docs: simplify custom.css to a static, professional style

Remove decorative hover animations (code block/card lift+glow, table
row highlighting, list item highlighting, animated nav underline,
button lift+glow) and the page-load fade-in transition. Keep the
color/typography branding, accessibility focus rings, and scrollbar
styling.

docs/concepts.md

@@ -8,16 +8,16 @@ icon: "book-open"
   New here? Start with [Getting Started](/getting-started) for hands-on examples, then return here for deeper understanding.
 </Info>
 
-Semantica transforms unstructured data (documents, web pages, reports, databases) into **knowledge graphs**: structured representations that AI systems can query, reason about, and trace back to sources.
+Semantica transforms unstructured data: documents, web pages, reports, databases: into **knowledge graphs**: structured representations that AI systems can query, reason about, and trace back to sources.
 
-At its core, Semantica adds a context and semantic layer on top of your existing AI stack. It doesn't replace LangChain, LlamaIndex, or your LLM provider. It makes their outputs grounded, traceable, and auditable.
+At its core, Semantica adds a **context and accountability layer** on top of your existing AI stack. It doesn't replace LangChain, LlamaIndex, or your LLM provider: it makes their outputs **grounded**, **traceable**, and **auditable**.
 
-- **Context Layer.** Knowledge graphs, GraphRAG retrieval, semantic embeddings, and temporal intelligence ground every LLM response in structured, queryable facts.
-- **Accountability Layer.** Provenance tracking, decision intelligence, conflict detection, and W3C PROV-O compliance make every claim in your AI stack auditable and explainable.
-- **Extension Layer.** `PluginRegistry` and `MethodRegistry` let you replace or augment any component (ingestors, extractors, reasoning engines, backends) without changing framework code.
+- **Context Layer** — Knowledge graphs, GraphRAG retrieval, semantic embeddings, and temporal intelligence ground every LLM response in structured, queryable facts.
+- **Accountability Layer** — Provenance tracking, decision intelligence, conflict detection, and W3C PROV-O compliance make every claim in your AI stack auditable and explainable.
+- **Extension Layer** — `PluginRegistry` and `MethodRegistry` let you replace or augment any component: ingestors, extractors, reasoning engines, backends: without changing framework code.
 
 <Warning>
-  **This is system-level explainability, not foundation-model explainability.** Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model. Its internal reasoning or chain-of-thought stays opaque, as it does for any external system. What Semantica explains is *outside* the model: the context and data fed in, the decision produced, its provenance, the relevant relationships, the policies applied, and the full execution trail. In short, Semantica explains and audits *what the AI system did*, not the foundation model's private internal reasoning.
+  **This is system-level explainability, not foundation-model explainability.** Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model — its internal reasoning or chain-of-thought stays opaque, as it does for any external system. What Semantica explains is *outside* the model: the context and data fed in, the decision produced, its provenance, the relevant relationships, the policies applied, and the full execution trail. In short, Semantica explains and audits *what the AI system did*, not the foundation model's private internal reasoning.
 </Warning>
 
 ## Knowledge Graphs
@@ -30,7 +30,7 @@ The foundation of everything in Semantica. A knowledge graph stores information
 - **Edges (relationships)**: `works_for`, `located_in`, `founded_by`
 - **Properties**: name, date, confidence score, source URL
 
-This structure makes knowledge searchable, connectable, and queryable. Critically, it's explainable: every answer can be traced back to the facts and relationships that produced it.
+This structure makes knowledge **searchable**, **connectable**, **queryable**, and: critically: **explainable**: every answer can be traced back to the facts and relationships that produced it.
 
 
 ## Entity Extraction (NER)
@@ -513,6 +513,6 @@ Semantica is designed for extension. Any component: ingestor, extractor, graph b
   </Accordion>
 </AccordionGroup>
 
-- [Quickstart Tutorial](/quickstart): build a full pipeline with code.
-- [Modules Guide](/modules): every module explained with examples.
-- [API Reference](/reference/context): complete technical reference.
+- [Quickstart Tutorial](/quickstart) — Build a full pipeline with code.
+- [Modules Guide](/modules) — Every module explained with examples.
+- [API Reference](/reference/context) — Complete technical reference.

