BuildGraph: A Synthetic Multi-Archetype Building Knowledge Graph Dataset

arXiv:2610.00038 · cs.DB · Submitted 2026-09-02 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Computer Science. The day in computer science: software, systems and theory on arXiv.

Tom: We're looking at the paper: "BuildGraph: A Synthetic Multi-Archetype Building Knowledge Graph Dataset".

Jane: Here's the gist of the paper. Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations, from natural-language access to cross-building analytics BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U.S.

Tom: Department of Energy prototype models and sensor-placement patterns from real buildings.

Jane: Dataset Scope and Grounding BuildGraph provides a collection of 120 synthetic building KGs in the Brick Schema ontology, derived from two empirical sources The dataset spans eight commercial building types across three ASHRAE energy-code vintages, with five realizations per archetype varying URI naming, sensor-attachment predicates, and topology.

Tom: Building configurations are derived from the U.S.

Paper summary: Jane: So we've covered the basics of what this paper is about. To wrap up the summary of "BuildGraph: A Synthetic Multi-Archetype Building Knowledge Graph Dataset," the main thesis is that building knowledge graphs are crucial for AI in building operations, but they are too scarce to be widely available because of proprietary issues.

Tom: Right. And BuildGraph addresses this scarcity by creating a synthetic dataset of one hundred twenty buildings in the Brick Schema ontology <ref:2610.00038#pg1,dataset of 120 buildings in the Brick Schema ontology>. It’s grounded in U.S. Department of Energy prototype models and sensor placement patterns from real buildings to make it as realistic as possible for research purposes, right?

Lu: Specifically, the dataset spans eight commercial building types across three ASHRAE energy-code vintages with five realizations per archetype that vary things like URI naming and sensor attachment predicates. This variety is key because it makes the data more challenging for testing.

Meng: And they used empirical data from the Mortar corpus to calibrate sensor placement, ensuring the frequency and type of sensors attached mirrors observed practice across real instrumented buildings. That’s an important detail for anyone building a model based on this.

Jane: It’s also important that they show structural completeness, achieving ninety-one point five percent Query Answerability Rate against thirty-five point eight percent for fifty-nine real-world Brick files, which shows the graphs are substantially more complete than what's currently public.

Tom: And beyond just completeness, they validated the dataset by reproducing real buildings’ sensor type proportions on their shared vocabulary with a cosine of zero point eighty six to zero point ninety four, which proves the data reflects real-world sensor usage patterns.

Lu: They also used SHACL schema conformance, and they achieved a one hundred percent conformance rate across all one hundred twenty buildings, confirming the present relationships are valid according to the schema <ref:2610.00038#pg1>. This gives us confidence in the structure they’ve built.

Meng: It’s clear this is a data creation effort aimed at solving a real bottleneck for AI integration into building operations where access to these knowledge graphs is currently blocked by proprietary restrictions and cost barriers.

Jane: Exactly, so they are providing a scalable, reproducible way to get high-quality, diverse building KGs for testing downstream tasks like text-to-SPARQL systems. This sets the stage for research that was previously limited by the small number of publicly available anonymized KG models.

Conclusion: Tom: So looking at the paper "BuildGraph: A Synthetic Multi-Archetype Building Knowledge Graph Dataset," it seems they’ve successfully created a large, structured synthetic building KG dataset for researchers to work with. The authors are Wooyoung Jung and his team.

Jane: It’s a very practical contribution because it directly tackles the problem of data scarcity in this area by providing something that is both diverse and grounded in real-world building models. They provide a documented, open-source methodology for generating these graphs which researchers can extend.

Lu: The main implication I see is that this dataset helps move text-to-SPARQL systems toward being better interfaces for facility managers by giving them the kind of structurally complete examples they need to train few-shot models effectively.

Meng: For me, the practical takeaway is that it gives us a way to generate diverse test cases tailored to specific portfolios, which is valuable for testing deployment stability on actual traffic.

Tom: So in simple terms, they’ve built a synthetic building KG dataset that helps researchers and engineers build better AI tools for accessing building knowledge through natural language queries without needing deep SPARQL expertise.

Jane: That’s the core idea: using synthetic data to solve a problem where real data is too scarce, and it gives us a solid foundation for the next wave of cross-building analytics in construction.

University of Arizona

cs.DB

Submitted: 2026-09-02

Updated: 2026-11-09

Comments: 25 pages, 3 figures. Data paper. Dataset, generator, and 75-query SPARQL benchmark openly available at https://github.com/humanbuildingsynergy/BuildGraph and https://doi.org/10.5281/zenodo.20015123. Re-set in the HUBS Lab paper layout (HUBS Lab Paper No. 2026-005); content unchanged

Code: https://github.com/humanbuildingsynergy/BuildGraph

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

Importance score: 90/100

The gist: Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations…

Key concepts

Brick Schema Ontology
This is the standardized vocabulary used to describe buildings in the knowledge graph. It provides a consistent way to label and connect different aspects of a building, such as equipment types, zones, and their relationships. This schema allows AI models to understand building data across various structures.
Synthetic Building KG
This is a dataset where buildings are artificially generated based on real-world prototypes. The researchers used DOE models and real sensor placement patterns to create these graphs. This method generates many varied building configurations, allowing researchers to test AI systems on diverse, realistic scenarios.
QAR (Query Answerability Rate)
QAR measures how well a knowledge graph can answer specific questions asked in natural language. It is calculated by checking the percentage of meaningful queries that successfully return at least one result. A high QAR indicates the graph is structurally complete and useful for complex information retrieval.
Text-to-SPARQL Experiment
This experiment tests how well a model can translate a natural language question into a precise SPARQL query that retrieves data from the building KG. It shows that few-shot prompting with examples significantly improves performance on cross-building generalization, proving the dataset's utility for complex analytical tasks.

Terminology

Summary

Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations, from natural-language access to cross-building analytics BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U. p. 0

Where the paper says it

(Corresponding author) Abstract: Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations, from natural-language access to cross-building analytics, but such KGs are rarely public owing to proprietary, security, and cost barriers. BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U.

S. Department of Energy prototype models and sensor-placement patterns from real buildings. p. 0
Where the paper says it

BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U. Department of Energy prototype models and sensor-placement patterns from real buildings.

