KELLY sector cognition OS
Unknown forge
See how KELLY creates questions from data, what it wants to test, and what would make it change its mind.
KELLY does not just answer. It creates testable hypotheses, names the causal chain, finds falsifiers, watches reality, and preserves the proof trail.
Objects on the bench
Required receipts
Live KELLY routes
- Unknown ledgerhttps://www.causalea.com/api/discovery/unknown-ledger
- Discovery enginehttps://www.causalea.com/api/intellectual-kernel/discovery-engine
- Causal gap organhttps://www.causalea.com/api/intellectual-kernel/causal-gap-organ
Unknown forge
Hypothesis Lab
See how KELLY creates questions from data, what it wants to test, and what would make it change its mind.
KELLY does not just answer. It creates testable hypotheses, names the causal chain, finds falsifiers, watches reality, and preserves the proof trail.
24-hour hypothesis closure
Which fresh hypothesis can be checked against reality fastest?
Causal bridge discovery
Which two systems appear linked, and what hidden loop could connect them?
Recursive theory refinement
Which theory has mutated the most under evidence while remaining replayable?
This window shows what KELLY is doing in Hypothesis Lab: what it is reading, what it thinks might matter, what proof exists, and what is still waiting.
Read the answer in this lab first. Open the proof shelf or JSON packet for the evidence behind it. Check the route status and last-checked timestamp before trusting freshness. Look for the mind-changer: the fact that would make KELLY revise the answer. If evidence is waiting, treat the output as a question or watch item, not a settled answer.
Live evidence appears only when KELLY exposes proof-linked sector output. Empty states are intentional waiting states, not filler.
New approved evidence, a falsifier, settlement, replay drift, calibration movement, or memory-lineage revision.
This lab communicates with KELLY as an inspection window. It cannot write ground truth, memory, GraphState, provider state, or reality receipts.
Processing flow
Unknowns become test plans
Hypothesis evidence
Unknowns, hypotheses, source plans, and closure targets
Checking KELLY proof surfaces
This lab renders live proof-linked items when KELLY exposes matching sector evidence.
Sources
Discovery inputs
- KELLY observation ledger
- approved public data feeds
- contradiction queue
- forecast deltas
- settlement and replay receipts
Proof standard
How users can tell
- Every hypothesis needs a falsifier.
- Old data can become new evidence under a new causal question.
- User questions can guide research intent without writing ground truth.
- Reality, not confidence, closes the loop.
Outputs
Discovery outputs
- unknown_ledger_entries
- active_hypotheses
- value_of_information_scores
- source_plans
- test_closure_receipts
Storage posture
Postgres: central KELLY spine
Use canonical KELLY Neon/Postgres for unknown_ledger, hypotheses, source_plans, experiment_tests, and closure_receipts.
Object storage
Immutable evidence shelf
Use R2/object storage for evidence bundles, source-plan packets, test traces, and immutable closure receipts.
Volume
No ground-truth volume
No dedicated persistent volume required. Runtime state must be reconstructable from canonical receipts.
Objects on the bench
Primary objects
- unknown_ledger_entry
- missing_variable
- causal_bridge
- source_plan
Required receipts
Black-box recorder
- voi_score
- experiment_receipt
- closure_receipt
- memory_mutation_candidate
Authority
Write boundary
- KELLY is the only write authority for durable learning.
- Labs are read-only processors and inspection windows.
- Glass Lab remains the traceable evidence console.