Skip to content

Author

MARCELO ROLDAO MATOS

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#graph neural networks Open access Sep 2026

memoria.ia: Resolutive Memory — v1.0.0 Release Candidate 5

Memoria.ia v1.0.0-rc5 — Native Relational Memory Candidate Release date: 2026-09-06 Summary v1.0.0-rc5 freezes the post-RC4 native relational-memory work for OFF.IA, server and mobile validation. Functional freeze commit: 06c747478e05ee11ab2c5c3c24cf75365262b872 No new runtime features are to be added to the RC5 line after this freeze. Changes after the freeze are restricted to release metadata, documentation, packaging and regression fixes required to publish the candidate coherently. Main additions since RC4 deterministic native concept identity and canonicalization; persisted relation-to-concept graph adaptation; bounded multi-hop concept relation traversal; relational inference activated only after direct resolution fails; deterministic natural-language extraction for explicit X↔Y relation questions; bounded one-hop relation neighborhood queries; deterministic confidence ordering with preserved evidence IDs; directional type collection for questions such as Quais gatos você conhece?; explicit separation between membership edges and taxonomy/attribute edges; namespace isolation and fail-closed ambiguity handling across relational modes; no LLM, embedding model, neural network or fuzzy matching required for these paths. Resolver precedence The frozen native resolver precedence is: direct/base HIT; explicit or inferred X↔Y relation inference; directional type collection; bounded one-hop neighborhood; UNRESOLVED. Concrete regression boundary The release regression includes a collection case in which: Alt é um gato; Luna é um gato; gato é um animal. The query Quais gatos você conhece? returns Alt and Luna while excluding animal, preserving evidence IDs and namespace isolation. Validation status The functional freeze passed the five recurring release-blocking gates: v0.96 semantic validation; product-alpha validation; product application credentials; Android mobile ABI; layered performance baseline. Architectural boundary Memoria.ia remains local-first and deterministic at the memory/inference layer. LLMs remain optional consumers and are not the authoritative memory store. application / OFF.IA / agent ↓ Memoria.ia ↓ Resolutive-DB / BDR Known RC5 boundaries external/public learning on the mobile ABI remains outside this candidate; collection-query language remains deliberately narrow and fail-closed; neighborhood exploration is bounded to one hop in this candidate; relational inference is bounded and conservative rather than general-purpose reasoning; no independent production-security certification is claimed; MA2A federation remains outside the stable local runtime boundary. Publication lineage Previous public release: v1.0.0-rc4 — layered adaptive memory candidate. Archived prior candidate DOI retained for lineage: v1.0.0-rc2 — DOI: 10.5281/zenodo.22244038. A new RC5 DOI must be inserted only after the archival record exists; no DOI is pre-assigned in this preparation commit. Claims boundary Memoria.ia remains an experimental Resolutive Memory architecture. This release does not claim AGI, unrestricted general reasoning, biological equivalence, production-security certification or replacement of general-purpose LLMs. Claims remain limited to the implementation, tests and reproducible evidence contained in the repository.

MARCELO ROLDAO MATOS · 0 citations
#artificial intelligence Open access Aug 2026

memoria.ia: Resolutive Memory — v1.0.0 Release Candidate 1

Memoria.ia v1.0.0-rc1 — Release Candidate 1 Release date: 2026-08-30 Summary v1.0.0-rc1 is the first publication candidate for the Memoria.ia v1 line. It consolidates the validated Resolutive Memory research lineage with the deployable PC/server product layer and the native/mobile runtime path, while keeping post-v1 experimentation isolated from the release candidate. The release architecture remains: application / OFF.IA / agent ↓ Memoria.ia ↓ Resolutive-DB / BDR Memoria.ia owns memory semantics and state. Resolutive-DB owns durable persistence. Optional LLMs are consumers, not the authoritative memory store. Included capabilities persistent local-first memory state; organization and namespace isolation; provenance and authority lineage; conservative HIT / MISS / UNRESOLVED resolution; semantic, episodic, temporal and relation kernels; correction/supersession behavior with preserved lineage; PC/server FastAPI product boundary; Docker/Compose deployment; provider-neutral language-model adapters; metrics and context-selection instrumentation; integrity-checked backup/restore; native production runtime; Android arm64-v8a mobile ABI; durable native BDR persistence and restart recovery; indexed native resolution for large-memory workloads; reproducibility and release metadata gates; official Memoria.ia visual identity assets. Frozen candidate provenance The functional candidate was frozen at: dc73cbcdddfe20e0729e7e6bdea4697f7e8308cd That commit integrated PR #112, which preserved ranking, confidence, provenance policy, ABI and BDR contracts while adding the indexed native resolve lineage. The release branch adds publication metadata, version alignment, release documentation and current branding without importing post-v1 PR #116 runtime behavior. Validation evidence The exact functional lineage used for this release candidate passed the recorded required gates before release preparation: Android mobile ABI: PASS; native production image: PASS; Ubuntu/Windows candidate regression: PASS; BDR Linux/Ubuntu/Windows integration: PASS; native 100 / 1k / 10k benchmark matrix: PASS. Recorded 10k native resolve benchmark improvement versus the prior frozen baseline: p50: 693.233 ms -> 6.288 ms (~110x); p95: 710.630 ms -> 6.391 ms (~111x). These figures are environment- and workload-specific benchmark evidence, not universal latency guarantees. Publication metadata Release version: 1.0.0-rc1 Python package version: 1.0.0rc1 License: Resolutive Research and Non-Commercial License (RRNCL) v1.0 Author: Marcelo Roldão Matos ORCID: 0009-0003-6075-4680 RSMS compatibility: 1.0-rc.1 A new archival DOI should be assigned to this publication. The v0.95 DOI must not be reused as the release DOI for v1.0.0-rc1. Why this is RC1 rather than final v1.0 The repository currently declares compatibility with RSMS 1.0-rc.1, and the published Resolutive Science baseline remains on that release-candidate specification. Therefore Memoria.ia is published as v1.0.0-rc1 rather than claiming final v1.0 compatibility prematurely. Final v1.0 promotion requires: successful release-candidate metadata and regression gates; reproducibility from the public release state; compatibility re-audit against stable RSMS; no release-blocking regression found during RC use; final archival metadata and DOI synchronization. Explicitly excluded from RC1 The following post-v1 work is not part of this release candidate: external/public knowledge learning from OFF.IA Curiosity (issue #114 / PR #116); autonomous curiosity policy; new MA2A federation transport; multimodal post-v1 expansion; new semantic-consolidation phases from the post-v1 roadmap. Those features continue independently after this publication. Security boundary This release candidate is not represented as independently production-security certified. Authentication, isolation, integrity and negative-path controls exist and are tested, but no independent production security audit is claimed. Claims boundary This release does not claim: artificial general intelligence; biological equivalence; replacement of general-purpose LLMs; universal O(1) semantic resolution; production-ready MA2A federation; security certification. Claims are limited to the implementation, tests, benchmarks and reproducible evidence recorded in the repository.

MARCELO ROLDAO MATOS · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.