KESPA Research

Experiments, evidence,
and measurable progress.

KESPA is an active NexLabs Studios research platform exploring whether smaller local models can gain practical capability through verified knowledge, retrieval, memory, selective escalation, and adaptive research. This archive is the public record of what we test, what worked, and what still needs proof.

3 Verified research releases
11 Verified claims in releases
5 Evidence records in releases
37 Published archive entries
Research boundary

Published KESPA results are scoped to the configuration, hardware, datasets, and policies used in each experiment. Individual results do not establish broad superiority over frontier systems or universal cost savings.

Public research repository

Published archive

Selected experiments, benchmarks, technical notes, datasets, and project updates are versioned separately from the private KESPA application repository and synchronized into this public archive.

Technical note

Trusted Knowledge Freshness and Continuous Reverification Foundation

KESPA established the database foundation for freshness-aware Trusted Knowledge and documented a configurable continuous-reverification lifecycle. Freshness state now exists on trusted knowledge, a knowledge_refresh_jobs queue exists, and the existing supersession/versioning path can be reused; policy configuration, scheduling, evidence reacquisition, change detection, stale-on-retrieval behavior, Admin controls, and refresh telemetry remain planned at this checkpoint.

trusted-knowledge freshness reverification supersession knowledge-lifecycle rag
Technical note

Public Research Archive and Immutable Revision Sync

KESPA established a public research repository and website bridge that publishes experiments, benchmarks, technical notes, datasets, and updates through a manifest-driven archive. The sync path resolves GitHub main to an immutable commit SHA before fetching the manifest and artifacts, eliminating stale branch-CDN reads and ensuring each sync uses one consistent repository revision.

research-archive provenance github immutable-revisions publication
Technical note

Fail-Closed Web Discovery and Evidence Qualification Pipeline

KESPA's autonomous research worker separates discovery from evidence, directly fetches candidate sources, rejects unsafe/off-topic/blocked material, requires independent organizations, and refuses high-stakes/private/volatile topics from durable autonomous learning. The validated Cuckoo-filter run accepted three independent sources while rejecting multiple unsuitable candidates and completed with four verified claims.

web-research evidence-quality fail-closed source-independence autonomous-research
Technical note

Signed Cross-Host Research Queue and Durable Handoff Architecture

KESPA split autonomous research across the application server and home research server using pull-based HTTPS, HMAC SHA-256 request authentication, nonce replay protection, durable filesystem queues, signed release handoff, and resumable delivery state. The design keeps the home server off the public inbound path while allowing queued research and completed releases to survive process restarts and host reboots.

distributed-systems research-queue hmac durability handoff
Technical note

Telemetry-Backed User Profiles, Community Scoring, and Privacy Controls

KESPA added complete authenticated profiles, historical usage analytics, milestones, a 182-day activity history, community leaderboards, KESPA Score v2, and opt-in public profiles using existing persisted telemetry rather than a second analytics pipeline. The design keeps prompts, answers, private memories, request diagnostics, and user/community statistics out of NexLedger.

telemetry user-profiles leaderboard privacy community-analytics
Technical note

Autonomous Natural Research Gap Lifecycle

KESPA operationalized a natural knowledge-gap research path that detects low-confidence public-knowledge gaps during normal use, queues isolated research jobs, gathers multi-source evidence, verifies claims, imports approved releases, promotes trusted knowledge, indexes it locally, and records provenance through NexLedger without modifying the legacy/manual lifecycle.

autonomous-research knowledge-gap trusted-knowledge groq nexledger
Experiment

Autonomous Knowledge Gap Acquisition

KESPA detected a live knowledge gap during normal use, researched the missing concept from multiple independent public sources, verified four claims, promoted the result to trusted knowledge, indexed it for retrieval, and recorded provenance through NexLedger.

adaptive-learning knowledge-gap evidence-verification trusted-knowledge nexledger
Technical note