docs/docs.json

@@ -2,7 +2,7 @@
   "$schema": "https://mintlify.com/docs.json",
   "theme": "mint",
   "name": "Semantica",
-  "description": "The Context and Semantic Layer for AI in High-Stakes Domains — Context Graphs · Decision Intelligence · Full Provenance",
+  "description": "The Accountability and Context Layer for AI — Context Graphs · Decision Intelligence · Full Provenance",
   "colors": {
     "primary": "#10B981",
     "light": "#10B981",
@@ -43,7 +43,7 @@
     "raiseIssue": true
   },
   "metadata": {
-    "og:title": "Semantica — Context & Semantic Layer for AI in High-Stakes Domains",
+    "og:title": "Semantica — Accountability & Context Layer for AI",
     "og:description": "Build explainable, auditable knowledge graphs with full provenance. Open source. MIT licensed.",
     "og:image": "/assets/img/semantica-logo.png",
     "twitter:card": "summary_large_image",
@@ -121,23 +121,6 @@
             "pages": [
               "vector_stores/pgvector"
             ]
-          },
-          {
-            "group": "FAQ",
-            "pages": [
-              "faq"
-            ]
-          },
-          {
-            "group": "Community",
-            "pages": [
-              "community",
-              "community-projects",
-              "contributing-guide",
-              "governance",
-              "citation",
-              "project-license"
-            ]
           }
         ]
       },
@@ -184,17 +167,7 @@
               "guides/policy-engine",
               "guides/visualization",
               "guides/distance-intelligence",
-              "guides/graph-analytics"
-            ]
-          }
-        ]
-      },
-      {
-        "tab": "API Reference",
-        "groups": [
-          {
-            "group": "Context & Intelligence",
-            "pages": [
+              "guides/graph-analytics",
               "reference/context",
               "reference/kg",
               "reference/temporal",
@@ -263,6 +236,32 @@
             ]
           }
         ]
+      },
+      {
+        "tab": "FAQ",
+        "groups": [
+          {
+            "group": "FAQ",
+            "pages": [
+              "faq"
+            ]
+          },
+          {
+            "group": "Community",
+            "pages": [
+              "community",
+              "community-projects",
+              "contributing-guide",
+              "governance",
+              "citation",
+              "project-license"
+            ]
+          }
+        ]
+      },
+      {
+        "tab": "Changelog",
+        "href": "https://github.com/semantica-agi/semantica/releases"
       }
     ]
   },

docs/guides/graphrag.md

@@ -1,9 +1,9 @@
 ---
-title: "GraphRAG: Graph-Augmented Retrieval"
+title: "GraphRAG — Graph-Augmented Retrieval"
 description: "Go beyond vector search: retrieve facts, trace reasoning paths, and ground LLM responses in your knowledge graph."
 ---
 
-GraphRAG combines vector similarity with knowledge graph traversal so retrieval finds structurally connected facts, not just text that sounds related. When a `ContextGraph` is attached to `AgentContext`, every retrieval call automatically blends semantic search with multi-hop graph expansion, and `query_with_reasoning()` returns an auditable reasoning path alongside the LLM answer.
+GraphRAG combines vector similarity with knowledge graph traversal so retrieval finds structurally connected facts, not just text that sounds related. When a `ContextGraph` is attached to `AgentContext`, every retrieval call automatically blends semantic search with multi-hop graph expansion — and `query_with_reasoning()` returns an auditable reasoning path alongside the LLM answer.
 
 ## What Is GraphRAG?
 
@@ -11,7 +11,7 @@ GraphRAG (Graph-Augmented Retrieval-Augmented Generation) enhances traditional R
 
 **GraphRAG vs. traditional vector-only RAG:** Vector RAG finds documents similar to your query text. GraphRAG finds documents similar to your query AND documents connected to those through entity relationships, even if they don't mention your query terms directly.
 
-**The role of graph traversal:** Starting from entities found in vector-similar documents, GraphRAG expands outward through relationship edges to discover related facts. This reveals connections that pure text similarity would miss, like finding that a threat actor targets healthcare by following the path: Actor → Tool → Victim Organization → Industry Sector.
+**The role of graph traversal:** Starting from entities found in vector-similar documents, GraphRAG expands outward through relationship edges to discover related facts. This reveals connections that pure text similarity would miss — like finding that a threat actor targets healthcare by following the path: Actor → Tool → Victim Organization → Industry Sector.
 
 ## Why Use GraphRAG?
 
@@ -96,7 +96,7 @@ context = AgentContext(
 )
 ```
 
-Now ingest your documents. `store()` with `extract_entities=True` runs the full extraction pipeline internally (Named Entity Recognition, relation extraction, and entity linking) and populates both the vector index and the graph simultaneously:
+Now ingest your documents. `store()` with `extract_entities=True` runs the full extraction pipeline internally — Named Entity Recognition (NER), relation extraction, and entity linking — and populates both the vector index and the graph simultaneously:
 
