sciknoworg · HamedBabaei · Mar 11, 2026 · Nov 24, 2025 · Nov 30, 2025 · Nov 30, 2025
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,6 +1,19 @@
 ## Changelog
 
-### v1.4.11 (Janouary 5, 2026)
+### v1.5.1 (February 23, 2026)
+- Fix challenge learner
+- Update requirements.
+
+### v1.5.0 (February 5, 2026)
+- Fix challenge learners
+- Adding MDS-Onto Ontologizer
+- Fix to Ontologizers and Processor
+- Minor code refactoring
+- Change to the theme of documentatin website
- Change to the theme of documentatin website
+- Change to the theme of documentation website
- Change to the theme of documentatin website
+- Change to the theme of documentation website
+- Update documentation website
+- Add LLM learners (Logit, Thinking, etc)
+
+### v1.4.11 (January 5, 2026)
 - Add `text2onto` component for challenge learners with their documentation.
 - Code refactoring
 - OS compatibility CI/CD

diff --git a/CITATION.cff b/CITATION.cff
@@ -31,5 +31,5 @@ keywords:
   - Large Language Models
   - Text-to-ontology
 license: MIT
-version: 1.4.10
-date-released: '2025'
+version: 1.5.0
-version: 1.5.0
+version: 1.5.1
-version: 1.5.0
+version: 1.5.1
+date-released: '2026'
diff --git a/README.md b/README.md
diff --git a/docs/source/benchmarking/agriculture/agro.rst b/docs/source/benchmarking/agriculture/agro.rst
@@ -25,7 +25,7 @@
 Agronomy Ontology (AgrO)
 ========================================================================================================
 
-An ontology is a formal representation of a disciplinary domain, representing a semantic standard     that can be employed to annotate data where key concepts are defined, as well as the relationships     that exist between those concepts (Gruber, 2009). Ontologies provide a common language for different kinds of data     to be easily interpretable and interoperable allowing easier aggregation and analysis. The Agronomy Ontology (AgrO)     provides terms from the agronomy domain that are semantically organized and can facilitate the collection,     storage and use of agronomic data, enabling easy interpretation and reuse of the data by humans and machines alike.     To fully understand the implications of varying practices within cropping systems and derive insights,     it is often necessary to pull together information from data in different disciplinary domains.     For example, data on field management, soil, weather and crop phenotypes may need to be aggregated     to assess performance of particular crop under different management interventions. However,     agronomic data are often collected, described, and stored in inconsistent ways, impeding data comparison, mining,     interpretation reuse. The use of standards for metadata and data annotation play a key role     in addressing these challenges. While the CG Core Metadata Schema provides a metadata standard     to describe agricultural datasets, the Agronomy Ontology enables the description     of agronomic data variables using standard terms.
+An ontology is a formal representation of a disciplinary domain, representing a semantic standard that can be employed to annotate data where key concepts are defined, as well as the relationships that exist between those concepts (Gruber, 2009). Ontologies provide a common language for different kinds of data to be easily interpretable and interoperable, allowing for easier aggregation and analysis. The Agronomy Ontology (AgrO) provides terms from the agronomy domain that are semantically organized and can facilitate the collection, storage, and use of agronomic data, enabling easy interpretation and reuse of the data by humans and machines alike. To fully understand the implications of varying practices within cropping systems and derive insights, it is often necessary to pull together information from data in different disciplinary domains. For example, data on field management, soil, weather, and crop phenotypes may need to be aggregated to assess performance of a particular crop under different management interventions. However, agronomic data are often collected, described, and stored in inconsistent ways, impeding data comparison, mining, interpretation, and reuse. The use of standards for metadata and data annotation plays a key role in addressing these challenges. While the CG Core Metadata Schema provides a metadata standard to describe agricultural datasets, the Agronomy Ontology enables the description of agronomic data variables using standard terms.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/agriculture/agrovoc.rst b/docs/source/benchmarking/agriculture/agrovoc.rst
@@ -1,5 +1,3 @@
-
-
 .. sidebar::
 