Trusted Knowledge Indexing Boundary and Private-Data Exclusion

KESPA introduced an authenticated trusted-knowledge indexing path that allows promoted public knowledge to enter the live Chroma retrieval index while blocking internal/private plaintext indexing. MySQL trusted_knowledge remains authoritative and Chroma remains a rebuildable search index; the first promoted trusted record was confirmed live, increasing the clean production index from 423 to 424 cards.

trusted-knowledge indexing privacy chroma security-boundary
Technical note

Trusted Research Release Promotion Pipeline

KESPA validated a research-release path that turns audited evidence and verified claims into a gated trusted-knowledge release, imports it as a research candidate, promotes it to trusted knowledge, indexes it for live Brain retrieval, and records the result through NexLedger. A systemd release completed the full path without modifying the existing NexLedger worker.

research-release trusted-knowledge evidence-verification nexledger provenance
Technical note

Automated Research Evidence Capture and NexLedger Attestation

KESPA operationalized an hourly cross-host evidence pipeline that reads closed telemetry from the RTX 3070 Brain machine, aggregates it on the research/home server, submits safe MET evidence through a signed intake, records the event in MySQL, and lets the generic worker attest it to NexLedger. The same automation watches future completed benchmark runs for BM evidence.

telemetry evidence-automation nexledger provenance benchmarks
Technical note

Autonomous Trusted Knowledge Lifecycle Operationalization

KESPA operationalized an end-to-end trusted-knowledge lifecycle for manually trained public knowledge: synthesis, candidate creation, evidence collection, local verification, policy-gated approval, trusted-knowledge promotion, and live local indexing. Autonomous publication was separated from human approval through explicit system-policy audit metadata.

autonomous-learning trusted-knowledge verification policy-gating production-architecture
Experiment

Autonomous Trust Policy v0.1 to v0.2 Backlog Reclassification

KESPA relaxed one auto-publication condition from two supporting evidence items to one while retaining verification, confidence, consensus, and zero-conflict requirements. Applying the policy change to the existing backlog made 29 previously held candidates eligible without rerunning evidence collection or local verification, raising projected backlog autonomy from 36.7% to approximately 95.9%.

autonomous-learning trust-policy auto-publish human-review policy-tuning
Technical note

Clean Verified Knowledge Production Baseline

KESPA replaced the legacy ~441k-card production retrieval corpus with the clean 423-claim verified baseline, preserved memory collections separately, validated known-claim retrieval at rank #1, and established trusted_knowledge as the authoritative knowledge store with Chroma as a rebuildable search index.

production-cutover verified-knowledge chroma retrieval architecture
Technical note

Public-Only External Intelligence Refinery and Budgeted Cloud Analysis

KESPA introduced an optional external-intelligence refinery that sends only explicitly classified public_external/public_benchmark tasks to Groq, retains all provider output as non-authoritative candidate analysis, enforces daily request/token budgets and rate-limit backoff, and persists queue/results/provenance locally. A desktop validation completed four Groq 120B analyses and exposed the provider's 8K TPM limit; the worker was then made rate-aware. A later Windows-service wrapper was prepared for the always-on home server but had not yet received a user-environment SCM validation at the recorded checkpoint.

external-intelligence groq privacy-boundary rate-limits retrieval-diagnostics budget-control
Research update

KESPA V2 Research Program: Verified Intelligence and Adaptive Compute

KESPA V2 formalized the research direction emerging from the completed A/B/C benchmark: verified externalized intelligence and fast trusted retrieval as the default path, adaptive orchestration only when justified, explicit separation of evidence/knowledge/memory, continuous knowledge growth, and compute-efficiency as a first-class research objective.

research-program master-plan-v2 verified-intelligence adaptive-compute nsf
Benchmark

Adaptive Inference D v001: Preregistered Efficiency Benchmark

KESPA D v001 tested adaptive inference on the frozen 54-case workload. It achieved a composite quality score of 55.2586 at 2.443 s mean latency and 0.153616 Wh mean energy, but failed the preregistered primary success criterion because retrieval Hit@1, gold recall, and escalation-rate thresholds were not met.

