mengzhx/semantica
1
0
Fork 0
mirror of https://github.com/semantica-agi/semantica.git synced 2026-08-29 04:26:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Restore 'What's New in v0.4.0' section

Browse Source 
Reintroduce the 'What's New in v0.4.0' section with detailed features of the Temporal Intelligence Stack.
This commit is contained in:
Mohd Kaif
2026-04-08 19:43:46 +05:30
committed by GitHub
parent 17289121cb
commit 47828cff0d
1 changed files with 17 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+17 -20
View File
@@ -53,26 +53,6 @@ pip install semantica
---
## 🚀 What's New in v0.4.0
**1,162+ tests · 0 failures · 0 regressions**
### 🕐 Temporal Intelligence Stack
Everything you need to reason about *when* — not just *what*.
- **Temporal GraphRAG** — retrieve knowledge as it existed at any point in the past. Natural-language queries like *"what did we know before the 2024 merger?"* are automatically parsed for temporal intent, with zero LLM calls.
- **Allen Interval Algebra** — 13 deterministic interval relations (before, meets, overlaps, during, starts, finishes, equals, and their converses). Find gaps, measure coverage, detect cycles — all without touching an LLM.
- **Point-in-time Query Engine** — reconstruct a self-consistent graph snapshot at any timestamp. Comes with a consistency validator that catches 5 classes of temporal errors: inverted intervals, dangling edges, overlapping relations, temporal gaps, and missing entities.
- **Temporal Metadata Extraction** — ask the LLM to annotate each extracted relation with `valid_from`, `valid_until`, and a calibrated confidence score (0–1 scale with baked-in anchors, so the model doesn't cluster near 1.0).
- **TemporalNormalizer** — converts ISO 8601, partial dates, relative phrases ("last year", "Q1 2024"), and 13 domain-specific phrase maps (Healthcare, Finance, Cybersecurity, Supply Chain, Energy…) into UTC datetime pairs. Zero LLM calls.
- **Bi-temporal Provenance** — every provenance record is automatically stamped with transaction time. Full revision history and audit log export in JSON or CSV. Temporal relationships export as OWL-Time RDF triples.
- **Decision validity windows** — decisions now carry `valid_from` / `valid_until`. Superseded decisions stay in the graph — history is immutable. Point-in-time causal chain reconstruction included.
- **Named checkpoints** — snapshot the full agent context at any moment and diff two snapshots to see exactly what changed.
→ [Temporal docs](docs/reference/) · [Temporal examples](cookbook/)
---
## Features
@@ -161,6 +141,23 @@ Everything you need to reason about *when* — not just *what*.
- **Inheritance propagation** — child shapes automatically include all ancestor property shapes (up to 3+ levels), cycle-safe
- **Three output formats** — Turtle (`.ttl`), JSON-LD, N-Triples; file export via `export_shacl()`
## 🚀 What's New in v0.4.0
### 🕐 Temporal Intelligence Stack
Everything you need to reason about *when* — not just *what*.
- **Temporal GraphRAG** — retrieve knowledge as it existed at any point in the past. Natural-language queries like *"what did we know before the 2024 merger?"* are automatically parsed for temporal intent, with zero LLM calls.
- **Allen Interval Algebra** — 13 deterministic interval relations (before, meets, overlaps, during, starts, finishes, equals, and their converses). Find gaps, measure coverage, detect cycles — all without touching an LLM.
- **Point-in-time Query Engine** — reconstruct a self-consistent graph snapshot at any timestamp. Comes with a consistency validator that catches 5 classes of temporal errors: inverted intervals, dangling edges, overlapping relations, temporal gaps, and missing entities.
- **Temporal Metadata Extraction** — ask the LLM to annotate each extracted relation with `valid_from`, `valid_until`, and a calibrated confidence score (0–1 scale with baked-in anchors, so the model doesn't cluster near 1.0).
- **TemporalNormalizer** — converts ISO 8601, partial dates, relative phrases ("last year", "Q1 2024"), and 13 domain-specific phrase maps (Healthcare, Finance, Cybersecurity, Supply Chain, Energy…) into UTC datetime pairs. Zero LLM calls.
- **Bi-temporal Provenance** — every provenance record is automatically stamped with transaction time. Full revision history and audit log export in JSON or CSV. Temporal relationships export as OWL-Time RDF triples.
- **Decision validity windows** — decisions now carry `valid_from` / `valid_until`. Superseded decisions stay in the graph — history is immutable. Point-in-time causal chain reconstruction included.
- **Named checkpoints** — snapshot the full agent context at any moment and diff two snapshots to see exactly what changed.
→ [Temporal docs](docs/reference/) · [Temporal examples](cookbook/)
### 📚 SKOS Vocabulary Management
Build and query controlled vocabularies inside your knowledge graph