 ```python
 intel_documents = [
@@ -132,17 +132,16 @@ stats = context.store(
 print("Graph built: {} nodes, {} edges".format(
     stats["graph_nodes"], stats["graph_edges"]
 ))
+# Graph built: 18 nodes, 14 edges
+# Nodes: APT29, HAMMERTOSS, NATO, LifeCare, AS59796, CISA Sector 6, ...
+# Edges: deployed, observed_on, classified_as, targets, operates_in, ...
 ```
 
-`store()` returns a dict with `stored_count`, `memory_ids`, `graph_nodes`, and
-`graph_edges`. The extracted nodes (APT29, HAMMERTOSS, LifeCare, AS59796, …) and
-edges (`deployed`, `observed_on`, `classified_as`, …) now span all four documents.
-
-The graph now contains a connected subgraph linking APT29 to healthcare infrastructure across four document boundaries, something that would be invisible to a pure vector search.
+The graph now contains a connected subgraph linking APT29 to healthcare infrastructure across four document boundaries — something that would be invisible to a pure vector search.
 
 ## Retrieving the relevant subgraph
 
-With the graph populated, a plain `retrieve()` call already does more than vector search. When `use_graph=True`, the retriever seeds the graph traversal from the top-k vector matches and expands outward by following edges. Expansion depth is set once, by `max_expansion_hops` on the `AgentContext` constructor:
+With the graph populated, a plain `retrieve()` call already does more than vector search. When `use_graph=True`, the retriever seeds the graph traversal from the top-k vector matches and expands outward by following edges, collecting connected facts within `max_hops`:
 
 ```python
 results = context.retrieve(
@@ -150,6 +149,7 @@ results = context.retrieve(
     use_graph=True,
     max_results=10,
     expand_graph=True,
+    max_hops=3,
 )
 
 for r in results:
@@ -169,25 +169,17 @@ Notice the top results: while pure vector search might rank connected facts lowe
 When you know specifically which entity you want to anchor the traversal to, pass `anchor_node`:
 
 ```python
-# Anchor on APT29 explicitly: proximity scores are calculated from this node
+# Anchor on APT29 explicitly — proximity scores are calculated from this node
 apt29_intel = context.retrieve(
     "C2 infrastructure beaconing patterns",
     use_graph=True,
     anchor_node="APT29",
     proximity_weight=0.7,   # strongly favour nodes close to APT29
-    max_hops=3,             # with an anchor, this bounds the proximity radius
+    max_hops=3,
     max_results=8,
 )
 ```
 
-<Note>
-  `max_hops` on `retrieve()` only takes effect when `anchor_node` is set: it
-  bounds the proximity radius used for scoring and drops results farther than
-  `max_hops` from the anchor. Without an `anchor_node` it is ignored. It does
-  **not** change how far graph expansion reaches: that is fixed by
-  `max_expansion_hops` on the constructor.
-</Note>
-
 ## Getting a grounded LLM answer with a reasoning path
 
 `retrieve()` gives you the grounded context. `query_with_reasoning()` goes one step further: it passes that subgraph context to an LLM and returns the answer together with the multi-hop path the retrieval system traced through the graph. That path is your audit trail.
@@ -205,7 +197,7 @@ result = context.query_with_reasoning(
     max_hops=3,
 )
 
-# The LLM answer, grounded in graph-retrieved context, not training memory
+# The LLM answer — grounded in graph-retrieved context, not training memory
 print(result["response"])
 
 # The multi-hop trace: APT29 → deployed → HAMMERTOSS → observed_on → LifeCare → ...
@@ -221,7 +213,7 @@ for src in result["sources"]:
     print("  [{:.3f}] {}".format(src["score"], src["content"][:80]))
 ```
 
-The `reasoning_path` field is what separates GraphRAG from a black-box LLM call. When an analyst asks "how do you know APT29 targeted healthcare?", you can show them the exact traversal the system made across your own documents, not a claim the model generated from training data.
+The `reasoning_path` field is what separates GraphRAG from a black-box LLM call. When an analyst asks "how do you know APT29 targeted healthcare?", you can show them the exact traversal the system made across your own documents — not a claim the model generated from training data.
 
 The full return structure from `query_with_reasoning()`:
 
@@ -240,11 +232,11 @@ The full return structure from `query_with_reasoning()`:
 
 <Tabs>
 
-<Tab title="Defense: CTI/Threat">
+<Tab title="Defense — CTI/Threat">
 
 Multi-INT intelligence fusion: OSINT threat feeds, NVD CVE data, and HUMINT summaries ingested into a single graph, then queried with multi-hop reasoning to trace C2 infrastructure chains and attribute campaigns to specific actors.
 
-In classified environments the graph can be partitioned by data handling caveat: each `AgentContext` operates over the subset of documents cleared for the querying user. The `reasoning_path` output doubles as a sanitisable audit trail for downgraded reporting.
+In classified environments the graph can be partitioned by data handling caveat — each `AgentContext` operates over the subset of documents cleared for the querying user. The `reasoning_path` output doubles as a sanitisable audit trail for downgraded reporting.
 
