What research does SaSame publish?
Published papers, DOI records, experiments, methodology, measurements, datasets and whitepapers.
- Collection
- research
- Updated
- 2026-08-13
- min read
- 4
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.
- Observed
- 2026-07-23 00:00 UTC
- Claim strength
- illustrative
- Dataset scope
- One published research artifact — the Registry-Runtime Gap study, DOI
10.5281/zenodo.21513720, v1.0.0. A second draft ("Hidden Tool Layer") exists only as an unintegrated internal branch and is not usable as current fact. - Methodology
- Every published SaSame paper discloses its author's conflict of interest (SaSame's own Observatory produced the underlying observations), its public/private data boundary, and an explicit correction-status field rather than presenting a fixed number as final.
- Limitations
- This overview does not itself carry new measurements; see Research Datasets, Research Measurements and Registry-Runtime Gap for the scoped figures.
Illustrative — describes a method or schema, not a specific measured result
In this collection
4Published papers
DOI-linked publications retain correction and reproducibility status. The only current publication is the Registry-Runtime Gap study (DOI 10.5281/zenodo.21513720, v1.0.0, published 2026-07-23), which measured 31,407 discovered MCP endpoint records over a 35-day window and remains in an open partial-reproduction state rather than a closed one.
Methodology
Research pages link to measurement definitions, dataset boundaries, evidence lineage and limitations.
From research to evidence
A published paper states a method and a result at a point in time; Evidence is where the same underlying observations are kept queryable and current. The mcp-readiness CLI is the open-source tool that produces the readiness grades the paper and the Observatory both draw on — its methodology is not a black box.
Research as variation generator
Inside the institution model, Research is the place where intentional thinking is generated. It strengthens existing ideas, challenges them, explains anomalies, creates novel hypotheses, recombines past findings and introduces bounded randomness so SaSame does not collapse into local optimum.
CP2 executable Research and Simulation loop
The CP2 projection proves Research as an executable variation and simulation layer: six structurally distinct candidates span exploit, challenge, anomaly, recombination, novelty and adversarial falsification modes; model-risk gates hold underdetermined explanations; material unknowns stay explicit; two simulation fidelities reduce the population before Mission Control; and a green simulation is never promoted to scientific truth, market demand, payment or North-Star credit.
Examples
3- 01
The Registry-Runtime Gap paper links to runtime evidence and architecture documentation.
- 02
The paper's conflict-of-interest disclosure states plainly that SaSame S.R.L. is the author and that SaSame's own Observatory produced the observations — the publication explicitly serves public understanding and SaSame's own evidence station, and is not an independent third-party audit.
- 03
Candidate R-CP2-006 survives as an adversarial challenger while R-CP2-002 is held as underdetermined, proving that Research preserves falsification and diversity rather than optimizing one noisy score.