     .. list-table:: **Ontology Card**
@@ -25,7 +23,9 @@
 AGROVOC Multilingual Thesaurus (AGROVOC)
 ========================================================================================================
 
-AGROVOC is a relevant Linked Open Data set about agriculture available for public use and facilitates     access and visibility of data across domains and languages. It offers a structured collection of agricultural concepts,     terms, definitions and relationships which are used to unambiguously identify resources, allowing standardized     indexing processes and making searches more efficient.
+AGROVOC is a comprehensive Linked Open Data resource developed and maintained by the Food and Agriculture Organization (FAO) of the United Nations. It provides a structured collection of agricultural concepts, terms, definitions, and relationships that enable unambiguous identification of resources and standardized indexing. As a multilingual thesaurus, AGROVOC supports multiple languages, facilitating access and visibility of agricultural data across domains and languages. The ontology covers diverse agricultural domains including crops, livestock, farm management practices, soil science, and food production. AGROVOC's hierarchical structure enables both broader and narrower term relationships, supporting semantic interoperability and making searches more efficient. The resource is widely used by research institutions, government agencies, and international organizations for data annotation, knowledge organization, and information retrieval. With millions of concept nodes and sophisticated relationship mappings, AGROVOC serves as a critical backbone for agricultural knowledge representation and data integration in the global agricultural community.
+
+**Example Usage**: Annotate a multilingual agricultural dataset with AGROVOC terms for crops, soil types, and farming practices to enable standardized indexing and cross-language search in international agricultural databases.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/agriculture/atol.rst b/docs/source/benchmarking/agriculture/atol.rst
@@ -1,5 +1,3 @@
-
-
 .. sidebar::
 
     .. list-table:: **Ontology Card**
@@ -25,7 +23,14 @@
 Animal Trait Ontology for Livestock (ATOL)
 ========================================================================================================
 
-ATOL (Animal Trait Ontology for Livestock) is an ontology of characteristics defining phenotypes of livestock     in their environment (EOL). ATOL aims to:     - provide a reference ontology of phenotypic traits of farm animals for the international scientific and educational     - communities, farmers, etc.;     - deliver this reference ontology in a language which can be used by computers in order to support database management,     semantic analysis and modeling;     - represent traits as generic as possible for livestock vertebrates;     - make the ATOL ontology as operational as possible and closely related to measurement techniques;     - structure the ontology in relation to animal production.
+ATOL (Animal Trait Ontology for Livestock) is an ontology of characteristics defining phenotypes of livestock in their environment. ATOL aims to: provide a reference ontology of phenotypic traits of farm animals for the international scientific and educational communities, farmers, etc.; deliver this reference ontology in a language which can be used by computers in order to support database management, semantic analysis and modeling; represent traits as generic as possible for livestock vertebrates; make the ATOL ontology as operational as possible and closely related to measurement techniques; and structure the ontology in relation to animal production.
+
+The ontology employs a class-based modeling approach, defining classes for different types of phenotypic traits, measurement techniques, and related data, along with properties to describe their characteristics and interactions. Hierarchies are used to organize classes into categories, enabling efficient data retrieval and analysis. ATOL supports the integration of data from various sources, promoting interoperability and data-driven research in animal science.
+
+Typical applications of ATOL include the development of new phenotypic trait analysis methods, the optimization of livestock management practices, and the integration of diverse datasets to support advanced analytics and knowledge discovery. By providing a standardized vocabulary and framework, ATOL enhances collaboration and innovation in the field of animal science.
+
+**Example Usage**:
+Annotate a livestock dataset with ATOL terms to specify phenotypic traits, measurement techniques, and related data, enabling semantic search and integration with animal science research platforms.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/agriculture/foodon.rst b/docs/source/benchmarking/agriculture/foodon.rst
@@ -25,7 +25,7 @@
 Food Ontology (FoodON)
 ========================================================================================================
 