 ```python
 from semantica.context import AgentContext, ContextGraph
@@ -308,11 +300,11 @@ proximate = context.retrieve(
 
 </Tab>
 
-<Tab title="Security: SOC/Incident">
+<Tab title="Security — SOC/Incident">
 
 Security operations: real-time alert triage against a graph containing hosts, CVEs, user accounts, runbooks, and historical incidents. GraphRAG retrieves the relevant runbook and similar past incidents in a single call, reducing mean-time-to-respond.
 
-The `decision_tracking=True` flag records every triage query as an auditable decision, with the full context that was provided to the LLM. That's essential for post-incident review and SOC metrics.
+The `decision_tracking=True` flag records every triage query as an auditable decision, with the full context that was provided to the LLM — essential for post-incident review and SOC metrics.
 
 ```python
 from semantica.context import AgentContext, ContextGraph
@@ -377,7 +369,7 @@ for inc in similar:
 
 </Tab>
 
-<Tab title="Life Science: Clinical/Pharma">
+<Tab title="Life Science — Clinical/Pharma">
 
 Clinical decision support: FDA drug labels, clinical guidelines, and trial summaries ingested into a graph where drug-enzyme-metabolite-interaction chains become traversable paths. A three-hop query (drug → enzyme → metabolite → contraindication) surfaces interaction risks that no single document would make explicit.
 
@@ -451,7 +443,7 @@ contra_chain = clinical_context.retrieve(
 
 </Tab>
 
-<Tab title="Banking: Risk/Compliance">
+<Tab title="Banking — Risk/Compliance">
 
 Regulatory compliance: Basel III (CRE20), BCBS 239, SR 11-7, and EBA IRRBB guidelines ingested as a graph where regulation articles cross-reference each other as edges. Multi-hop queries traverse those cross-references automatically, so a question about commercial real estate RWA pulls the relevant CRE20 paragraphs and the BCBS 239 data quality requirements that govern their calculation in a single call.
 
@@ -474,17 +466,12 @@ compliance_context = AgentContext(
     retention_days=2555,   # 7-year regulatory retention
 )
 
-# In production the text comes from a parsed file, e.g. FileIngestor().ingest_file(path).text;
-# inline strings here for brevity
-basel_cre20_text = (
-    "CRE20.32: For income-producing real estate where repayment depends on "
-    "property cash flows, RWA = exposure × risk weight, where risk weight "
-    "is determined by LTV bucket per Table CRE20.3..."
-)
-bcbs239_text = (
-    "Principle 3: Risk data should be accurate and have a single authoritative source. "
-    "Where data is aggregated across systems, reconciliation must be documented..."
-)
+# In production these come from ingest_file() — shown as strings here for brevity
+basel_cre20_text  = "CRE20.32: For income-producing real estate where repayment depends on "
+                    "property cash flows, RWA = exposure × risk weight, where risk weight "
+                    "is determined by LTV bucket per Table CRE20.3..."
+bcbs239_text      = "Principle 3: Risk data should be accurate and have a single authoritative source. "
+                    "Where data is aggregated across systems, reconciliation must be documented..."
 
 compliance_context.store(
     [
@@ -509,7 +496,7 @@ print(answer["response"])
 print("Regulatory sources cited: {}".format(answer["num_sources"]))
 print("Confidence: {:.1%}".format(answer["confidence"]))
 
-# The reasoning path is the audit log: show it to the regulator
+# The reasoning path is the audit log — show it to the regulator
 print("\n--- Reasoning Path (audit log) ---")
 print(answer["reasoning_path"])
 ```
@@ -537,18 +524,18 @@ The `hybrid_alpha` parameter set in the `AgentContext` constructor establishes a
 When targeting a specific `anchor_node`, you can apply `proximity_weight` in `retrieve()` to dynamically blend structural distance from the anchor into the final score:
 
 ```python
-# Anchor node provided: let vector semantics lead, graph proximity only slightly boosts
+# Anchor node provided — let vector semantics lead, graph proximity only slightly boosts
 results = context.retrieve(
     query, use_graph=True, anchor_node="APT29", proximity_weight=0.2
 )
 
-# Known-entity tracing: topology drives the retrieval
+# Known-entity tracing — topology drives the retrieval
 results = context.retrieve(
     query, use_graph=True, anchor_node="APT29", proximity_weight=0.8
 )
 ```
 
-Each additional expansion hop exponentially increases the subgraph size. Practical defaults by domain:
+Each additional hop in `max_hops` exponentially increases the subgraph size. Practical defaults by domain:
 
 ```text
 General Q&A             max_expansion_hops=2  (95% of useful facts within 2 hops)
@@ -557,7 +544,7 @@ Drug interactions       max_expansion_hops=3  (drug → enzyme → metabolite
 Regulatory cross-ref    max_expansion_hops=2  (rule → article → article)
 ```
 
-Expansion depth is a constructor setting only (`max_expansion_hops`); there is no per-call override on `retrieve()`. `query_with_reasoning()` does take a per-call `max_hops` argument.
+Set globally in the constructor; override per call with the `max_hops` argument to `retrieve()`.
 
