}\t0\t{parts[2]}")
+    out.write_text("\n".join(rows) + "\n")
+    n0 = sum(1 for r in rows if r.startswith("0"))
+    print(f"  {out.name}: {len(rows)} rows  low_entropy={n0}  needs_routing={len(rows)-n0}")
+
+
+def split_stage2(src: Path, out: Path):
+    """6-way TSV → 4-way TSV keeping only needs_routing rows, remapped to 0-3."""
+    rows = []
+    with open(src) as f:
+        for line in f:
+            parts = line.strip().split("\t", 2)
+            if len(parts) < 3:
+                continue
+            orig = int(parts[0])
+            if orig in STAGE2_REMAP:
+                rows.append(f"{STAGE2_REMAP[orig]}\t0\t{parts[2]}")
+    out.write_text("\n".join(rows) + "\n")
+    from collections import Counter
+    dist = Counter(int(r.split("\t")[0]) for r in rows)
+    print(f"  {out.name}: {len(rows)} rows  " + "  ".join(f"{STAGE2_LABELS[i]}={dist[i]}" for i in range(4)))
+
+
+def train(run_dir: Path, train_tsv: Path, eval_tsv: Path, labels: str, max_steps: int = 10000) -> bool:
+    run_dir.mkdir(parents=True, exist_ok=True)
+    for f in run_dir.glob("*"):
+        f.unlink()
+    r = subprocess.run([
+        str(VENV_PYTHON), str(TRAIN_SCRIPT),
+        "--dataset",      str(train_tsv),
+        "--eval-dataset", str(eval_tsv),
+        "--out-dir",      str(run_dir),
+        "--labels",       labels,
+        "--lr",           "0.001",
+        "--weight-decay", "0.01",
+        "--max-steps",    str(max_steps),
+        "--hidden-dim",   "256",
+        "--layers",       "2",
+        "--heads",        "4",
+        "--batch-size",   "256",
+        "--grok-loss-threshold", "0.05",
+        "--grok-acc-jump",       "10.0",
+        "--stop-after-grokking-blocks", "4",
+        "--reset",
+        "--history-out",  str(run_dir / "history.json"),
+    ])
+    return r.returncode == 0
+
+
+def eval_checkpoint(run_dir: Path, eval_tsv: Path, labels: str) -> dict | None:
+    ck = run_dir / "checkpoint.pt"
+    if not ck.exists():
+        return None
+    r = subprocess.run(
+        [str(VENV_PYTHON), str(EVAL_SCRIPT),
+         "--checkpoint", str(ck),
+         "--dataset", str(eval_tsv), "--labels", labels, "--quiet"],
+        capture_output=True, text=True,
+    )
+    if r.returncode != 0:
+        return None
+    try:
+        return json.loads(r.stdout.strip().splitlines()[-1])
+    except (json.JSONDecodeError, IndexError):
+        return None
+
+
+def evaluate_combined(eval_tsv_6way: Path, stage1_run: Path, stage2_run: Path) -> dict:
+    """Load both models; stage1 routes, stage2 classifies routed items.
+    Reports: routing accuracy, 5-way accuracy (low_entropy merged), and
+    comparison against original 6-way labels."""