adaptive-inference benchmark preregistered compute-efficiency negative-result
Technical note

Always-On Orchestration Overhead in the Locked A/B/C Runtime Run

The locked 54-case A/B/C runtime run showed that the then-current full KESPA orchestration path was materially more expensive than both the raw local model and the verified-retrieval fast path. Arm C averaged 9.066 s and 0.5759 Wh, executed 65 LLM passes, searched RAG on all 54 cases but used it on only 28, invoked planner/reviewer selectively, and avoided inference on zero cases. This runtime profile helped motivate V2 adaptive compute rather than always-on orchestration.

orchestration compute-efficiency latency energy adaptive-inference
Technical note

Blinded Quality Judging and Offline Gold-Metadata Repair

KESPA preserved a completed 162-row A/B/C benchmark after discovering that all raw rows had empty gold_claim_ids. The evaluator repaired gold associations offline from locked reference_claim_ids without modifying raw results, verified frozen corpus/evaluation hashes, and used blinded one-answer judge inputs containing no arm labels, runtime metrics, or system identity.

benchmark-integrity blinded-judging metadata-repair evaluation reproducibility
Technical note

Frozen Benchmark Construction and Evaluation Leakage Prevention

KESPA built a 66-question benchmark from the 423-claim verified corpus, separating 12 calibration questions from 54 locked evaluation questions. Evaluation hashes were frozen before retrieval-policy tuning, and calibration tooling verified the locked evaluation hash without parsing its contents.

benchmark-design evaluation-freeze data-leakage reproducibility verified-corpus
Technical note

Frozen Evidence Identity: Canonical URL Plus SHA-256

KESPA corrected its scale claim/evidence verifier so frozen evidence is identified by canonical URL plus SHA-256 rather than URL alone. The change addressed 17 authoritative URLs that legitimately mapped to multiple frozen excerpts, 16 of which were referenced by generated candidates, while preserving strict contamination controls.

evidence-verification provenance sha256 integrity claim-verifier
Technical note

Chroma Corpus Compatibility and Retrieval Equivalence

KESPA validated that the isolated 423-claim clean corpus could be reproduced in a Brain-compatible Chroma layout without changing IDs, documents, metadata, or observed retrieval ordering. All 423 records matched structurally, 32/32 top-1/top-10 retrieval checks matched, and only float-scale embedding round-trip differences were observed.

chroma retrieval compatibility deterministic-validation verified-knowledge
Technical note

Compute-Aware Model Routing and Telemetry Foundation

KESPA validated its local model registry, routing infrastructure, persistent telemetry, metrics endpoint, RTX 3070 instrumentation, and Admin controls on the actual KESPA machine. A subsequent routing-policy correction separated technical-learning requests from coding requests while preserving local-first execution.

model-routing telemetry compute-efficiency local-ai instrumentation
Benchmark

Atomic Knowledge Retrieval Policy Calibration

A locked 12-question calibration showed that legacy long-card retrieval filters were poorly matched to short verified atomic claims. Plain vector top-6 achieved 12/12 Hit@1 and 67/87 claim recall, while legacy minimum-length filtering produced severe retrieval loss; the final policy freeze selected plain_vector_top6.

retrieval calibration atomic-claims vector-search policy-freeze
Experiment

Claim-Level Verification and Clean Corpus Consolidation

KESPA consolidated strict claim-level verifier survivors from a 100-card diagnostic subset into a clean 423-claim corpus. The experiment recorded a 48.0% strict claim survival rate and rescued 331 independently supportable claims from cards that would have been discarded under whole-card acceptance.

claim-verification knowledge-quality corpus-consolidation atomic-claims provenance
Benchmark