 ## How GraphRAG works internally
 
@@ -589,9 +576,9 @@ The vector search and graph traversal run independently, then their scores are f
 
 ## Related Guides
 
-- [Semantic Extraction](/guides/semantic-extraction): build the graph from raw unstructured text
-- [Agent Memory](/guides/agent-memory): store, retrieve, and persist agent memories
-- [Context Graphs](/guides/context-graphs): build and traverse the knowledge graph directly
-- [Reasoning](/guides/reasoning): derive new facts and run inference rules over the graph
-- [Decision Intelligence](/guides/decision-intelligence): causal chains, policy enforcement, decision tracking
-- [LLM Integrations](/guides/llm-integrations): connect Groq, OpenAI, Anthropic, HuggingFace, and 100+ more
+- [Semantic Extraction](/guides/semantic-extraction) — build the graph from raw unstructured text
+- [Agent Memory](/guides/agent-memory) — store, retrieve, and persist agent memories
+- [Context Graphs](/guides/context-graphs) — build and traverse the knowledge graph directly
+- [Reasoning](reasoning) — derive new facts and run inference rules over the graph
+- [Decision Intelligence](/guides/decision-intelligence) — causal chains, policy enforcement, decision tracking
+- [LLM Integrations](/guides/llm-integrations) — connect Groq, OpenAI, Anthropic, HuggingFace, and 100+ more

docs/index.md

@@ -1,87 +1,97 @@
 ---
 title: "Semantica"
-description: "The Context and Semantic Layer for AI in High-Stakes Domains: Context Graphs · Decision Intelligence · Full Provenance"
+description: "The Accountability and Context Layer for AI: Context Graphs · Decision Intelligence · Full Provenance"
 ---
 
 ```bash
 pip install semantica
 ```
 
-Most AI agents store embeddings, not meaning. They can't say why a fact was recalled, where it came from, or what led to a decision. In healthcare, finance, legal, and government, that lack of a traceable record blocks production deployment.
+Your AI agent just made a decision. Now someone needs to explain it.
 
-Semantica is the context and semantic layer for AI in high-stakes domains, sitting beneath your existing agent framework. It doesn't replace LangChain or LlamaIndex; it makes their outputs traceable.
+*What did it know at the time? Which facts shaped the outcome? Where did those facts come from? Has it made the same call before: and did that go well?*
+
+If your stack can't answer those questions with a traceable record, you have a gap. Not a capability gap: an **accountability gap**. It's the reason AI hasn't landed at scale in healthcare, finance, legal, and government. And it's why teams building for those markets keep rebuilding the same guardrails from scratch.
+
+**Semantica closes that gap.** It's the context and accountability layer that sits beneath your existing agent framework: not a replacement for LangChain or LlamaIndex, but the infrastructure that makes their outputs trustworthy.
 
 
-## What Most AI Stacks Are Missing
+## The Problem Every Production AI Team Hits
 
-**No memory structure.** Agents store embeddings, not meaning.
+Powerful agents aren't automatically trustworthy ones. Five structural blind spots make modern AI systems impossible to deploy in regulated environments:
+
+**No memory structure** — agents store embeddings, not meaning
 - No way to ask *why* a fact was recalled
 - No link from a recalled fact back to its source document
 - Context is a black box that resets on every run
 
-**No decision trail.** Agents act continuously but record nothing.
+**No decision trail** — agents act continuously but record nothing
 - No history to hand to a regulator or auditor
 - No way to replay or reproduce a past decision
 - Debugging means re-running, not reviewing
 
-**No provenance.** Outputs can't be traced to source facts.
-- A hard compliance blocker in healthcare, finance, and legal
+**No provenance** — outputs can't be traced to source facts
+- In healthcare, finance, and legal: this is a hard compliance blocker
 - No lineage from inference back to the original document
-- No way to demonstrate what the agent actually relied on
+- Impossible to demonstrate what the agent actually relied on
 
-**No reasoning transparency.** Black-box answers with no explanation.
-- No way to validate the reasoning path
-- No way to contest a specific conclusion
+**No reasoning transparency** — black-box answers with no explanation
+- Impossible to validate the reasoning path
+- Impossible to contest a specific conclusion
 - No basis for improving or correcting future behavior
 
-**No conflict detection.** Contradictory facts silently coexist in vector stores.
+**No conflict detection** — contradictory facts silently coexist in vector stores
 - No detection when two sources disagree
 - Outputs become inconsistent and unpredictable over time
 - Silent failures compound as the knowledge base grows
 
+<Note>
+  These aren't edge cases. They're why enterprise AI pilots stall: and why your compliance team keeps saying *not yet*.
+</Note>
+
 