Dataset Scope and Grounding

BuildGraph provides a collection of 120 synthetic building KGs in the Brick Schema ontology, derived from two empirical sources The dataset spans eight commercial building types across three ASHRAE energy-code vintages, with five realizations per archetype varying URI naming, sensor-attachment predicates, and topology. Building configurations are derived from the U. p. 1

Where the paper says it

This data paper introduces BuildGraph and its associated dataset: a collection of 120 synthetic building KGs in the Brick Schema ontology, grounded in two independent empirical sources. First, building configurations are derived from the U.

S. Department of Energy (DOE) Commercial Prototype Building Models (U. p. 1
Where the paper says it

First, building configurations are derived from the U. Department of Energy (DOE) Commercial Prototype Building Models (U.

S. Department of Energy 2024), which define HVAC system type, equipment counts, terminal unit configuration, and zone structure for eight representative commercial building types spanning three energy code vintages. p. 1
Where the paper says it

Department of Energy (DOE) Commercial Prototype Building Models (U. Department of Energy 2024), published specifications that define the HVAC system type, equipment counts, terminal unit configuration, and zone structure for eight representative commercial building types spanning three energy code vintages.

Sensor placement probabilities are calibrated against real buildings from the Mortar corpus (Fierro et al. p. 1
Where the paper says it

commercial building simulation research. Second, sensor placement probabilities are calibrated against real buildings from the Mortar corpus (Fierro et al.

2019; Brick Schema Community 2024), ensuring that the frequency and type of sensors attached to each equipment class reflects observed practice across real instrumented buildings. p. 1
Where the paper says it

Second, sensor placement probabilities are calibrated against real buildings from the Mortar corpus (Fierro et al. 2019; Brick Schema Community 2024), ensuring that the frequency and type of sensors attached to each equipment class reflects observed practice across real instrumented buildings.

Structural Completeness Metrics

Dataset quality is assessed along two dimensions, first by a 75-query SPARQL benchmark measuring the Query Answerability Rate (QAR) BuildGraph achieves an overall QAR of 91.5%, compared to 35. p. 1

Where the paper says it

BuildGraph achieves an overall QAR of 91. 5%, compared to 35.

8% for a corpus of 59 public building files, indicating that the generated graphs are substantially more structurally complete with respect to this benchmark. p. 1
Where the paper says it

5%, compared to 35. 8% for a corpus of 59 publicly available real-world Brick building files – indicating that the generated graphs are substantially more structurally complete with respect to this benchmark.

Second, a downstream text-to-SPARQL experiment directly evaluates the dataset’s utility for cross-building generalization. p. 1
Where the paper says it

8% for a corpus of 59 publicly available real-world Brick building files – indicating that the generated graphs are substantially more structurally complete with respect to this benchmark. Second, a downstream text-to-SPARQL experiment directly evaluates the dataset’s utility for cross-building generalization.

The QAR is defined as the fraction of applicable, semantically meaningful SPARQL queries that return at least one result row when executed against a building KG. p. 3
Where the paper says it

These omissions are invisible to SHACL because SHACL checks conformance – whether what is present is schema-valid – not completeness – whether everything a query requires is there. The appropriate measure is therefore query-centric: the Query Answerability Rate (QAR), defined as the fraction of applicable, semantically meaningful SPARQL queries that return at least one result row when executed against a building KG.

Validation and Fidelity Checks

Dataset quality is validated across six complementary dimensions, including generation-time structural checks and SHACL schema conformance. The validator counts how many generated entity-property-entity triples match entries in the empirical pattern database, with a threshold of at least one floor-zone, zone-terminal, and AHU-terminal relationship required for structural failure. p. 2

Where the paper says it

SPARQL (Harris and Seaborne 2013) is the W3C standard query language for RDF, enabling queries to pattern-match against building instance triples using Brick class and property definitions to navigate relationships. A key capability is the property path operator (brick:feeds+), which matches one or more consecutive brick:feeds edges, enabling a single query to trace the full supply chain from chiller to zone.

SHACL conformance verifies that the present relationships are schema-valid across all 120 released buildings yields a 100% conformance rate (Section 6. p. 3
Where the paper says it

SAT-1 brick:hasPoint SHACL: pass QAR: fail (no path to zone) SHACL: pass QAR: pass (path found) (a) Schema-valid but structurally imcomplete (b) Schema-valid and structurally complete Fig. SHACL conformance verifies that present relationships are schema-valid; QAR measures whether the graph contains the relationships that queries require.

1).

Downstream Utility and Generalization

The text-to-SPARQL experiment with Gemma 4 (26B) reaches 27.3% Row-Matching F1 (+17. p. 0

Where the paper says it

A downstream text-to-SPARQL experiment with Gemma 4 (26B) reaches 27. 3% Row-Matching F1 (+17.

5 pp over zero-shot) on 12 held-out buildings, demonstrating that few-shot prompting with cross-building BuildGraph examples achieves this performance. p. 2
Where the paper says it

Downstream validation via a text-to-SPARQL evaluation using Gemma 4 (26B) (Gemma Team, Google DeepMind 2026) on 12 held-out buildings, demonstrating that few-shot prompting with cross-building BuildGraph text-to-SPARQL examples achieves 27. 3% Row-Matching F1 (the harmonic mean of precision and recall over the set of result rows a query returns— measuring whether the query returns the correct answer independent of SPARQL surface form, and defined in Section 6.

This result establishes two findings relevant to BuildGraph’s utility, first that the dataset provides genuinely challenging test cases where Category 5 (Multi-hop / Complex) scores 0. p. 0
Where the paper says it

Author keywords: building knowledge graph; synthetic dataset; Brick Schema; SPARQL; intelligent buildings; text-toSPARQL Practical Applications BuildGraph gives building practitioners a free, ready-made set of 120 realistic building knowledge graphs and a 75-question query benchmark that would otherwise require proprietary, hard-to-obtain building data. Facility managers and controls engineers can test fault-detection and energy-analytics queries across many building types and vintages before applying them to their own sites; software developers can benchmark tools that translate plain-English questions into building-database queries; and digital-twin developers can prototype and validate semantic applications without first assembling a real building’s knowledge graph.

