TAG ARCHIVE
nlp
2 MARIA OS blog articles tagged nlp, organized as a Bonginkan topic archive for search engines and LLM retrieval.
Judgment OS / Decision Intelligence OS
Core MARIA OS research on turning organizational judgment into executable decision systems.
Agentic Company Architecture
Research on human-agent organizations, delegation boundaries, role topology, and governed autonomy.
Responsibility Gates and AI Governance
Safety, accountability, fail-closed gates, auditability, and human-in-the-loop control for AI agents.
Evidence, RAG, and Knowledge Governance
Evidence bundles, retrieval architecture, Graph RAG, knowledge trust, and auditable reasoning pipelines.
Agentic R&D and Judgment Science
Research operations, simulation labs, judgment science, recursive improvement, and experimental AI governance.
Evidence-Linked Meeting Minutes: Structured Extraction with Mandatory Citation Chains
Every decision must cite its source — how MARIA Meeting AI eliminates hallucinated minutes through segment-level evidence linking
Traditional meeting minutes suffer from a fundamental trust problem: the reader cannot verify whether a recorded decision actually occurred in the meeting or was interpolated by the note-taker. MARIA Meeting AI solves this by enforcing mandatory evidence linking — every decision, action item, and summary section must reference specific transcript segments as evidence. This paper formalizes the evidence-linking constraint, presents the incremental summarization algorithm that generates minutes every 15 seconds during live meetings, and proves that the citation coverage metric converges to completeness as transcript length increases. In evaluated Japanese business meetings, the system achieved 94% citation coverage with zero hallucinated decisions.
Contract Risk Vectorization: Transforming Legal Clauses into Computable Risk Vectors
Converting contract provisions into multi-dimensional risk representations and extracting negatively correlated clause clusters for automated risk assessment
Enterprise contract review is still heavily manual in many organizations. We present a mathematical framework that transforms legal clauses into dense risk vectors `r_i in R^d`, builds inter-clause correlation matrices, and extracts negatively correlated clause clusters associated with adversarial or misaligned provisions. The quantitative examples in this post should be read as internal review-simulation signals for triage support, not as a replacement for legal judgment or as universal due-diligence performance claims.