 ## What Semantica Adds to Your Stack
 
-Semantica gives every agent the infrastructure it needs to be accountable, and it drops into an existing setup in minutes.
+Semantica gives every agent the infrastructure it needs to be accountable. Drop it into your existing setup in minutes:
 
-**Context Graphs.** A structured, queryable graph of everything your agent knows, decides, and reasons about.
-- Persistent across agent runs, with no context loss between sessions
+**Context Graphs** — a structured, queryable graph of everything your agent knows, decides, and reasons about
+- Persistent across agent runs: no context loss between sessions
 - Queryable with SPARQL and full graph algorithms
 - Temporal model with `valid_from` / `valid_until` on nodes and edges
 - Point-in-time snapshots of the full knowledge state
 
-**Decision Intelligence.** Every decision is a first-class object in your system.
+**Decision Intelligence** — every decision is a first-class object in your system
 - `record_decision()` captures full lifecycle and causal chain
 - Hybrid precedent search over past decisions for consistency
 - `analyze_decision_impact()` shows downstream consequences
 - Causal chain visualization from trigger to outcome
 
-**Full Provenance.** Every fact links to its source document and ingestion event.
+**Full Provenance** — every fact links to its source document and ingestion event
 - W3C PROV-O compliant lineage across all modules
 - Full traceability from raw input to final inference
 - `recorded_at` stamping with OWL-Time export
 - Audit-ready for HIPAA, SOX, GDPR, FDA 21 CFR Part 11
 
-**Reasoning Engines.** Explainable reasoning paths, not black boxes.
+**Reasoning Engines** — explainable reasoning paths, not black boxes
 - Forward chaining, Rete, deductive, abductive
 - SPARQL query-based inference over RDF graphs
 - Datalog with recursive Horn clause rules
 - Every conclusion backed by a traceable derivation path
 
-**Temporal Intelligence.** Your graph knows not just *what*, but *when*.
-- Allen interval algebra covering all 13 temporal relations
+**Temporal Intelligence** — your graph knows not just *what*, but *when*
+- Allen interval algebra: all 13 temporal relations
 - Point-in-time queries over historical graph states
 - Temporal provenance stamping on every fact
 - OWL-Time export for standards-compliant archiving
 
-**Ontology Hub.** Full ontology lifecycle in the browser.
+**Ontology Hub** — full ontology lifecycle in the browser
 - Visual editor for schema design and editing
 - SHACL Studio for constraint authoring and validation
 - Alignment authoring across multiple ontologies
 - Health dashboard and version control built in
 
 <Tip>
-  Works alongside any LLM provider and any agent framework. Add it to an existing stack without changing your architecture.
+  Works alongside any LLM provider and any agent framework: add it to an existing stack without changing your architecture.
 </Tip>
 
 <img src="/assets/img/diagrams/architecture-overview.svg" alt="Semantica four-layer architecture: Ingestion → Processing → Intelligence → Application" style={{ width: '100%', borderRadius: '12px', margin: '24px 0' }} />
@@ -175,17 +185,17 @@ decision_id = context.record_decision(
 
 </CodeGroup>
 
-- [Full Quickstart](/quickstart): step-by-step pipeline walkthrough
-- [Cookbook](/cookbook): 40+ real-world Jupyter notebooks
-- [Join Discord](https://discord.gg/sV34vps5hH): community chat and support
+- [Full Quickstart](/quickstart) — Step-by-step pipeline walkthrough
+- [Cookbook](/cookbook) — 40+ real-world Jupyter notebooks
+- [Join Discord](https://discord.gg/sV34vps5hH) — Community chat and support
 
 
-## Industry Use Cases
+## Built for Where Mistakes Have Consequences
 
-Semantica is used in domains where every decision must be explainable and every fact must be traceable.
+Semantica was designed for domains where every decision must be explainable and every fact must be traceable.
 
 <Warning>
-  **This is system-level explainability, not foundation-model explainability.** Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model. Its internal reasoning or chain-of-thought stays opaque, as it does for any external system. What Semantica explains is *outside* the model: the context and data fed in, the decision produced, its provenance, the relevant relationships, the policies applied, and the full execution trail. See [Core Concepts](/concepts) for the full scope note.
+  **This is system-level explainability, not foundation-model explainability.** Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model — its internal reasoning or chain-of-thought stays opaque, as it does for any external system. What Semantica explains is *outside* the model: the context and data fed in, the decision produced, its provenance, the relevant relationships, the policies applied, and the full execution trail. See [Core Concepts](/concepts) for the full scope note.
 </Warning>
 
 **Healthcare & Life Sciences**
@@ -246,7 +256,7 @@ Semantica is used in domains where every decision must be explainable and every
     - Knowledge graphs vs. vector stores: when to use each
     - What GraphRAG is and how Semantica implements it
     - How provenance and decision tracking work together
-    - The context and semantic layer architecture
+    - The accountability layer architecture
   </Step>
   <Step title="Go deep on any module">
     Every module has a dedicated [reference page](/reference/context) with:
@@ -256,12 +266,12 @@ Semantica is used in domains where every decision must be explainable and every
   </Step>
 </Steps>
 