0% zero-shot and 10. p. 0
Where the paper says it

3% Row-Matching F1 (+17. 5 pp over zero-shot) on 12 held-out buildings.

1% with examples. p. 1
Where the paper says it

Real-world building KGs are rarely publicly available due to proprietary restrictions, security concerns, and lack of instrumented buildings, limiting supply to a small number of anonymized KG models released by national laboratories and universities. This scarcity is particularly acute for text-to-SPARQL research – systems that translate natural language questions into executable SPARQL Protocol and RDF Query Language (SPARQL) queries, emerging as a critical interface for facility managers and energy engineers to access building knowledge without SPARQL expertise – because such systems require diverse, structurally complete KGs as few-shot examples, training data, and evaluation benchmarks.

Second, cross-building examples are most effective for aggregation queries, showing a +37. p. 1
Where the paper says it

8% for a corpus of 59 publicly available real-world Brick building files – indicating that the generated graphs are substantially more structurally complete with respect to this benchmark. Second, a downstream text-to-SPARQL experiment directly evaluates the dataset’s utility for cross-building generalization.

8 pp gain on Category 4 (Aggregation). p. 7
Where the paper says it

3 Knowledge Graph Content Entity Classes The dataset uses 83 distinct Brick classes. Table 6 organizes the equipment entity classes by functional category.

Contribution and Extensibility

The primary contributions of this paper include a publicly accessible dataset of 120 synthetic building KGs in the Brick Schema ontology, spanning eight commercial building types, three ASHRAE energy code vintages, and various HVAC configurations. A documented, open-source methodology for reproducible synthetic building KG generation is provided to enable the research community to extend the dataset to additional building types or seeds. p. 1

Where the paper says it

A 75-query SPARQL benchmark for measuring structural quality of building KGs, with scope-detection logic that automatically determines which queries are applicable to each graph and an evaluation framework aligned with building complexity. A documented, open-source methodology for reproducible synthetic building KG generation, grounded in published prototype models and empirical sensor placement data, enabling the research community to extend the dataset to additional building types, ontology modes, or seeds.

The generator is released, allowing practitioners to produce additional buildings tailored to their own portfolio. p. 0
Where the paper says it

Facility managers and controls engineers can test fault-detection and energy-analytics queries across many building types and vintages before applying them to their own sites; software developers can benchmark tools that translate plain-English questions into building-database queries; and digital-twin developers can prototype and validate semantic applications without first assembling a real building’s knowledge graph. Because the generator is released, practitioners can also produce additional buildings tailored to their own portfolio.

Limitations and Future Directions

Known limitations include that the text-to-SPARQL experiment uses a structured natural-language summary rather than the raw RDF graph, which should be read as a conservative lower bound. The dataset does not include actual sensor measurement values, and its scope is limited to structural and topological information only. p. 7

Where the paper says it

“Scope” indicates which buildings include instances of that category. Category Brick classes Scope Building hierarchy Building, Floor, HVAC Zone All Air-handling units AHU, Supply Fan, Return Fan, Heating Coil, Cooling Coil, Variable Frequency Drive, Economizer Damper, Exhaust Damper, Return Damper All Heat recovery Heat Exchanger (ERV) 2013 DOAS only VAV terminals VAV, Variable Air Volume Box With Reheat VAV, PVAV, and CAV systems FCU terminals Fan Coil Unit FCU systems Central plant Chiller, Cooling Tower, Boiler, Chilled Water Pump, Hot Water Pump, Condenser Water Pump Central-plant buildings Metering Electrical Meter 2004 and 2013 Sensor and Control Points Sensor and control points span four domains, sampled from probabilities calibrated against the Mortar dataset.

Furthermore, the synthetic topology does not represent any specific real facility, though statistical properties match real buildings at the distribution level. p. 1
Where the paper says it

Structurally realistic synthetic KGs – matching the equipment types, sensor placement patterns, topological relationships, and HVAC system configurations found in real buildings – can substitute for real KGs as few-shot examples and evaluation benchmarks without privacy risk or access barriers. The key design challenge is ensuring that the synthesis is empirically grounded rather than arbitrary: a randomly generated graph can satisfy syntactic constraints while being physically implausible, producing a dataset that teaches a model the wrong distribution.

The dataset is deposited at Zenodo (https://doi. p. 6
Where the paper says it

0 Repository / DOI https://doi. 5281/zenodo. p. 6

Where the paper says it

0 Repository / DOI https://doi. 5281/zenodo.

org/10.5281/zenodo.20015123) and the generator source code, benchmark queries, and pattern databases are available in the BuildGraph repository. p. 0
Where the paper says it

5 pp over zero-shot) on 12 held-out buildings. BuildGraph gives facility managers and digital-twin developers a testbed for portable analytics and natural-language interfaces, and its dataset, generator, and benchmark are openly available at https://github.

The data availability statement confirms that all data used to produce the dataset is documented in the repository. p. 3
Where the paper says it

A high QAR confirms that the A-box is structurally rich enough to support the full range of queries a downstream application would issue; a low QAR reveals coverage gaps – analogous to the query-based completeness dimension in linked data quality literature (Zaveri et al. 2016) – that would silently produce empty results in practice (Figure 2).

References

Almashor, M., Rana, M., McCulloch, J., Rahman, A., and Sethuvenkatraman, S. (2023). “What’s the point: AutoEncoding building point names. p. 4

Where the paper says it

(2021) confirmed that Brick offers the strongest foundation for semantic querying among existing schemas. Complementary standards have since emerged – ASHRAE 223P (ASHRAE 2023) for connection-point topology, the Building Topology Ontology (BOT) (Rasmussen et al.

” Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys). p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

ASHRAE (1995). p. 3

Where the paper says it

3 Related Work 3. 1 Building Metadata Standards and the Brick Schema Early standardization efforts addressed communication interoperability (BACnet (ASHRAE 1995)) and tag-based operational semantics (Project Haystack (Project Haystack Association 2014)), but lacked typed, named relationships between entities, making SPARQL-based querying and ontological inference impossible (Bhattacharya et al.

