QGI demonstrations / LQBENCH-QGI/0.7

Move from a benchmark design to evidence-producing execution.

Public QGI R4 defines how a quantitative-intelligence demonstration should be registered before execution, evaluated across declared domains and held-out regimes, and published with inspectable evidence rather than a marketing score.

Evidence publication Registry JSON

Reference demonstration tracks

Different quantitative worlds. One declared intelligence architecture.

DT-01

Human systems / HumanTwin

state estimation, predictive simulation, uncertainty and evidence across measurable human-system variables

reference-track-no-public-result

DT-02

Mission & engineering / Stratomission

dynamics, simulation, constrained optimisation, control and reproducible engineering evidence

reference-track-no-public-result

DT-03

Stochastic & financial systems

forecasting, risk, optimisation, regime shift and calibrated uncertainty

reference-track-no-public-result

DT-04

Scientific discovery systems

multifidelity modelling, candidate search, experiment selection, reproducibility and scientific memory

reference-track-no-public-result

These are reference demonstration tracks, not reported benchmark results. R4 does not claim that any track has been completed or passed.

Demonstration discipline

Register first. Execute second. Publish everything material.

Register the demonstration objective, domain, task families, held-out regimes, metrics, baselines and resource budget before execution.

Use the same declared intelligence architecture across the demonstration; domain-specific tools may vary only when the task contract permits them.

Publish successful, failed, infeasible, contradictory, timed-out and challenged runs rather than curating only favorable outcomes.

Bind every public result to exact task, system, environment, dataset, model, solver, simulator and evidence hashes.

Keep benchmark methodology separate from evidence, and evidence separate from any future QGI level or certification claim.

Treat cross-domain transfer as evidence only when the held-out regime and domain separation were declared before results were observed.

Demonstration manifest

The public record begins before the result exists.

A demonstration manifest binds the system version, objective, domain, task families, held-out regimes, baselines, tools, resource budget, uncertainty and evidence requirements before execution.

demonstration_iddemonstration_versiontitlesystem_idsystem_versiondomaintask_family_idsheld_out_regimesobjectiveconstraintsinput_lineagebaseline_idsallowed_toolsresource_budgetpre_registered_metricsuncertainty_requirementevidence_requirementevaluation_manifest_idstatus

DEMONSTRATION BOUNDARY

No public QGI demonstration result is fabricated by R4.

public_demonstrations, published_results and certifications remain empty until real evaluations are executed and evidence is available.

A demonstration is useful only if someone else can inspect how the result was produced.

Read the evidence protocol