-FoodOn, the food ontology, contains vocabulary for naming food materials and their anatomical and taxonomic origins,     from raw harvested food to processed food products, for humans and domesticated animals.     It provides a neutral and ontology-driven standard for government agencies,     industry, nonprofits and consumers to name and reference food products and their components     throughout the food supply chain.
+FoodOn, the Food Ontology, provides comprehensive vocabulary for naming and classifying food materials throughout the entire food supply chain. It encompasses raw harvested foods and their botanical/zoological origins as well as processed food products designed for both human consumption and animal feed. FoodOn integrates anatomical and taxonomic knowledge, enabling precise semantic representation of food items and their components. The ontology is designed as a neutral, ontology-driven standard that bridges the interests of government agencies, industry stakeholders, nonprofits, and consumers. Its hierarchical structure captures relationships between ingredient components, processing methods, and final food products. FoodOn facilitates standardized naming conventions and interoperability across diverse food-related databases and systems. The ontology supports critical applications including food safety traceability, nutritional analysis, dietary research, and supply chain transparency. By providing unambiguous semantic definitions, FoodOn enables automated systems to track food products, ingredients, and allergens, enhancing data integration across the food industry and supporting evidence-based policy decisions in food security and nutrition.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/agriculture/po.rst b/docs/source/benchmarking/agriculture/po.rst
@@ -25,7 +25,7 @@
 Plant Ontology (PO)
 ========================================================================================================
 
-The Plant Ontology (PO) is a structured vocabulary and database resource that links plant anatomy,     morphology and growth and development to plant genomics data.
+The Plant Ontology (PO) is a structured vocabulary and database resource that links plant anatomy, morphology and growth and development to plant genomics data. Developed collaboratively by plant biologists and ontology experts, PO provides a comprehensive framework for describing plant structures and developmental stages. The ontology integrates anatomical terms that can be associated with plant genes, enabling researchers to annotate phenotypic data and support comparative genomics across plant species. PO is designed to facilitate seamless data integration and interoperability in plant science research, allowing scientists to discover relationships between genes and plant structures. With its hierarchical organization of plant parts from whole organism level down to cellular structures, PO supports diverse applications including literature curation, genome annotation, and systems biology studies. The ontology is actively maintained by the Planteome project and integrated with other biological ontologies to ensure compatibility and comprehensive semantic representation in the plant science community.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/arts_and_humanities/chordontology.rst b/docs/source/benchmarking/arts_and_humanities/chordontology.rst
@@ -25,7 +25,7 @@
 Chord Ontology (ChordOntology)
 ========================================================================================================
 
-The Chord Ontology is an ontology for describing chords in musical pieces.
+The Chord Ontology is a formal representation for describing and classifying chords in musical compositions. It provides a structured vocabulary for representing harmonic concepts and chord structures, enabling precise annotation and analysis of music at the semantic level. The ontology captures essential chord properties including chord type (major, minor, diminished, augmented), root note, and constituent pitch classes. It facilitates semantic annotation of audio files, musical scores, and music information retrieval systems, allowing researchers and musicians to query and discover musical pieces based on harmonic content. The ontology integrates with broader music theory frameworks and supports interoperability with other music-related ontologies. By formalizing chord relationships and structures, the Chord Ontology enables computational music analysis, music recommendation systems, and digital musicology applications. It provides a common framework for music annotation across diverse platforms and datasets, supporting music education, composition analysis, and music information systems development.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/arts_and_humanities/icon.rst b/docs/source/benchmarking/arts_and_humanities/icon.rst
@@ -25,7 +25,7 @@
 Icon Ontology (ICON)
 ========================================================================================================
 