-- [Installation](/installation): get Semantica installed in under a minute
-- [Quickstart](/quickstart): build a complete knowledge graph pipeline in 5 minutes
-- [Core Concepts](/concepts): the mental model behind the API
-- [API Reference](/reference/context): exact module, class, and method details
-- [Cookbook](/cookbook): domain notebooks for real-world use cases
-- [Changelog](https://github.com/semantica-agi/semantica/releases): release history
+- [Installation](/installation) — Get Semantica installed in under a minute
+- [Quickstart](/quickstart) — Build a complete knowledge graph pipeline in 5 minutes
+- [Core Concepts](/concepts) — The mental model behind the API
+- [API Reference](/reference/context) — Exact module, class, and method details
+- [Cookbook](/cookbook) — Domain notebooks for real-world use cases
+- [Changelog](https://github.com/semantica-agi/semantica/releases) — Release history
 
 
 ## Full Capabilities
@@ -384,20 +394,20 @@ Semantica is used in domains where every decision must be explainable and every
 
 ## Why Semantica?
 
-**Open Source, MIT.** No vendor lock-in, no paywalled features.
+**Open Source, MIT** — No vendor lock-in. No paywalled features.
 - Full source available on GitHub
 - Every line auditable by your security team
 - Fork, extend, and self-host with no restrictions
 - No telemetry, no usage reporting
 
-**Production Ready.** Built for teams that can't afford surprises.
+**Production Ready** — Built for teams that can't afford surprises.
 - 1,000+ passing tests with full regression coverage
 - `PipelineValidator` catches configuration errors at startup
 - `FailureHandler` with exponential backoff and dead-letter queues
-- Ongoing security hardening, with fixes shipped in every release ([CHANGELOG](https://github.com/semantica-agi/semantica/blob/main/CHANGELOG.md))
+- Ongoing security hardening: fixes shipped in every release ([CHANGELOG](https://github.com/semantica-agi/semantica/blob/main/CHANGELOG.md))
 
-**Modular by Design.** Import only what you need.
+**Modular by Design** — Import only what you need.
 - Use `NERExtractor` without a graph store
 - Use `ContextGraph` without vector storage
 - Every component independently swappable and testable
-- No framework lock-in, and works with any agent stack
+- No framework lock-in: works with any agent stack

docs/reference/context.md

@@ -30,28 +30,28 @@ icon: "brain"
 
 ## What You Get
 
-- **AgentContext**: memory, decision tracking, and graph-backed retrieval behind one API
+- **AgentContext** — Memory, decision tracking, and graph-backed retrieval behind one API
   - Conversation history and checkpoint diffing
   - Persist and restore full context state to disk
-- **ContextGraph**: thread-safe in-memory knowledge graph
+- **ContextGraph** — Thread-safe in-memory knowledge graph
   - PageRank, centrality, community detection, temporal validity
   - Cross-graph navigation and link traversal
-- **AgentMemory**: embedding-backed memory with retention policy
+- **AgentMemory** — Embedding-backed memory with retention policy
   - LRU eviction at configurable `max_memory_size`
   - Per-conversation history isolation
-- **DecisionRecorder**: records decisions with causal chains and confidence scores
+- **DecisionRecorder** — Records decisions with causal chains and confidence scores
   - Temporal validity windows (`valid_from` / `valid_until`)
   - Cross-system context capture on every decision
-- **PolicyEngine**: versioned policy storage in the knowledge graph
+- **PolicyEngine** — Versioned policy storage in the knowledge graph
   - Compliance checking against recorded decisions
   - Policy exception tracking with approver audit trail
-- **EntityLinker**: maps entity text to stable URIs
+- **EntityLinker** — Maps entity text to stable URIs
   - Creates typed links between entity IDs
   - Prevents "Apple", "Apple Inc.", "AAPL" becoming separate nodes
-- **ContextRetriever**: fuses vector similarity, graph traversal, and agent memory
+- **ContextRetriever** — Fuses vector similarity, graph traversal, and agent memory
   - Richer context than pure vector search
   - Configurable `hybrid_alpha` and expansion hops
-- **CausalChainAnalyzer**: traces upstream causes and downstream effects of any decision
+- **CausalChainAnalyzer** — Traces upstream causes and downstream effects of any decision
   - Explainability paths with relationship types
   - Configurable depth and direction
 