“BACnet — a data communication protocol for building automation and control networks. p. 3
Where the paper says it

3 Related Work 3. 1 Building Metadata Standards and the Brick Schema Early standardization efforts addressed communication interoperability (BACnet (ASHRAE 1995)) and tag-based operational semantics (Project Haystack (Project Haystack Association 2014)), but lacked typed, named relationships between entities, making SPARQL-based querying and ontological inference impossible (Bhattacharya et al.

” ANSI/ASHRAE Standard 135-1995, American Society of Heating, Refrigerating and Air-Conditioning Engineers, Atlanta, GA. p. 0
Where the paper says it

1 Introduction Building knowledge graphs (KGs) are semantic models that represent the physical components, relationships, and instrumentation of a building as a machine-readable graph. For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al.

p. 0
Where the paper says it

1 Introduction Building knowledge graphs (KGs) are semantic models that represent the physical components, relationships, and instrumentation of a building as a machine-readable graph. For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al.

p. 0
Where the paper says it

1 Introduction Building knowledge graphs (KGs) are semantic models that represent the physical components, relationships, and instrumentation of a building as a machine-readable graph. For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al.

ASHRAE (2021). p. 4

Where the paper says it

(2021) confirmed that Brick offers the strongest foundation for semantic querying among existing schemas. Complementary standards have since emerged – ASHRAE 223P (ASHRAE 2023) for connection-point topology, the Building Topology Ontology (BOT) (Rasmussen et al.

Guideline 36-2021: High-Performance Sequences of Operation for HVAC Systems. American Society of Heating, Refrigerating and Air-Conditioning Engineers, Atlanta, GA.

ASHRAE (2023). p. 4

Where the paper says it

(2021) confirmed that Brick offers the strongest foundation for semantic querying among existing schemas. Complementary standards have since emerged – ASHRAE 223P (ASHRAE 2023) for connection-point topology, the Building Topology Ontology (BOT) (Rasmussen et al.

“Ashrae standard 223p: Designation and classification of semantic tags for building systems. p. 4
Where the paper says it

(2021) confirmed that Brick offers the strongest foundation for semantic querying among existing schemas. Complementary standards have since emerged – ASHRAE 223P (ASHRAE 2023) for connection-point topology, the Building Topology Ontology (BOT) (Rasmussen et al.

” Report no., American Society of Heating, Refrigerating and Air-Conditioning Engineers, Atlanta, GA.

Balaji, B., Bhattacharya, A. p. 1

Where the paper says it

2025), covers four buildings annotated in a mixture of Brick, ASHRAE 223P, and mixed-schema formats, providing insufficient scale and structural diversity for systematic evaluation or cross-building generalization studies. This data scarcity problem is likely to persist for the foreseeable future due to a steep learning curve for practitioners to learn, create, and maintain building KGs (Bhattacharya et al.

p. 1
Where the paper says it

2025), covers four buildings annotated in a mixture of Brick, ASHRAE 223P, and mixed-schema formats, providing insufficient scale and structural diversity for systematic evaluation or cross-building generalization studies. This data scarcity problem is likely to persist for the foreseeable future due to a steep learning curve for practitioners to learn, create, and maintain building KGs (Bhattacharya et al.

p. 1
Where the paper says it

2025), covers four buildings annotated in a mixture of Brick, ASHRAE 223P, and mixed-schema formats, providing insufficient scale and structural diversity for systematic evaluation or cross-building generalization studies. This data scarcity problem is likely to persist for the foreseeable future due to a steep learning curve for practitioners to learn, create, and maintain building KGs (Bhattacharya et al.

p. 1
Where the paper says it

2025), covers four buildings annotated in a mixture of Brick, ASHRAE 223P, and mixed-schema formats, providing insufficient scale and structural diversity for systematic evaluation or cross-building generalization studies. This data scarcity problem is likely to persist for the foreseeable future due to a steep learning curve for practitioners to learn, create, and maintain building KGs (Bhattacharya et al.

, Fierro, G. p. 0
Where the paper says it

For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al. 2016; Fierro et al.

p. 0
Where the paper says it

For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al. 2016; Fierro et al.

p. 0
Where the paper says it

For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al. 2016; Fierro et al.

p. 0
Where the paper says it

For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al. 2016; Fierro et al.

, Gao, J., Gluck, J., Hong, D., Johansen, A., Koh, J., Ploennigs, J., Agarwal, Y., Berges, M., Culler, D. (2016). “Brick: Towards a unified metadata schema for buildings. p. 4
Where the paper says it

2019), which published anonymized Brick models for 45 real buildings from multiple U. university campuses and provided a unified SPARQL query interface over building data.

” Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys), 41–50. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Balaji, B., Bhattacharya, A., Fierro, G., Gao, J., Gluck, J., Hong, D., Johansen, A., Koh, J., Ploennigs, J., Agarwal, Y., Berges, M., Culler, D. (2018). “Brick: Metadata schema for portable smart building applications. p. 4

Where the paper says it

Mortar showed that a single set of portable analytics applications – fault detection rules, occupancy-based control algorithms, energy benchmarking queries – could be executed across heterogeneous buildings without modification (Balaji et al. 2018), validating Brick’s core design goal.

” Applied Energy. p. 0
Where the paper says it

BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U. Department of Energy prototype models and sensor-placement patterns from real buildings.

Beckett, D. p. 5

Where the paper says it

2016; Fierro et al. 2022), serialized in RDF Turtle (TTL) format (Beckett et al.

, Berners-Lee, T., Prud’hommeaux, E., and Carothers, G. (2014). “RDF 1.1 turtle: Terse RDF triple language. p. 2
Where the paper says it

The Resource Description Framework (RDF) (Cyganiak et al. 2014) provides this representation through a simple but expressive model: every fact is a triple of the form subject–predicate–object.

