Current company, Factory, documentation, research, evidence, product and API records are searched by default. Historical records are available only when you explicitly include them.
How does SaSame improve its own evolution method?
SaSame evolves by converting both successful execution and operational residue into knowledge: CP5 makes cleanup, dependency hygiene and test drift part of the same inherited learning loop.
What is the registry-runtime gap in MCP?
Registry presence and declared metadata do not guarantee that an MCP endpoint is reachable, interoperable or behaving as described at observation time.
What research does SaSame publish?
SaSame Research now has an executable CP2 loop: it generates structurally diverse hypotheses, runs adversarial falsification and epistemic-state gates, simulates candidates at multiple fidelities, and emits only bounded Mission candidates before reality exposure.
What must a SaSame research dataset disclose?
A dataset discloses provenance, collection window, identity keys, fields, exclusions, license and privacy boundaries.
How should MCP measurements be interpreted?
Measurements are bounded results tied to an instrument, target identity, time and denominator; they are not timeless ratings.
How does SaSame define reproducible MCP research?
Research records population, observation window, identity assumptions, instruments, exclusions, transformations, retained evidence and known mismatches.