L2ET Research Instruments
Browse the domain map, open a category, or scroll through every protected research instrument. Outputs are preliminary research aids, not certification or professional advice.
Choose a research domain
Select a unique domain, open any individual instrument directly from its category card, jump to the section below, or open the dedicated category page.
127 research instruments across the L2ET research domain map.
AI governance, evidence readiness, release gates and assurance-review tools.
Mission, spacecraft, flight-systems, autonomy and certification evidence tools.
Agentic workflow, RAG, prompt-injection, permission-boundary and release-gate instruments.
Observation planning, cosmology sensitivity, exoplanet triage and astrophysical inference tools.
Threat hunting, telemetry coverage, evidence provenance, incident response and DFIR readiness.
Architecture controls, digital-trust evidence, operational resilience and source-quality instruments.
Theory stress tests, falsification mapping, dimensional checks and scale-separation tools.
Clinical-AI evidence, validation gates, dataset checks, human factors and safety-hazard instruments.
Research-guide, source-register and signal-triage tools for evidence monitoring.
Post-quantum readiness, crypto exposure, CBOM, HNDL planning and migration evidence tools.
Quantum states, circuits, resources, measurement, QFT scale and quantum-information workbenches.
Autonomy readiness, robotics safety cases, HRI, ODD scenarios and control-stability tools.
Reproducibility, formal methods, scientific-AI validation, formulas and benchmark-readiness tools.
Standards mapping, crosswalk generation and control-reference alignment tools.
5 instruments.
Checks whether an AI initiative has enough controls, evidence and ownership to proceed toward production.
Maps an AI use case to the governance evidence required before approval, release or expansion.
Walks through intended use, autonomy, affected persons and context to produce a preliminary AI system classification packet.
Measures eight AI assurance dimensions and produces a maturity radar with evidence gaps and next artifacts.
Converts AI assurance claims into a Claim to Evidence to Control to Test to Owner review pipeline.
13 instruments.
Checks whether autonomous decision logic in aerospace or UAV contexts has evidence for operating envelope, sensor dependency, override and verification.
Builds a phase-specific mission-risk envelope with hazards, margins, validation evidence and abort conditions.
Scores early mission risk across TRL, margins, verification, communications, thermal and fault-management evidence.
Scores model credibility evidence: verification, validation, uncertainty, sensitivity and benchmark replay.
Maps hazards, assurance evidence, verification and operational limitations into a certification-oriented crosswalk.
Plans autonomy evidence for envelope definition, monitoring, simulation, real-world tests and human override.
Creates an FMEA row set with severity, occurrence, detectability, mitigation and verification notes.
Calculates Reynolds, Mach and Knudsen indicators to classify continuum, compressibility and flow-regime pressure.
Extends received-power scouting with bandwidth, noise temperature, required Eb/N0 and link margin.
Computes first-pass circular orbit velocity, period, escape speed and Hohmann transfer estimates.
Computes ideal delta-v from specific impulse and mass fractions using the Tsiolkovsky rocket equation.
Maps latency, bandwidth, link interruption, autonomy fallback and data criticality into a communications constraint profile.
Estimates free-space path loss and received-power pressure for a simplified spacecraft link.
9 instruments.
Creates an allow/deny permission-boundary architecture for tool-using AI systems.
Builds separated risk, readiness and confidence safety-case artifacts for tool-using AI agents.
Builds a swimlane control map for user, agent, policy, memory, retrieval, tools, human approval, audit and rollback.
Generates buyer or vendor assurance questions for model APIs, copilots, RAG platforms and agentic workflow vendors.
Defines executable evaluation tasks, datasets, scorers, logs and JSON export contract for frontier/agentic systems.
Produces a go/no-go release memo for models, RAG systems, copilots and agentic features.
Classifies suspicious instruction patterns in test text and maps them to defensive containment recommendations.
Plans adversarial prompt/RAG test cases, scorers, logs and replay artifacts.
Maps contamination paths from source material through retrieval into model output and downstream action.
10 instruments.
Screens observation feasibility using target altitude proxy, sky/instrument constraints and S/N target.
Builds an observation-planning matrix from target, band, window, instrument constraints and signal-to-noise needs.
Converts astrophysical distance, redshift, luminosity, mass and time scales into order-of-magnitude notes.
Maps inference risks from selection effects, calibration, priors, confounders and model assumptions.
Builds a sensitivity table showing how selected cosmological parameters influence an observable under stated uncertainty ranges.