” W3c recommendation, W3C. p. 2
Where the paper says it

, brick:AHU as a subclass of brick:HVAC Equipment) and the formal semantics of each relationship, while each building’s RDF file encodes its own instance data. SPARQL (Harris and Seaborne 2013) is the W3C standard query language for RDF, enabling queries to pattern-match against building instance triples using Brick class and property definitions to navigate relationships.

p. 2
Where the paper says it

, brick:AHU as a subclass of brick:HVAC Equipment) and the formal semantics of each relationship, while each building’s RDF file encodes its own instance data. SPARQL (Harris and Seaborne 2013) is the W3C standard query language for RDF, enabling queries to pattern-match against building instance triples using Brick class and property definitions to navigate relationships.

p. 2
Where the paper says it

, brick:AHU as a subclass of brick:HVAC Equipment) and the formal semantics of each relationship, while each building’s RDF file encodes its own instance data. SPARQL (Harris and Seaborne 2013) is the W3C standard query language for RDF, enabling queries to pattern-match against building instance triples using Brick class and property definitions to navigate relationships.

p. 2
Where the paper says it

, brick:AHU as a subclass of brick:HVAC Equipment) and the formal semantics of each relationship, while each building’s RDF file encodes its own instance data. SPARQL (Harris and Seaborne 2013) is the W3C standard query language for RDF, enabling queries to pattern-match against building instance triples using Brick class and property definitions to navigate relationships.

Bhattacharya, A., Ploennigs, J., and Culler, D. (2015a). “Analyzing metadata schemas for buildings: The good, the bad, and the ugly. p. 4

Where the paper says it

2018), validating Brick’s core design goal. A subsequent review of 40 building metadata schemas by Pritoni et al.

” Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments (BuildSys). p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Bhattacharya, A. A., Hong, D., Culler, D. E., Ortiz, J., Whitehouse, K., and Wu, E. (2015b). “Automated metadata construction to support portable building applications. p. 0

Where the paper says it

2016; Fierro et al. This structured representation underpins the integration of artificial intelligence into building operations: it enables the semantic querying, inference, and reasoning behind applications that range from natural-language interfaces—which let practitioners retrieve building information without SPARQL expertise—to portable analytics that transfer across buildings.

” Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments (BuildSys).

Brick Schema Community (2024). p. 1

Where the paper says it

Second, sensor placement probabilities are calibrated against real buildings from the Mortar corpus (Fierro et al. 2019; Brick Schema Community 2024), ensuring that the frequency and type of sensors attached to each equipment class reflects observed practice across real instrumented buildings.

“Mortar public Brick building models,. p. 5
Where the paper says it

The existing public building-KG resources (Table 1) each leave a different gap for method development. BuildingQA pairs natural-language questions with SPARQL but covers only four buildings; Mortar publishes 45 real Brick models, but as a fixed, uncontrolled collection with no paired query benchmark; and Open223 offers roughly nineteen illustrative example buildings, likewise without one.

45 anonymized Brick models of real buildings, as originally published with the Mortar paper; individually downloadable; accessed 2026-04-30”. p. 4
Where the paper says it

The value of Brick at scale was demonstrated by the Mortar project (Fierro et al. 2019), which published anonymized Brick models for 45 real buildings from multiple U.

BrickSchema Community (2024). p. 1

Where the paper says it

Second, sensor placement probabilities are calibrated against real buildings from the Mortar corpus (Fierro et al. 2019; Brick Schema Community 2024), ensuring that the frequency and type of sensors attached to each equipment class reflects observed practice across real instrumented buildings.

“Brick schema example building models,. p. 0
Where the paper says it

1 Introduction Building knowledge graphs (KGs) are semantic models that represent the physical components, relationships, and instrumentation of a building as a machine-readable graph. For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al.

Accessed 2026-04-30”. p. 0
Where the paper says it

00038v1 [cs. DB] 2 Sep 2026

buildingSMART International (2013). p. 4

Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

“Industry foundation classes (IFC) – ISO 16739:2013. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

” International standard, ISO. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Crawley, D. p. 4

Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

B., Lawrie, L. K., Winkelmann, F. C., Buhl, W. F., Huang, Y. J., Pedersen, C. O., Strand, R. K., Liesen, R. J., Fisher, D. E., Witte, M. J., and Glazer, J. (2001). “EnergyPlus: Creating a new-generation building energy simulation program. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

” Energy and Buildings. p. 0
Where the paper says it

BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U. Department of Energy prototype models and sensor-placement patterns from real buildings.

p. 0
Where the paper says it

BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U. Department of Energy prototype models and sensor-placement patterns from real buildings.

Cyganiak, R. p. 2

Where the paper says it

1 From Sensor Data to Queryable Knowledge Graphs Integrating heterogeneous building sensor and equipment data across vendors and sites requires a common representation in which entities, their types, and the relationships between them are explicitly encoded. The Resource Description Framework (RDF) (Cyganiak et al.

, Wood, D., and Lanthaler, M. (2014). “RDF 1.1 concepts and abstract syntax. p. 0
Where the paper says it

E-mail: wooyoung@arizona. (Corresponding author) Abstract: Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations, from natural-language access to cross-building analytics, but such KGs are rarely public owing to proprietary, security, and cost barriers.

” W3c recommendation, W3C.

Dubey, M., Banerjee, D., Abdelkawi, A., and Lehmann, J. (2019). “LC-QuAD 2. p. 5

Where the paper says it

3 Text-to-SPARQL for Building Systems Text-to-SPARQL has been studied extensively for general-purpose KGs, with large-scale benchmarks including Spider (Yu et al. 2018), LC-QuAD (Trivedi et al.

0: A large dataset for complex question answering over Wikidata and DBpedia. p. 5
Where the paper says it

therefore constrained by the same data scarcity this work targets: a large, structurally consistent synthetic corpus offers one route to the scale and variety such methods require (Nikolenko 2021). Synthetic data generation is well established in adjacent fields – from synthetic KGs and question-answering corpora to simulated sensor streams – but building informatics has lacked an equivalent resource.