A/B/C Verified-Intelligence Quality and Compute Benchmark

A frozen 54-question, 162-execution benchmark compared a raw local 7B path, clean verified atomic retrieval, and the then-current KESPA orchestration. The verified-retrieval arm achieved the highest reported composite quality score (54.22), 54/54 retrieval Hit@1, 79.17% gold recall, and the lowest mean latency and GPU energy of the three arms.

benchmark verified-rag compute-efficiency retrieval blinded-evaluation
Experiment

Full Seed-Ready Evidence Scale Run

KESPA executed the seeded evidence-acquisition path across 3,128 planned evidence slots representing 2,831 cards. It collected and audited 2,146 evidence excerpts; 1,555 of 2,831 cards passed the evidence gate, while 463 evidence rows required review for missing scope-term matches. The run was deliberately held before card generation.

knowledge-factory scale-study evidence-acquisition quality-gates failure-analysis
Technical note

Deterministic Evidence Acquisition Preflight and Bounded Smoke Harness

KESPA converted the validated 3,982-card knowledge blueprint into a 4,807-slot evidence-acquisition workload with explicit primary/supporting/cross-check roles, a conservative 60-family source-policy catalog, an offline evidence-quality auditor, invariant validation, and a deterministic 28-slot/24-topic smoke harness. Local preflight checks passed with zero network/provider calls; the recorded checkpoint explicitly notes that the Windows live smoke had not yet been executed.

evidence-acquisition deterministic-smoke preflight source-policy knowledge-factory
Experiment

Cross-Model Claim Verification and Human-Review Gating Pilot

Four recorded pilot verifier runs evaluated 21 candidate-card executions with a different model family from the generator. The verifier produced 19 card passes, one evidence-support failure, and one structural execution failure while rechecking frozen evidence hashes and candidate identity. Seven high-stakes/safety cards still required human review despite model-level support, demonstrating that model agreement did not bypass policy or trust gates.

claim-verification cross-model human-review high-stakes fail-closed knowledge-factory
Experiment

Groq Evidence-Bound Generation Canary and Fail-Closed Verification

A four-blueprint cross-domain Groq canary generated four evidence-bound knowledge candidates with zero generation failures for $0.003482 in reported provider cost, while assigning no trust and making no Chroma writes. Downstream verification then demonstrated the intended fail-closed boundary: a PostgreSQL candidate passed claim support verification, a calculus candidate failed on a partially supported claim, and a diabetes candidate surfaced a structural missing-claim-number execution failure.

knowledge-factory groq evidence-bound-generation claim-verification fail-closed canary
Benchmark

Clean Pilot Retrieval Gate and Contamination-Metric Correction

A 30-card clean candidate corpus achieved 93.3% exact-card retrieval at rank 1 and 100% expected-topic retrieval at rank 1. The first benchmark run incorrectly treated legitimate cross-topic top-5 retrieval as hard contamination and produced a NO-GO; benchmark v002 separated hard contamination from cross-topic retrieval, after which the recorded public checkpoint reported 0/150 hard synthetic flags and a GO scale gate.

retrieval clean-pilot contamination metric-correction knowledge-factory
Technical note

Evidence-Bound Candidate Generation and Provider Rate-Limit Resilience

KESPA's clean pilot generator bound model output to frozen evidence, atomic claim-to-source mappings, retrieval-focused text, contamination guards, and deferred trust. Subsequent provider-pacing changes added rate-header-aware throttling, Retry-After handling, token accounting, and a regression fix for an 8,041-token estimate against an 8,000-TPM limit.

knowledge-factory evidence-bound-generation rate-limits provider-resilience provenance
Technical note

Evidence-Bound Knowledge Factory Pilot Design

KESPA's first clean Knowledge Factory pilot defined a 15-topic, 30-card evidence-bound generation contract with authoritative-source policies, independent organization checks for high-stakes topics, evidence hashing, atomic claim-to-source mappings, contamination guards, and deferred trust assignment.

knowledge-factory evidence-bound-generation provenance high-stakes pilot-design
Technical note