+    import torch
+    import torch.nn as nn
+    import numpy as np
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+    def _tok(text):
+        return text.lower().split()
+
+    class _Model(nn.Module):
+        def __init__(self, cfg):
+            super().__init__()
+            D, L, H, V, seq = cfg["hidden_dim"], cfg["layers"], cfg["heads"], cfg["vocab_size"], cfg["seq_len"]
+            self.tok_emb = nn.Embedding(V, D, padding_idx=0)
+            self.pos_emb = nn.Embedding(seq, D)
+            enc = nn.TransformerEncoderLayer(d_model=D, nhead=H, dim_feedforward=D*4,
+                                             dropout=0.0, batch_first=True)
+            self.encoder = nn.TransformerEncoder(enc, num_layers=L, enable_nested_tensor=False)
+            self.head = nn.Linear(D, cfg["n_labels"])
+            self.seq_len = seq
+
+        def forward(self, x):
+            pad_mask = (x == 0)
+            pos = torch.arange(x.size(1), device=x.device).unsqueeze(0)
+            h = self.tok_emb(x) + self.pos_emb(pos)
+            h = self.encoder(h, src_key_padding_mask=pad_mask)
+            lengths = (~pad_mask).float().sum(1, keepdim=True).clamp(min=1)
+            h = (h * (~pad_mask).unsqueeze(-1).float()).sum(1) / lengths
+            return self.head(h)
+
+    def load_model(run_dir):
+        ckpt = torch.load(run_dir / "checkpoint.pt", map_location=device, weights_only=False)
+        m = _Model(ckpt["config"]).to(device)
+        m.load_state_dict(ckpt["model"])
+        m.eval()
+        vocab = ckpt.get("vocab_obj") or ckpt.get("vocab")
+        if isinstance(vocab, dict):
+            class _V:
+                UNK = 1
+                def __init__(self, d): self.str_to_id = d
+                def encode(self, text, seq_len):
+                    ids = [self.str_to_id.get(t, self.UNK) for t in text.lower().split()]
+                    ids = ids[:seq_len]; ids += [0] * (seq_len - len(ids)); return ids
+            vocab = _V(vocab)
+        return m, vocab, ckpt["config"]["seq_len"]
+
+    def predict_probs(model, vocab, seq_len, texts):
+        import torch.nn.functional as F
+        all_probs = []
+        with torch.no_grad():
+            for start in range(0, len(texts), 256):
+                batch = texts[start:start+256]
+                ids = [vocab.encode(t, seq_len) for t in batch]
+                x = torch.tensor(ids, dtype=torch.long, device=device)
+                logits = model(x)
+                all_probs.append(F.softmax(logits, dim=-1).cpu().numpy())
+        return np.concatenate(all_probs, axis=0)
+
+    # Load original 6-way eval data
+    labels_gt, texts = [], []
+    with open(eval_tsv_6way) as f:
+        for line in f:
+            parts = line.strip().split("\t", 2)
+            if len(parts) < 3:
+                continue
+            labels_gt.append(int(parts[0]))
+            texts.append(parts[2])
+    labels_gt = np.array(labels_gt)
+    n = len(labels_gt)
+
+    m1, v1, s1 = load_model(stage1_run)
+    m2, v2, s2 = load_model(stage2_run)
+
+    probs1 = predict_probs(m1, v1, s1, texts)   # shape (n, 2): [low_entropy, needs_routing]
+    probs2 = predict_probs(m2, v2, s2, texts)   # shape (n, 4): [specialist, slm, llm, human]
+
+    stage1_pred = np.argmax(probs1, axis=1)  # 0=low_entropy, 1=needs_routing
+
+    # Ground-truth routing: 0 if original label in {0,1}, else 1
+    gt_routing = np.where(np.isin(labels_gt, [0, 1]), 0, 1)
+    routing_acc = float((stage1_pred == gt_routing).mean() * 100)
+
+    # Build 5-way predictions (low_entropy=0, specialist=1, slm=2, llm=3, human=4)
+    stage2_pred = np.argmax(probs2, axis=1)  # 0-3 → specialist/slm/llm/human
+    pred_5way = np.where(stage1_pred == 0, 0, stage2_pred + 1)
+
+    # Ground-truth 5-way: low_entropy if orig in {0,1}, else stage2 remapped
+    gt_5way = np.where(np.isin(labels_gt, [0, 1]), 0, labels_gt - 1)
+
+    acc_5way = float((pred_5way == gt_5way).mean() * 100)