” Proceedings of the 18th International Semantic Web Conference (ISWC), 69–78. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Fierro, G., Pritoni, M. p. 4

Where the paper says it

4 attempted to address this by layering Web Ontology Language (OWL) structure on the tag model, acknowledging that the folksonomy approach was insufficient for programmatic reasoning (Pritoni et al. 2021) – yet retrofitting formal semantics onto a flat tagging system proved architecturally incomplete.

p. 4
Where the paper says it

4 attempted to address this by layering Web Ontology Language (OWL) structure on the tag model, acknowledging that the folksonomy approach was insufficient for programmatic reasoning (Pritoni et al. 2021) – yet retrofitting formal semantics onto a flat tagging system proved architecturally incomplete.

p. 4
Where the paper says it

4 attempted to address this by layering Web Ontology Language (OWL) structure on the tag model, acknowledging that the folksonomy approach was insufficient for programmatic reasoning (Pritoni et al. 2021) – yet retrofitting formal semantics onto a flat tagging system proved architecturally incomplete.

p. 4
Where the paper says it

4 attempted to address this by layering Web Ontology Language (OWL) structure on the tag model, acknowledging that the folksonomy approach was insufficient for programmatic reasoning (Pritoni et al. 2021) – yet retrofitting formal semantics onto a flat tagging system proved architecturally incomplete.

, AbdelBaky, M., Lengyel, D., Leyden, J., Prakash, A., Gupta, P., Raftery, P., Peffer, T., Thomson, G., and Culler, D. E. (2019). “Mortar: An open testbed for portable building analytics. p. 5
Where the paper says it

It ships with a reusable 75-query QAR benchmark that runs across all 120 buildings, and, because the generator is released, it is not a fixed corpus but an open, extensible resource: users can create additional buildings—new archetypes, vintages, sizes, and naming or predicate conventions—at any scale. To the author’s knowledge it is the first large-scale synthetic building-KG dataset released with an accompanying evaluation protocol, giving research groups an identical, citable, and extensible substrate on which to develop and reproducibly evaluate methods—the shared infrastructure that portable building-analytics research currently lacks.

” ACM Transactions on Sensor Networks. p. 0
Where the paper says it

BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U. Department of Energy prototype models and sensor-placement patterns from real buildings.

Fierro, G., Pritoni, M., AbdelBaky, M., Lentzos, D., Prakash, A., Thomson, G., and Culler, D. E. (2022). “Brick schema: Building a unified metadata schema for buildings. p. 3

Where the paper says it

3 Related Work 3. 1 Building Metadata Standards and the Brick Schema Early standardization efforts addressed communication interoperability (BACnet (ASHRAE 1995)) and tag-based operational semantics (Project Haystack (Project Haystack Association 2014)), but lacked typed, named relationships between entities, making SPARQL-based querying and ontological inference impossible (Bhattacharya et al.

” Energy and Buildings.

Gao, J., Ploennigs, J., and Berges, M. (2015). “A data-driven meta-data inference framework for building automation systems. p. 0

Where the paper says it

This structured representation underpins the integration of artificial intelligence into building operations: it enables the semantic querying, inference, and reasoning behind applications that range from natural-language interfaces—which let practitioners retrieve building information without SPARQL expertise—to portable analytics that transfer across buildings. As the building industry increasingly embraces semantic models, building KGs are becoming a critical data infrastructure, and their public availability is essential for research progress.

” Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments (BuildSys), 1–10. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Gemma Team, Google DeepMind (2026). p. 2

Where the paper says it

Downstream validation via a text-to-SPARQL evaluation using Gemma 4 (26B) (Gemma Team, Google DeepMind 2026) on 12 held-out buildings, demonstrating that few-shot prompting with cross-building BuildGraph text-to-SPARQL examples achieves 27. 3% Row-Matching F1 (the harmonic mean of precision and recall over the set of result rows a query returns— measuring whether the query returns the correct answer independent of SPARQL surface form, and defined in Section 6.

“Gemma 4 technical report. p. 0
Where the paper says it

94), evidence of realistic instrumentation where measurable. A downstream text-to-SPARQL experiment with Gemma 4 (26B) reaches 27.

” Report No. arXiv:2607. p. 0
Where the paper says it

As the building industry increasingly embraces semantic models, building KGs are becoming a critical data infrastructure, and their public availability is essential for research progress. 1 arXiv:2610.

02770, Google DeepMind. p. 2
Where the paper says it

Downstream validation via a text-to-SPARQL evaluation using Gemma 4 (26B) (Gemma Team, Google DeepMind 2026) on 12 held-out buildings, demonstrating that few-shot prompting with cross-building BuildGraph text-to-SPARQL examples achieves 27. 3% Row-Matching F1 (the harmonic mean of precision and recall over the set of result rows a query returns— measuring whether the query returns the correct answer independent of SPARQL surface form, and defined in Section 6.

Hammar, K., Wallin, E. O., Karlberg, P., and Halleberg, D. (2019). “The RealEstateCore ontology. p. 4

Where the paper says it

Complementary standards have since emerged – ASHRAE 223P (ASHRAE 2023) for connection-point topology, the Building Topology Ontology (BOT) (Rasmussen et al. 2021) for spatial decomposition within the W3C Linked Building Data community, and RealEstateCore (Hammar et al.

” Proceedings of the 18th International Semantic Web Conference (ISWC), Vol. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

11779 of Lecture Notes in Computer Science, 130–145.

Harris, S. and Seaborne, A. p. 2

Where the paper says it

, brick:AHU as a subclass of brick:HVAC Equipment) and the formal semantics of each relationship, while each building’s RDF file encodes its own instance data. SPARQL (Harris and Seaborne 2013) is the W3C standard query language for RDF, enabling queries to pattern-match against building instance triples using Brick class and property definitions to navigate relationships.

(2013). “SPARQL 1. p. 0
Where the paper says it

It spans eight commercial building types across three ASHRAE energy-code vintages, with five realizations per archetype varying URI naming, sensor-attachment predicates, and topology. A 75-query SPARQL benchmark confirms structural completeness: BuildGraph reaches 91.

1 query language. p. 1
Where the paper says it

Real-world building KGs are rarely publicly available due to proprietary restrictions, security concerns, and lack of instrumented buildings, limiting supply to a small number of anonymized KG models released by national laboratories and universities. This scarcity is particularly acute for text-to-SPARQL research – systems that translate natural language questions into executable SPARQL Protocol and RDF Query Language (SPARQL) queries, emerging as a critical interface for facility managers and energy engineers to access building knowledge without SPARQL expertise – because such systems require diverse, structurally complete KGs as few-shot examples, training data, and evaluation benchmarks.

