Insights
Community reading notes and practical insight from current work.
Insights is the Curate Labs blog: community research spotlights, field notes, and practical observations from the graph-data and AI systems space we are part of.
Community Reading: GLiNER-Relex for Zero-Shot Joint Extraction
GLiNER-Relex extends the GLiNER family into a unified zero-shot NER and relation extraction model.
Read insightWACCY v0.1.0: A Three-Statement Modeling Slice
WACCY v0.1.0 is the first released vertical slice of our small-business financial modeling stack: extraction contracts, validated datasets, model builders, and exporters.
Read insightGraphForge v0.4.0: Three-Surface API
GraphForge v0.4.0 completed the three-surface architecture: Cypher execution, graph algorithms, and hybrid search.
Read insightGraphForge v0.3.10: Analytics Integration
GraphForge v0.3.10 made the engine easier to integrate with analytical and agentic graph workflows.
Read insightGraphForge v0.3.9: Performance
GraphForge v0.3.9 kept full TCK compliance while delivering performance improvements across the stack.
Read insightGraphForge v0.3.8: Full openCypher TCK Compliance
GraphForge v0.3.8 reached 100% openCypher TCK compliance with 3,885 of 3,885 scenarios passing.
Read insightGraphForge v0.3.7: Function Coverage
GraphForge v0.3.7 expanded function coverage and moved reported TCK compliance to 3,235 of 3,885 scenarios.
Read insightGraphForge v0.3.6: TCK Harness and Temporal Fixes
GraphForge v0.3.6 was a correctness release that moved TCK coverage from 1,694 to 2,507 passing scenarios.
Read insightGraphForge v0.3.4: Operators and String Functions
GraphForge v0.3.4 filled in operator and string-function gaps, raising reported feature completeness to 92%.
Read insightGraphForge v0.3.5: Math, Aggregation, and TCK Steps
GraphForge v0.3.5 added sqrt, rand, pow, aggregation test fixes, and missing TCK step definitions.
Read insightGraphForge v0.3.1: Predicate Functions
GraphForge v0.3.1 completed predicate functions and improved NULL-aware list and property testing.
Read insightGraphForge v0.3.2: List Operations
GraphForge v0.3.2 completed list functions, adding filter, extract, and reduce with proper scoping and NULL handling.
Read insightGraphForge v0.3.3: Pattern and CALL Features
GraphForge v0.3.3 pushed deeper into expressive graph queries with pattern predicates, CALL subqueries, and pattern comprehension.
Read insightGraphForge v0.3.0: Major Cypher Feature Release
GraphForge v0.3.0 was a major query-language release that substantially expanded openCypher compatibility.
Read insightCommunity Reading: DOREMI for Long-Tail DocRE
DOREMI focuses on the deployment problem of rare relation performance rather than proposing another relation model.
Read insightGraphForge v0.2.1: Dataset Loading
GraphForge v0.2.1 made it easier to start analysis quickly by adding cached loading for real-world SNAP graph datasets.
Read insightGraphForge v0.2.0: Core Cypher Complete
GraphForge v0.2.0 moved the query language from early capability toward practical core Cypher coverage.
Read insightGraphForge v0.1.4: CI/CD Excellence
GraphForge v0.1.4 made the project faster to iterate on by moving coverage feedback and test analytics closer to the developer.
Read insightGraphForge v0.1.2: Infrastructure Improvements
GraphForge v0.1.2 focused on the professional project infrastructure needed for a graph database to mature in public.
Read insightCommunity Reading: CoDe-KG and Sentence Complexity
CoDe-KG treats scientific KG construction as a pipeline of coreference, simplification, decomposition, and relation extraction.
Read insightCommunity Reading: GRAPHTREX for Clinical Temporal RE
GRAPHTREX uses span extraction and heterogeneous graph transformers to model long-range temporal relations in clinical notes.
Read insightCommunity Reading: KGGen for Text-to-KG Construction
KGGen pairs an LLM text-to-KG pipeline with a benchmark focused on graph usefulness.
Read insightCommunity Reading: Graph-DPEP for Few-Shot DocRE
Graph-DPEP makes prompted document relation extraction more structured by decomposing relation types and revisiting missed pairs.
Read insightCommunity Reading: Mathematical Derivation Graphs
Mathematical Derivation Graphs defines a graph extraction task over equation dependencies in STEM manuscripts.
Read insightCommunity Reading: CoRE-NEPD for Cross-Document RE
CoRE-NEPD uses a unified entity graph and debiasing to improve cross-document relation extraction.
Read insightCommunity Reading: GraphER as Structure Learning for IE
GraphER shifts joint extraction from tagging or generation toward graph structure learning.
Read insightCommunity Reading: Extract, Define, Canonicalize
EDC treats knowledge graph construction as extraction plus schema definition and canonicalization.
Read insightCommunity Reading: FCDS and Syntax-Fused Document RE
FCDS is a reminder that syntax still matters for document-level relation extraction.
Read insightCommunity Reading: GraphScholarBERT for Semi-Structured Web IE
GraphScholarBERT treats webpages as semi-structured graph-and-language objects rather than plain text.
Read insightCommunity Reading: ATG for Joint Entity and Relation Extraction
ATG is a clean text-to-graph formulation for supervised joint entity and relation extraction.
Read insight