@@ -273,7 +273,7 @@ icon: "brain"
 </Tip>
 
 <Tip>
-  **Persist your context between runs.** `VectorStore` does not auto-persist; passing `index_path=` to its constructor is a no-op. Call `context.save("agent_state/")` to write memory, the vector index, and the graph to disk, and `context.load("agent_state/")` on the next process to restore them. See the "Persist & Restore" tab under [Real-World Patterns](#real-world-patterns) below.
+  **Persist your context between runs.** `VectorStore` does not auto-persist — passing `index_path=` to its constructor is a no-op. Call `context.save("agent_state/")` to write memory, the vector index, and the graph to disk, and `context.load("agent_state/")` on the next process to restore them. See the "Persist & Restore" tab under [Real-World Patterns](#real-world-patterns) below.
 </Tip>
 
 ### Memory Methods
@@ -449,7 +449,7 @@ print("Nodes: {}, Edges: {}".format(stats["node_count"], stats["edge_count"]))
 `ContextGraph` exposes a full Distance Intelligence API for exploring semantic neighborhoods and blending proximity into retrieval.
 
 <Info>
-  Full Distance Intelligence reference (distance matrices, API endpoints, embedding cache, Explorer UI) is covered in the dedicated [Distance Intelligence](/reference/distance) page. This section documents the context-layer API.
+  Full Distance Intelligence reference — distance matrices, API endpoints, embedding cache, Explorer UI — is covered in the dedicated [Distance Intelligence](/reference/distance) page. This section documents the context-layer API.
 </Info>
 
 ### Neighbors with Distance Metadata
@@ -480,7 +480,7 @@ for n in neighbors:
 | Added field | Type | Description |
 | :---------- | :---- | :----------- |
 | `distance_band` | `str` | `"direct"` (1 hop) / `"near"` (2) / `"mid-range"` (3–4) / `"distant"` (5+) |
-| `confidence_decay` | `float` | `edge_weight ^ hop_count`; decays with each hop |
+| `confidence_decay` | `float` | `edge_weight ^ hop_count` — decays with each hop |
 | `path_to_anchor` | `List[str]` | Shortest path from anchor node to this neighbor |
 | `hop_count` | `int` | BFS depth from anchor |
 
@@ -659,7 +659,7 @@ if not receipt.complete:
 ```
 
 <Warning>
-Check the receipt. The call returning is not proof the data is gone. FAISS,
+Check the receipt — the call returning is not proof the data is gone. FAISS,
 Milvus, and Weaviate expose no delete method, so erasure cannot be completed on
 those backends today; the receipt reports `unsupported` rather than a success it
 did not achieve.
@@ -687,9 +687,9 @@ At least one store is required; a store that is not supplied reports
 
 | Status | Meaning |
 | :--- | :--- |
-| `erased` | Reached, data removed. On the vectors leg this means the store accepted the delete for the ids given; backends offer no portable existence check, so it is not a count of embeddings that were really there |
+| `erased` | Reached, data removed. On the vectors leg this means the store accepted the delete for the ids given — backends offer no portable existence check, so it is not a count of embeddings that were really there |
 | `not_found` | Reached, held nothing for this entity |
-| `not_configured` | No such store was bound: normal, not a failure |
+| `not_configured` | No such store was bound — normal, not a failure |
 | `unsupported` | The store cannot delete at all; retrying will not help |
 | `failed` | The store was reached and the deletion did not succeed |
 
@@ -721,7 +721,7 @@ receipt.to_dict()
 # }
 ```
 
-Erasure runs outward-in: vectors, then memory, then the graph. The tombstone is
+Erasure runs outward-in — vectors, then memory, then the graph. The tombstone is
 the durable attestation that an erasure happened, so it is written last: a crash
 mid-cascade leaves the node present and the receipt incomplete, rather than a
 tombstone claiming more than actually happened. A store that raises is recorded
@@ -1087,10 +1087,10 @@ class EntityLink:
   </Tab>
 </Tabs>
 
-- [Vector Store](/reference/vector_store): embedding storage backend for memory retrieval.
-- [Knowledge Graph](/reference/kg): graph algorithms and analytics used inside ContextGraph.
-- [Reasoning](/guides/reasoning): logical inference layered on top of context.
-- [Provenance](/guides/provenance): W3C PROV-O lineage for every stored fact.
+- [Vector Store](/reference/vector_store) — Embedding storage backend for memory retrieval.
+- [Knowledge Graph](/reference/kg) — Graph algorithms and analytics used inside ContextGraph.
+- [Reasoning](reasoning) — Logical inference layered on top of context.
+- [Provenance](provenance) — W3C PROV-O lineage for every stored fact.
 
-- [Context Module](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/19_Context_Module.ipynb): memory and decision tracking · Intermediate
-- [Advanced Context Engineering](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb): production FAISS + Neo4j setup · Advanced
+- [Context Module](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/19_Context_Module.ipynb) — Memory and decision tracking · Intermediate
+- [Advanced Context Engineering](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb) — Production FAISS + Neo4j setup · Advanced