” W3c recommendation, W3C.

Knublauch, H. p. 2

Where the paper says it

Query Answerability Structural completeness cannot be measured by schema validation alone. The Shapes Constraint Language (SHACL) (Knublauch and Kontokostas 2017) is the W3C standard for validating whether an RDF graph conforms to the property definitions and cardinality constraints declared in the T-box: for example, that every brick:TemperatureSensor has the required brick:isPointOf relationships to entities of type brick:Equipment (brick:isPointOf is the sensor-to-equipment direction; its inverse, brick:hasPoint, attaches sensors from the equipment side).

and Kontokostas, D. p. 2
Where the paper says it

Query Answerability Structural completeness cannot be measured by schema validation alone. The Shapes Constraint Language (SHACL) (Knublauch and Kontokostas 2017) is the W3C standard for validating whether an RDF graph conforms to the property definitions and cardinality constraints declared in the T-box: for example, that every brick:TemperatureSensor has the required brick:isPointOf relationships to entities of type brick:Equipment (brick:isPointOf is the sensor-to-equipment direction; its inverse, brick:hasPoint, attaches sensors from the equipment side).

(2017). “Shapes constraint language (SHACL). p. 2
Where the paper says it

Query Answerability Structural completeness cannot be measured by schema validation alone. The Shapes Constraint Language (SHACL) (Knublauch and Kontokostas 2017) is the W3C standard for validating whether an RDF graph conforms to the property definitions and cardinality constraints declared in the T-box: for example, that every brick:TemperatureSensor has the required brick:isPointOf relationships to entities of type brick:Equipment (brick:isPointOf is the sensor-to-equipment direction; its inverse, brick:hasPoint, attaches sensors from the equipment side).

” W3c recommendation, W3C.

Koh, J., Balaji, B. p. 0

Where the paper says it

1 Introduction Building knowledge graphs (KGs) are semantic models that represent the physical components, relationships, and instrumentation of a building as a machine-readable graph. For example, a building KG encodes which air handling units (AHUs) serve which heating, ventilation, and air conditioning (HVAC) zones, which sensors are attached to which equipment, and how chilled water and hot water flow through the plant – expressed in a formal ontological vocabulary such as the Brick Schema (Balaji et al.

, Sengupta, D., McAuley, J., Agarwal, Y., and Gupta, R. (2017). “Scrabble: Converting unstructured metadata into Brick for many buildings. p. 0
Where the paper says it

Author keywords: building knowledge graph; synthetic dataset; Brick Schema; SPARQL; intelligent buildings; text-toSPARQL Practical Applications BuildGraph gives building practitioners a free, ready-made set of 120 realistic building knowledge graphs and a 75-question query benchmark that would otherwise require proprietary, hard-to-obtain building data. Facility managers and controls engineers can test fault-detection and energy-analytics queries across many building types and vintages before applying them to their own sites; software developers can benchmark tools that translate plain-English questions into building-database queries; and digital-twin developers can prototype and validate semantic applications without first assembling a real building’s knowledge graph.

” Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys). p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Koh, J., Hong, D., Gupta, R., Whitehouse, K., Wang, H., and Agarwal, Y. (2018). “Plaster: An integration, benchmark, and development framework for metadata normalization methods. p. 4

Where the paper says it

A parallel line of work infers semantic metadata from existing building automation system (BAS) deployments via signal processing and active learning (Gao et al. 2015), semi-automated metadata normalization (Koh et al.

” Proceedings of the 5th ACM International Conference on Systems for Energy-Efficient Buildings, Cities and Transportation (BuildSys). p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Kovriguina, L. p. 5

Where the paper says it

2017; Dubey et al. 2019), and recent LLM-based approaches achieving high accuracy on open-domain graphs (Kovriguina et al.

, Teucher, R., Radyush, D., and Mouromtsev, D. (2024). “LLM-based SPARQL query generation from natural language over federated knowledge graphs”. p. 1
Where the paper says it

Real-world building KGs are rarely publicly available due to proprietary restrictions, security concerns, and lack of instrumented buildings, limiting supply to a small number of anonymized KG models released by national laboratories and universities. This scarcity is particularly acute for text-to-SPARQL research – systems that translate natural language questions into executable SPARQL Protocol and RDF Query Language (SPARQL) queries, emerging as a critical interface for facility managers and energy engineers to access building knowledge without SPARQL expertise – because such systems require diverse, structurally complete KGs as few-shot examples, training data, and evaluation benchmarks.

Lan, Y., He, G., Jiang, J., Jiang, J., Zhao, W. X., and Wen, J.-R. (2021). “A survey on complex knowledge base question answering: Methods, challenges and solutions. p. 5

Where the paper says it

therefore constrained by the same data scarcity this work targets: a large, structurally consistent synthetic corpus offers one route to the scale and variety such methods require (Nikolenko 2021). Synthetic data generation is well established in adjacent fields – from synthetic KGs and question-answering corpora to simulated sensor streams – but building informatics has lacked an equivalent resource.

” Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI). p. 0
Where the paper says it

E-mail: wooyoung@arizona. (Corresponding author) Abstract: Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations, from natural-language access to cross-building analytics, but such KGs are rarely public owing to proprietary, security, and cost barriers.

Mulayim, O. p. 1

Where the paper says it

This scarcity is particularly acute for text-to-SPARQL research – systems that translate natural language questions into executable SPARQL Protocol and RDF Query Language (SPARQL) queries, emerging as a critical interface for facility managers and energy engineers to access building knowledge without SPARQL expertise – because such systems require diverse, structurally complete KGs as few-shot examples, training data, and evaluation benchmarks. The only existing benchmark, BuildingQA (Mulayim et al.

B., Anwar, A., Saka, M., Paul, L., Prakash, A. K., Fierro, G., Pritoni, M., and Berges, M. (2025). “BuildingQA: ´A benchmark for natural language question answering over building knowledge graphs. p. 4
Where the paper says it

The BuildingQA benchmark (Mulayim et al. 2025) is the only resource providing paired (natural language, SPARQL) question-answer data, yet covers just 4 buildings.