Separates detection strength from false-positive pressure: periodicity, noise, stellar activity, blends and follow-up.
Classifies exoplanet detection signal plausibility from method, periodicity, noise, stellar activity and follow-up evidence.
Computes flat-Lambda-CDM distance, age-lookback orientation and local sensitivity to H0 and Omega_m.
Creates a reproducibility dossier for scientific AI with data, code, environment, benchmark and uncertainty evidence.
Builds an astrophysics survey systematics register for selection functions, calibration, covariance and photo-z/outlier risks.
13 instruments.
Maps hunt hypothesis, ATT&CK tactic/technique, telemetry, baseline and falsification evidence.
Maps a disruption scenario to controls, telemetry, recovery evidence and test cadence.
Maps telemetry coverage across identity, endpoint, cloud, network, email, application and data layers.
Maps where an AI system changes cyber dependencies, identities, data flows and incident-response paths.
Builds an evidence source matrix and investigation sequence for a selected incident scenario.
Creates an evidence provenance and chain-of-custody checklist for incident artifacts.
Plans tabletop, telemetry replay, evidence acquisition and recovery benchmark tests.
Checks whether incident timestamps, evidence sources and time-zone assumptions are internally consistent.
Normalizes incident timestamps and flags impossible or undocumented timeline orderings.
Estimates likely blast-radius pressure from identity scope, lateral movement potential, data reach and dependency concentration.
Prioritizes review of a known-exploited vulnerability using user-entered exposure, asset criticality and compensating controls.
Manual connector-style triage for CVE exposure using KEV, EPSS, CVSS, asset criticality and patchability evidence.
Turns a defensive suspicion into a hunt hypothesis with telemetry, expected observations and falsification criteria.
8 instruments.
Converts release-gate evidence into machine-checkable CI status conditions.
Tracks dated sources, evidence objects, owners, review cadence and staleness for AI governance outputs.
Turns a system trust claim into evidence, controls, owners, audit trail and monitoring requirements.
Maps capabilities, applications, data flows, owners, dependencies and controls into an architecture control map.
Creates a scenario plan for a critical service, disruption, dependencies, recovery objectives and test history.
Separates source trust, novelty, uncertainty and actionability into distinct evidence axes.
Maps recommendations to dated sources, controls, artifacts, owners and evidence objects.
Crawls static routes, sitemap, redirects, headers and Worker dependencies for release integrity.
9 instruments.
Checks whether a proposed physical relation has matching dimensions and suggests where exponents are inconsistent.
Classifies a bold scientific claim by mechanism clarity, evidence type, falsifiability and competing explanations.
Builds falsification benchmarks for frontier physics claims with observables, thresholds, confounders and null tests.
Defines golden cases, dimensional checks and edge-case regression tests for physics/quantum calculators.
Identifies relevant physical scale regimes and approximations for a cross-scale research problem.
Computes how a quantity changes under a scale factor and exponent uncertainty.
Extends dimensional analysis beyond M/L/T toward SI-base exponent vectors and Buckingham-Pi readiness.
Produces falsification, null-test, observable, threshold and confounder artifacts for scientific theory claims.
Creates a falsification matrix linking a frontier-physics hypothesis to observables, thresholds, confounders and next tests.
8 instruments.
Maps false-data injection, model, data, identity and monitoring hazards for AI/ML medical systems.
Plans calibration, threshold, subgroup, drift and harm-sensitivity checks for clinical AI.
Builds a structured intended-use, validation, safety and lifecycle evidence dossier for clinical AI.
Maps clinical AI intended use, validation evidence, subgroup performance and workflow controls into a gap report.
Structures evaluation of clinical LLM/VLM outputs, hallucination, citation, safety and user workflow evidence.
Assesses dataset provenance, representativeness, reference standards, adjudication and leakage controls.
Checks whether a biomedical prediction model has reproducible code, data, environment and reporting artifacts.
Builds a prospective workflow, user, override and human-factors evaluation plan.
3 instruments.
Routes visitors to relevant L2ET research tracks, tools, frameworks and artifacts based on role and intent.
Classifies a paper, advisory, standard or update by source quality, novelty, uncertainty, actionability and L2ET domain fit.
Creates a source-register card with domain, source type, update cadence, reliability, actionability and monitoring purpose.
18 instruments.
Builds a manual cryptographic bill of materials draft with algorithms, operations, owners, evidence and migration candidates.
