Hypothesis Lab · Answered directly by KELLY · public writes blocked
Hypothesis Lab
KELLY's unknown-ledger, causal-gap, value-of-information, and experiment-planning organ.
Turns surprise, missing variables, and evidence gaps into falsifiable hypotheses with source plans, tests, closure targets, and memory mutation candidates.
Samples Glass Lab, Advanced Processing Evidence Spine, and the lab-specific runtime routes every 15 seconds.
Glass panels
0/3
Snapshot
0/?
Routes
linked
Refresh
15s
This lab uses anchored Glass Lab proof routes only.
Hypothesis & Theory Workbench
Test plans and falsifiers — hypotheses are not facts; memory_candidate ≠ memory write.
- • Source plan + falsifier lanes stay inspect-only until durable candidates land.
- • Closure never promotes truth without settlement + severe-test receipts.
- • Public users cannot create Prime unknowns from this shell.
- • Gauges follow GET event-bus status (process-local Map), not multi-replica truth.
- • List API may serve process-local Map rows when non-empty; else demo_fallback — never multi-replica.
- • CLI Map seed scripts write a separate process Map and do not hydrate this engine HTTP list.
- • memory_candidate is a court-queue hint only — never memory_written / GraphState write.
- • Falsifiers and source-plan are test-plan lists; closure pending is not truth promotion.
Event bus status
Loading event-bus status…
Map stores status
Loading map-stores status…
Organs glass chain
Loading organs chain…
process_is_not_truth · never uses terminal “blocked” · Glass mission control only
APES organ rollups
Loading organ rollups…
instrument rollups · labeled_unproven · never demo-as-live · process_is_not_truth
Glass Lab visibility
Loading visibility pack…
four panels · inspect-only · never terminal “blocked” · process_is_not_truth
Cognition Organs V1
Loading organs V1 completion…
ladder=n/a · neon_any=no · instrumented=no
envelope · neon-first labeled · no direct writes · process_is_not_truth
Operator command ladder
Loading operator ladder…
never auto-deploy · process_is_not_truth · missing_evidence not “blocked”
Program status
Loading program status…
process_is_not_truth · never terminal “blocked” · public lens only
Organ honesty summary
- ✓ Map stores process-local
- ✓ CLI seed ≠ engine HTTP
- ✓ Claim→hyp links not truth
- ✓ Radar inspect-only
- ✓ Severe-test inspect-only
- ✓ Claim strength not settlement
- ✓ memory_candidate ≠ written
- ✓ Falsifiers not proof of kill
- ✓ Closure pending ≠ promotion
- ✓ lineage_view not write
- ✓ birth_chain not settlement
Standing law checklist — never multi_replica_ready; never public write; process is not truth.
Cognition workbench
This is the sector-specific operating view for Hypothesis: gauges, receipt queue, closure timeline, topology, and empty-state behavior. Live route health remains in the real-time panel above.
Unknown ledger
first-class gaps
Surprise, blind spots, missing causes, and missing sources become explicit objects.
Value of information
rank before chase
The lab prioritizes unknowns that can change forecasts, memory, or causal structure.
Experiment plan
source + test
Each hypothesis needs a source plan, falsifier, and closure target.
Closure
confirm / weaken / kill
Outcomes must be explicit before memory or GraphState promotion is considered.
Receipt queue
The queue is a receipt path, not a claim of hidden live data.
Surprise signal
detectPrediction error, stale loop, or contradiction enters as a candidate unknown.
Missing variable
explainKELLY names the hidden variable or cause that could reduce forecast error.
Source plan
planThe hypothesis is tied to observations, tests, and closure criteria.
Memory candidate
gateOnly replayable closed hypotheses can become memory mutation candidates.
Lineage and closure timeline
Surprise
observedSomething changed more than expected.
Unknown
writtenThe gap becomes a ledger object.
Hypothesis
formedKELLY proposes a falsifiable causal bridge.
Test
plannedSource plan, falsifier, and reality check are declared.
Closure
pendingConfirm, weaken, kill, defer, or promote.
Cognitive topology
Prediction miss
Forecast or model error that creates surprise.
Unknown
Missing variable, cause, source, or context.
Hypothesis
Falsifiable answer candidate.
Experiment
Observation plan that can change the answer.
Memory candidate
Only after closure and replay.
Viewport empty-state contract
No active unknown selected
If the unknown ledger has no current item, the lab should say what it is watching and keep source-plan links visible instead of showing fake hypotheses.
Open unknown ledgerLive inputs
Active objects
Receipts
Closure status
Automation loop
Continuously refreshes from surprise, blind-spot, unknown-ledger, and causal-gap signals.
step 1
Detect surprise or forecast miss from live reality and evidence spine.
step 2
Ingest self-inquiry answer seeds (assumptions, claims, falsifiers) — answers are not truth.
step 3
Write the unknown as a ledger object with value-of-information scoring.
step 4
Generate a causal bridge, falsifier, source plan, and closure target.
step 5
Send closed or weakened hypotheses to memory lineage and GraphState promotion review.
Glass Lab source
These are the full proof windows this lab samples into the one-page view.
Storage posture
Postgres
Use canonical KELLY Neon/Postgres with hypothesis-scoped tables/read models for unknown_ledger, hypotheses, source_plans, experiment_tests, and closure_receipts.
Object store
Use R2/object storage only for evidence packets, test bundles, and immutable closure receipts linked from Postgres.
Volume
No dedicated persistent volume required. Runtime state should be reconstructable from canonical receipts.
Runtime routes
Lab functions stay simple on this page; deeper receipts open in the exact runtime or Glass Lab window.