-The ICON ontology deals with high granularity art interpretation. It was developed by conceptualizing     Panofsky's theory of levels of interpretation, therefore artworks can be described according     to Pre-iconographical, Iconographical and Iconological information.
+The ICON ontology provides a formal framework for high-granularity art interpretation and analysis. It was developed by conceptualizing Panofsky's theory of levels of interpretation, enabling artworks to be systematically described according to three complementary analytical perspectives: Pre-iconographical (visual elements and their formal properties), Iconographical (symbolic meaning and subject matter), and Iconological (deeper cultural and philosophical context). This three-level approach enables comprehensive semantic annotation of artworks, capturing both surface-level visual descriptions and deeper interpretive insights. The ontology supports structured knowledge representation of artistic elements, iconographic themes, cultural references, and symbolic meanings. It facilitates semantic interoperability in digital art collections, museum databases, and art history research platforms. The ICON ontology enables advanced search and discovery capabilities based on artistic interpretation levels, supporting art historians, curators, and researchers in analyzing and understanding artworks. It also supports linked data integration with other cultural heritage ontologies and knowledge bases, enabling rich cross-domain art historical research and interpretation analysis.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/arts_and_humanities/musicontology.rst b/docs/source/benchmarking/arts_and_humanities/musicontology.rst
@@ -25,7 +25,7 @@
 Music Ontology (MusicOntology)
 ========================================================================================================
 
-The Music Ontology Specification provides main concepts and     properties fo describing music (i.e. artists, albums and tracks)     on the Semantic Web.
+The Music Ontology Specification provides a comprehensive framework for describing music and related entities on the Semantic Web. It defines core concepts and properties for representing artists, albums, tracks, performances, and musical relationships. The ontology enables standardized music metadata annotation, facilitating interoperability across music information systems, streaming platforms, and digital libraries. It supports rich description of musical works including production details, distribution information, and artistic collaborations. The Music Ontology integrates with other semantic web vocabularies and allows linking of music resources with external datasets and knowledge bases. It enables music recommendation systems, search engines, and music discovery applications to leverage structured semantic data. The ontology supports various music-related use cases including discography management, performance tracking, playlist creation, and music history documentation. By providing a common framework for music representation, the Music Ontology facilitates semantic data integration across the music industry and enables advanced music information retrieval and analysis capabilities.
 
 Metrics & Statistics
 --------------------------

diff --git a/docs/source/benchmarking/arts_and_humanities/nomisma.rst b/docs/source/benchmarking/arts_and_humanities/nomisma.rst
@@ -25,7 +25,7 @@
 Nomisma Ontology (Nomisma)
 ========================================================================================================
 
-Nomisma Ontology is a collaborative project to provide stable digital representations of numismatic concepts according     to the principles of Linked Open Data. These take the form of http URIs that provide access to the information     about a concept in various formats. The project is a collaborative effort of the American Numismatic Society     and the Institute for the Study of the Ancient World at New York University.
+The Nomisma Ontology is a collaborative project that provides stable, standardized digital representations of numismatic concepts following the principles of Linked Open Data. It offers HTTP URIs that provide persistent access to information about numismatic entities in multiple formats, enabling seamless integration with other linked open data resources. Developed collaboratively by the American Numismatic Society and the Institute for the Study of the Ancient World at New York University, Nomisma represents a comprehensive framework for describing coins, denominations, mints, rulers, and monetary systems across different periods and cultures. The ontology facilitates semantic annotation of numismatic data, supporting interoperability across digital coin collections, archaeological databases, and historical research platforms. It enables advanced querying and analysis capabilities for numismatists, archaeologists, and historians seeking to understand monetary systems and economic aspects of historical societies. The ontology integrates with broader cultural heritage and historical linked data ecosystems, supporting cross-domain research on ancient economies, trade networks, and political history. By providing standardized semantic representations, Nomisma enhances discoverability and reusability of numismatic data in the global digital humanities and cultural heritage communities.
 
 Metrics & Statistics
 --------------------------