Maps user-entered assets, algorithms, protocols and data lifetimes into a quantum-vulnerable dependency inventory.
Validates manual CBOM completeness and emits machine-readable crypto inventory fields.
Estimates harvest-now-decrypt-later urgency from confidentiality lifetime, capture feasibility and migration lead time.
Computes HNDL pressure from data shelf life, migration lead time, capture likelihood and public-key exposure.
Plans protocol interop, downgrade, fallback, performance and certificate-chain tests for hybrid/PQC migration.
Classifies quantum-safe readiness stage and identifies the first evidence actions for post-quantum transition.
Creates PQC-related contract language themes and evidence topics for legal and procurement review.
Checks implementation evidence for algorithm, parameter set, KATs, side-channel notes, hybrid behavior and rollback.
Produces a maturity-band view of quantum-safe readiness with an unknown-evidence penalty and confidence level.
Creates a phased post-quantum migration roadmap from inventory, supplier, protocol and governance inputs.
Separates TLS session capability, negotiated evidence, certificate-chain readiness and observation gaps.
Compares vendor evidence for crypto inventory, algorithm agility, hybrid support, testing and contractual commitments.
Scores protocol migration pressure from exposure, difficulty, business criticality and data lifetime.
Distinguishes PQC migration, QKD infrastructure assessment and specialized hybrid scenarios.
Classifies algorithms by classical/PQC family, standardization status, operation and migration implication.
Normalizes supplier PQC evidence into inventory, roadmap, testing, contractual and monitoring fields.
Generates supplier questions and evidence requests for post-quantum readiness and crypto-agility.
7 instruments.
Scaffolds density-matrix validity, trace, positivity, noise-channel and measurement checks.
Converts energy, length and time scales in natural-unit style and checks order-of-magnitude consistency.
Estimates logical and physical resource pressure from qubits, depth, T-count and error-rate assumptions.
Computes normalization and a concurrence-style indicator for two-qubit pure states.
Computes measurement probabilities and deterministic expected counts for a chosen basis and trial count.
Checks whether a quantum-resource estimate includes architecture, QEC, error budget, T-count/factories and physical assumptions.
Normalizes a single-qubit state and computes measurement probabilities, Bloch coordinates and density matrix notes.
11 instruments.
Checks whether an autonomous mission has enough navigation, communication-loss, telemetry and abort-condition evidence.
Screens collaborative robot separation/contact risk using speed, stopping time, separation and contact severity inputs.
Estimates second-order overshoot and settling behavior from damping ratio and natural frequency assumptions.
Creates a checklist for operator proximity, collaboration mode, emergency stop and feedback channels.
Builds a perception failure-mode matrix from sensors, environment, occlusion, weather and decision dependency.
Creates a robotics autonomy hazard map from operating environment, sensing stack, actuator risk and fail-safe assumptions.
Generates operational design domain and scenario-regression coverage priorities.
Builds a robotics hazard, mitigation, verification and residual-risk safety-case scaffold.
Sketches runtime safety envelope, monitored state, barrier condition and fallback evidence for autonomous robots.
Checks whether sensor sources, confidence, time alignment and fallback logic support a reliable fusion claim.
Separates sensor-fusion complexity, calibration, time sync, uncertainty and fallback evidence.
10 instruments.
Maps a system to TLA+/Dafny/Lean/Rocq/SMT-style proof obligations and readiness gaps.
Assesses whether a system has enough state, invariants, interfaces and failure modes for formal specification work.
Creates golden cases, dimensional checks, domain constraints and tolerance tests for formula calculators.
Plans capability, safety, robustness and deployment evaluations for frontier or agentic AI systems.
Assesses Lean/mathlib formalization readiness: definitions, dependencies, theorem statement, examples and compile target.
Scores whether a study or model result has enough artifacts to be reproduced or independently checked.
Builds a validation protocol for scientific AI, simulations, imaging models or analytical workflows.
Generates scientific-AI validation protocols with baselines, leakage, ablations, uncertainty and external validity.
Builds golden regression fixtures for scientific calculators across formula, unit and edge-case checks.
Creates a reproducibility scorecard for datasets, code, environments, evaluation protocols and reporting completeness.
3 instruments.
Maps governance, security and assurance control themes across AI, cyber, resilience and supplier frameworks.
Provides a filterable matrix for mapping obligations, controls, evidence, owners and gaps across major standards.
Creates a stronger matrix across AI, cyber, resilience, PQC and evidence frameworks.