Knowledge Blueprint v004: Deterministic Bootstrap Planning

KESPA Blueprint v004 converted a repaired 729-topic recovered taxonomy plus 37 approved foundational additions into 759 canonical generating topics, 3,982 unique planned card scopes, and 4,807 evidence-source slots. Windows user-environment validation later confirmed the deterministic rebuild matched the expected artifacts byte-for-byte.

knowledge-factory blueprint taxonomy deterministic-planning safety-gates
Experiment

Seeded Evidence Scale: Scope-Precision Correction

A fixed 120-card, 142-slot evidence batch was rerun after a bounded seed-precision correction. Card-level evidence-gate passage improved from 62/120 (51.7%) to 82/120 (68.3%), while hard no-scope-term-match issues fell from 24 to 1 without changing the canonical blueprint, collector architecture, or source trust registry.

knowledge-factory evidence-acquisition scope-precision controlled-rerun retrieval-quality
Experiment

Evidence Discovery: From Search Dependency to Source-First Discovery

Three bounded discovery iterations showed that general web search was not reliable enough to be a required evidence locator in the tested Windows KESPA runtime. A source-first design using catalog hints, first-party entrypoints, robots.txt, sitemaps, and same-host navigation produced candidates for 26 of 28 smoke slots without Google or DuckDuckGo.

knowledge-factory evidence-discovery source-first failure-analysis authoritative-sources
Technical note

Source-Organization Independence and High-Stakes Evidence Policy

KESPA hardened its pilot evidence policy by moving independence from hostname counting to source-organization counting, adding explicit source_organization provenance, strengthening high-stakes cross-check requirements, replacing weak/failed seeds with authoritative sources, and preserving evidence-excerpt, hashing, redirect, and SSRF safety rails. Syntax and offline cross-check policy tests passed; no LLM, Chroma, or Brain changes were involved.

evidence-policy source-independence high-stakes provenance knowledge-factory
Technical note

Legacy Corpus Recovery and Clean Rebuild Boundary

KESPA recovered 729 original subject areas from the legacy synthetic corpus, resolved all 121 ambiguous taxonomy classifications, split the recovered scope into 484 TECH_REVIEW and 245 REBUILD_FROM_SOURCE topics, preserved the ~442k-card synthetic corpus as immutable archive material, and explicitly rejected those synthetic cards for clean production indexing.

corpus-recovery taxonomy contamination-control clean-rebuild knowledge-factory
KESPA Research Repository Last synchronized 2026-09-17T08:09:14+00:00
Open public repository ↗
Verified research lifecycle

Research releases

These entries come directly from completed KESPA research-release manifests already received by the production research lifecycle. They are operational research records, not automatically public repo releases.

Verified release

Key Facts About Life Purpose

What is your purpose?

1 claims 2 evidence 2 organizations
forge-release-bf03200aaaba424029d46688
Verified release

Key facts about cuckoo filters

What is a Cuckoo filter?

4 claims 2 evidence 2 organizations
forge-release-07990ffc7fc9d09f9be2dd3b
Verified release

systemd overview

What is systemd?

6 claims 1 evidence 1 organizations
forge-release-b668d809f8b517bb46cdb92b
Active research tracks

What KESPA is testing now

01

Adaptive knowledge acquisition

Can KESPA identify a real knowledge gap during normal use, gather evidence, verify claims, and improve future retrieval without retraining its base model?

02

Capability per unit of compute

How much practical capability can system architecture add to a constrained local model before larger inference hardware becomes necessary?

03

Retrieval and solved-work reuse

Can verified knowledge and repeated-work reuse reduce unnecessary inference while preserving or improving answer quality?

04

Trust and evidence policy

Which verification, provenance, source-independence, and release gates meaningfully reduce weak or unsupported permanent knowledge?

05

Provider and model routing

When should KESPA use local inference, stronger hosted models, external research, or no escalation at all?

06

Private memory and user context

How can persistent user context improve usefulness while remaining clearly separated from public factual knowledge?