LEGALIR / Infrastructure

The graph grounds the law.

Indian law is a network of authority, jurisdiction and time.

Sign in to learn more ↗
The permissioned thin filmInstitutional records remain in a lower plane. A thin policy boundary lets only permitted retrieval units reach approved agents above. Restricted information stays below.APPROVED AGENTSSCOPED RETRIEVAL ↑POLICY BOUNDARYPRIVATE RECORDSFIG. 03 / PREPARE ONCE. RETRIEVE UNDER AUTHORITY.
PROPOSED INFRASTRUCTURE / IN DEVELOPMENT
01

Nodes with legal identity

The proposed ontology includes constitutional provisions, Acts, sections, rules, notifications, judgments, courts, benches, legal propositions and amendments. A node is identified by its source and version; similar text does not establish that two authorities are interchangeable.

02

Edges that make a claim

Cites, interprets, applies, distinguishes, overrules, modifies, repeals and derives-authority-from are different legal relationships. Each edge needs an exact supporting passage, a verification state, effective dates and the reviewer or extraction process that produced it. A similarity score must never be presented as a precedent relationship.

03

Time belongs in the query

Recorded time and legal effective time must be stored separately. Research about a past transaction should resolve the provision in force at that date. Later treatment of a judgment remains visible, with ambiguity and unresolved conflicts flagged rather than silently collapsed.

04

Hybrid retrieval

Exact citation and full-text search locate identifiers and wording. Semantic retrieval finds conceptual matches. Graph traversal follows authority and treatment. Metadata narrows court, jurisdiction, document type and period. Ranking must preserve the distinction between relevance and binding authority.

Your knowledge remains yours.

Enter the reading room ↗