KELLY live pulserefreshed agolearninglifetime heartbeat 0browser pulses warmingcells 0replay-ready 0engine checkinglatest cell watchingevidence checkinglive memory laneloop: checking live activity
activity feed
Interactive lens

Science and Research Lab · Answered directly by KELLY · public writes blocked

interactive cognition lens · answered by KELLY

Science and Research Lab

KELLY's evidence, citation, contradiction, replication, and falsification organ.

Turns external research into source-bound evidence packets, contradiction pressure, falsifiers, and research receipts that other KELLY organs can inspect.

real timeGlass Lab sourcedread-only window
Real-time cognition window

Samples Glass Lab, Advanced Processing Evidence Spine, and the lab-specific runtime routes every 15 seconds.

Glass Lab sourceReceiptspublic writes blocked

Glass panels

0/2

Snapshot

0/?

Routes

linked

Refresh

15s

Glass Lab source panels
prime research queuepending
advanced processing evidence spinepending
Runtime route checks

This lab uses anchored Glass Lab proof routes only.

Latest snapshot: pending. Evidence spine: pending. The lab can surface evidence and source plans. It does not let public users write KELLY memory or GraphState.

Science & Research Workbench

Evidence digestion lens — support/contradiction only, not ground truth.

read_onlymulti_replica_ready=falseprocess_is_not_truth
queue
0
open claims
0
stale
0
latest receipt
none
  • • Contradiction radar is inspect-only until durable evidence rows attach.
  • • Demo/fallback packets must stay labeled — never treated as live neon.
  • • Public users cannot write prime memory from this surface.
  • • Gauges follow GET event-bus status (process-local Map), not multi-replica truth.
  • • Claims list 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.
  • • Claim→hypothesis links are test-plan edges only; contradiction radar is inspect-only — not settlement.
  • • Claim strength is a scoped inspect lens — not settlement grade or receipt.

Event bus status

GET onlymulti_replica=falseprocess_local_map

Loading event-bus status…

Map stores status

GET onlymulti_replica=falseprocess_local_map

Loading map-stores status…

Organs glass chain

GET onlymulti_replica=falseladder=n/a

Loading organs chain…

process_is_not_truth · never uses terminal “blocked” · Glass mission control only

APES organ rollups

GET onlymulti_replica=falseorgans=n/a

Loading organ rollups…

instrument rollups · labeled_unproven · never demo-as-live · process_is_not_truth

Glass Lab visibility

GET onlymulti_replica=falsepanels=n/a

Loading visibility pack…

four panels · inspect-only · never terminal “blocked” · process_is_not_truth

Cognition Organs V1

GET onlymulti_replica=falsen/a%

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

GET onlyauto_deploy=falseobserved=0

Loading operator ladder…

never auto-deploy · process_is_not_truth · missing_evidence not “blocked”

Program status

GET onlymulti_replica=false

Loading program status…

process_is_not_truth · never terminal “blocked” · public lens only

Organ honesty summary

GET onlymulti_replica=falseprocess_is_not_truth
  • 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 Science/Research: gauges, receipt queue, closure timeline, topology, and empty-state behavior. Live route health remains in the real-time panel above.

operator grade

Claim map

support / contradict

Every research answer separates supporting evidence, contradiction pressure, and missing replication.

Citation state

source-bound

Papers, APIs, and research packets must carry source metadata before they can influence a claim.

Severe test

falsifier-first

The lab should ask what would weaken the claim before treating support as useful.

Handoff

to hypothesis

Closed or contested evidence becomes a hypothesis input, not a hidden truth write.

Receipt queue

The queue is a receipt path, not a claim of hidden live data.

traceable

Lineage and closure timeline

1

Claim

captured

State the research claim and boundary.

2

Source

indexed

Attach DOI, API, citation, or provider metadata.

3

Conflict

searched

Look for contradiction and replication posture.

4

Falsifier

planned

Name the evidence that would weaken the claim.

5

Receipt

ready

Emit source-plan and severe-test receipts.

Cognitive topology

Claim

Plain claim with scope and uncertainty.

Sources

Citation and provider evidence lanes.

Contradictions

Conflicting evidence and replication limits.

Falsifier

Severe test that can weaken the claim.

Hypothesis

Downstream question or source plan.

Viewport empty-state contract

No research packet selected

If live research panels are empty, this lab must show a waiting state and route the operator to source intake rather than inventing support.

Open research queue

Live inputs

Approved papers, citation metadata, source freshness, and contradiction searches.
Claims generated by Ask KELLY, Hypothesis Lab, and external research queues.
Scientific seal and empirical seal status from the runtime proof spine.

Active objects

Evidence packets
Contradiction cards
Falsifier candidates
Replication posture
Research closure plans

Receipts

DOI/arXiv/Crossref source receipts
Prime research queue receipts
Scientific seal receipts
Evidence-spine source-plan receipts

Closure status

A research object closes only when support, contradiction, source plan, and severe-test posture are visible.
Closed evidence can feed hypotheses; weak evidence stays labeled as candidate support.

Automation loop

Runs as a continuous research triage organ from Glass Lab and standalone lab runtime snapshots.

cognition pipeline

step 1

Collect source metadata from approved research lanes.

step 2

Separate support, contradiction, replication posture, and uncertainty.

step 3

Emit falsifier candidates and severe-test receipts.

step 4

Hand eligible evidence packets to Hypothesis Lab and Glass Lab evidence spine.

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 science-scoped read models for research_sources, evidence_packets, citation_edges, contradiction_cards, and severe_test_receipts.

Object store

Use R2/object storage prefixes for paper snapshots, parsed artifacts, citation bundles, and immutable evidence receipts.

Volume

Optional app-local cache volume only for parser/model scratch files. It must never be the source of truth.

Runtime routes

Lab functions stay simple on this page; deeper receipts open in the exact runtime or Glass Lab window.

operator links