+    correct_5way = pred_5way == gt_5way
+
+    label_names_5 = ["low_entropy", "specialist", "slm", "llm", "human"]
+    per_class = {}
+    for i, name in enumerate(label_names_5):
+        mask = gt_5way == i
+        per_class[name] = {
+            "acc": float(correct_5way[mask].mean() * 100) if mask.sum() > 0 else None,
+            "n": int(mask.sum()),
+        }
+
+    errors = Counter()
+    for gt, pred in zip(gt_5way.tolist(), pred_5way.tolist()):
+        if gt != pred:
+            errors[(label_names_5[gt], label_names_5[pred])] += 1
+
+    return {
+        "method": "2stage_decomposed",
+        "routing_accuracy": round(routing_acc, 1),
+        "accuracy_5way": round(acc_5way, 1),
+        "n_eval": n,
+        "per_class_5way": per_class,
+        "top_errors": [{"gt": k[0], "pred": k[1], "count": v}
+                       for k, v in errors.most_common(6)],
+        "note": "low_entropy bucket = {deterministic, template} merged; 5-way is the effective label space",
+    }
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--data-dir",    default="specialists/data/generated")
+    ap.add_argument("--runs-dir",    default="/mnt/storage/fabricate_runs")
+    ap.add_argument("--results-out", default="specialists/eval/results/automatability_decompose.json")
+    ap.add_argument("--skip-train",  action="store_true")
+    args = ap.parse_args()
+
+    data_dir  = Path(args.data_dir)
+    runs_dir  = Path(args.runs_dir)
+    results   = Path(args.results_out)
+    results.parent.mkdir(parents=True, exist_ok=True)
+
+    tmp = data_dir  # write split TSVs alongside existing data
+
+    stage1_train = tmp / "automatability_binary_train.tsv"
+    stage1_eval  = tmp / "automatability_binary_eval.tsv"
+    stage2_train = tmp / "automatability_routed_train.tsv"
+    stage2_eval  = tmp / "automatability_routed_eval.tsv"
+
+    print("=== Splitting data ===")
+    split_binary(data_dir / "automatability_train.tsv", stage1_train)
+    split_binary(data_dir / "automatability_eval.tsv",  stage1_eval)
+    split_stage2(data_dir / "automatability_train.tsv", stage2_train)
+    split_stage2(data_dir / "automatability_eval.tsv",  stage2_eval)
+
+    stage1_run = runs_dir / "whetstone_automatability_stage1_binary"
+    stage2_run = runs_dir / "whetstone_automatability_stage2_4way"
+
+    if not args.skip_train:
+        print("\n=== Training stage 1: low_entropy vs needs_routing (binary) ===")
+        train(stage1_run, stage1_train, stage1_eval, "low_entropy,needs_routing")
+
+        print("\n=== Training stage 2: specialist/slm/llm/human (4-way) ===")
+        train(stage2_run, stage2_train, stage2_eval, "specialist,slm,llm,human")
+
+    print("\n=== Evaluating individual models ===")
+    r1 = eval_checkpoint(stage1_run, stage1_eval, "low_entropy,needs_routing")
+    r2 = eval_checkpoint(stage2_run, stage2_eval, "specialist,slm,llm,human")
+    if r1:
+        print(f"  Stage 1 (binary):  {r1.get('overall_accuracy')}%")
+    if r2:
+        print(f"  Stage 2 (4-way):   {r2.get('overall_accuracy')}%")
+
+    print("\n=== Evaluating combined 2-stage pipeline ===")
+    combined = evaluate_combined(data_dir / "automatability_eval.tsv", stage1_run, stage2_run)
+    print(f"  Routing accuracy:  {combined['routing_accuracy']}%")
+    print(f"  5-way accuracy:    {combined['accuracy_5way']}%")
+    print("  Per class (5-way):")
+    for name, stat in combined["per_class_5way"].items():
+        if stat["acc"] is not None:
+            print(f"    {name:20s}: {stat['acc']:.1f}%  (n={stat['n']})")
+
+    output = {
+        "gate": "automatability",
+        "flat_6way_baseline": {"small_plus": 69.6, "medium": 78.3},
+        "decomposed": {
+            "stage1_binary": r1,
+            "stage2_4way":   r2,
+            "combined":      combined,
+        },
+    }
+    results.write_text(json.dumps(output, indent=2))
+    print(f"\nResults → {results}")
+
+
+if __name__ == "__main__":
+    main()