AI Research Laboratory3 records
Programs
Long-running research lines that group research, theory, experiments, papers and systems.
- ProgramPRG-2026-0201AI Agent Publication Boundary and Security Closure (APBSC)What do AI coding agents carry from a private workspace into public repositories, and how can that be measured without anyone reading other people's leaks? Phase I (ten papers, 2026-09-21) built the vocabulary — the five-state information chain, the green-light fallacy, agent context as an egress surface, recoverability, warning levels — and RBPM, a researcher-blind algorithm whose only observer of repository content is a sealed machine process. Phase II (2026-10) ran it on fresh public samples of companies, organizations and individuals and found agent-related publication-boundary signals in every population. The study stops there by decision: going further would mean reading what people did not mean to publish. Algorithm, protocols, released features and reports are open source.
- ProgramPRG-2026-0001Adaptive Epistemic SystemsA research program that derives an AI runtime from first principles — world knowledge changes at heterogeneous rates, natural language is a rendering rather than the canonical state, capability must be remembered and reused, algorithm and compute substrate are separate — and then forces the derivation into executable reality: the AER-0 reference runtime with six architecture-comparison rounds, and the PACC micro-lab on whether non-probabilistic primitives converge to probability-like structure.
- ProgramPRG-2026-0101Intelligence Physical Metrology (IPM)A research program that asks not how smart an AI is but what one answer costs a physical system: how many user turns, generation trajectories and hidden loops it took, how much effective semantic work was done, how much energy and computational spacetime was occupied, how much external scaffolding was leaned on, and how much verifiable quality came back. Ten theoretical papers (2026-09-02) define the measurement objects — task, quality, semantic work, physical computation, scaffolding capability, measurement metadata — and five falsifiable propositions; the v0.2 experimental protocol (Experiment A, single-pass vs scaffolded) is instantiated as the XA-02…XA-06L instrument packages and was executed once on a local 9B model.