” Proceedings of the 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys). p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Nikolenko, S. p. 1

Where the paper says it

Even if more real building KGs are released, they will likely be limited in number, biased toward certain building types or instrumentation patterns, and encumbered by proprietary restrictions that limit their utility for research and evaluation. Synthetic generation of building KGs is a promising strategy to address this data scarcity problem and provide a diverse, scalable, and publicly accessible dataset for research (Nikolenko 2021).

I. (2021). Synthetic Data for Deep Learning, Vol. p. 1
Where the paper says it

2025), covers four buildings annotated in a mixture of Brick, ASHRAE 223P, and mixed-schema formats, providing insufficient scale and structural diversity for systematic evaluation or cross-building generalization studies. This data scarcity problem is likely to persist for the foreseeable future due to a steep learning curve for practitioners to learn, create, and maintain building KGs (Bhattacharya et al.

174 of Springer Optimization and Its Applications. p. 0
Where the paper says it

com/humanbuildingsynergy/BuildGraph. Author keywords: building knowledge graph; synthetic dataset; Brick Schema; SPARQL; intelligent buildings; text-toSPARQL Practical Applications BuildGraph gives building practitioners a free, ready-made set of 120 realistic building knowledge graphs and a 75-question query benchmark that would otherwise require proprietary, hard-to-obtain building data.

Open223 Project (2023). p. 4

Where the paper says it

2019; Brick Schema Community 2024) is the largest of these resources, offering publicly downloadable Brick models of 45 real buildings, but as a fixed collection of deployed real models released without a paired query benchmark. The Open223 project (Open223 Project 2023) provides approximately 19 unique 223P example buildings from national laboratories, freely available but a small, illustrative set that likewise ships no query benchmark.

“Open223 example building models, ”. p. 5
Where the paper says it

The existing public building-KG resources (Table 1) each leave a different gap for method development. BuildingQA pairs natural-language questions with SPARQL but covers only four buildings; Mortar publishes 45 real Brick models, but as a fixed, uncontrolled collection with no paired query benchmark; and Open223 offers roughly nineteen illustrative example buildings, likewise without one.

Pritoni, M., Paine, D., Fierro, G., Mosiman, C., Poplawski, M., Saha, A., Bender, J., and Granderson, J. (2021). “Metadata schemas and ontologies for building energy applications: A critical review and use case analysis. p. 4

Where the paper says it

2018), validating Brick’s core design goal. A subsequent review of 40 building metadata schemas by Pritoni et al.

” Energies.

Project Haystack Association (2014). p. 3

Where the paper says it

3 Related Work 3. 1 Building Metadata Standards and the Brick Schema Early standardization efforts addressed communication interoperability (BACnet (ASHRAE 1995)) and tag-based operational semantics (Project Haystack (Project Haystack Association 2014)), but lacked typed, named relationships between entities, making SPARQL-based querying and ontological inference impossible (Bhattacharya et al.

“Project haystack: Semantic data models and web services for smart devices and equipment, ”. p. 3
Where the paper says it

3 Related Work 3. 1 Building Metadata Standards and the Brick Schema Early standardization efforts addressed communication interoperability (BACnet (ASHRAE 1995)) and tag-based operational semantics (Project Haystack (Project Haystack Association 2014)), but lacked typed, named relationships between entities, making SPARQL-based querying and ontological inference impossible (Bhattacharya et al.

Rasmussen, M. p. 4

Where the paper says it

(2021) confirmed that Brick offers the strongest foundation for semantic querying among existing schemas. Complementary standards have since emerged – ASHRAE 223P (ASHRAE 2023) for connection-point topology, the Building Topology Ontology (BOT) (Rasmussen et al.

H., Lefranc¸ois, M., Schneider, G. F., and Pauwels, P. (2021). “BOT: The building topology ontology of the W3C linked building data group. p. 4
Where the paper says it

Complementary standards have since emerged – ASHRAE 223P (ASHRAE 2023) for connection-point topology, the Building Topology Ontology (BOT) (Rasmussen et al. 2021) for spatial decomposition within the W3C Linked Building Data community, and RealEstateCore (Hammar et al.

” Semantic Web. p. 4
Where the paper says it

4 attempted to address this by layering Web Ontology Language (OWL) structure on the tag model, acknowledging that the folksonomy approach was insufficient for programmatic reasoning (Pritoni et al. 2021) – yet retrofitting formal semantics onto a flat tagging system proved architecturally incomplete.

p. 4
Where the paper says it

4 attempted to address this by layering Web Ontology Language (OWL) structure on the tag model, acknowledging that the folksonomy approach was insufficient for programmatic reasoning (Pritoni et al. 2021) – yet retrofitting formal semantics onto a flat tagging system proved architecturally incomplete.

RDFLib Contributors (2022). p. 2

Where the paper says it

3 (Fierro et al. 2022) introduced SHACL shapes that enable automated conformance checking for any Brick model.

“pySHACL: A python validator for SHACL, ”. p. 8
Where the paper says it

Approximately 85% of sensors in each building carry a timeseries reference, reflecting realistic deployment scenarios where some sensors may be offline or unregistered. 5 Methodology and Data Collection The BuildGraph generation pipeline proceeds through five stages (Figure 3): (1) archetype definition – DOE prototype parameters are encoded as Python dataclasses; (2) specification construction – each archetype is instantiated into a BuildingSpec intermediate representation with sampled structural parameters; (3) graph building – the Brick builder consumes the spec and produces an RDF graph with full topology, sensor attachments, and metadata; (4) serialization – the graph is written to RDF Turtle; and (5) validation – generation-time structural checks and the full SPARQL benchmark confirm structural completeness (Section 6).

Trivedi, P. p. 5

Where the paper says it

3 Text-to-SPARQL for Building Systems Text-to-SPARQL has been studied extensively for general-purpose KGs, with large-scale benchmarks including Spider (Yu et al. 2018), LC-QuAD (Trivedi et al.

, Maheshwari, G., Dubey, M. p. 5
Where the paper says it

2018), LC-QuAD (Trivedi et al. 2017; Dubey et al.

, and Lehmann, J. (2017). “LC-QuAD: A corpus for complex question answering over knowledge graphs. p. 5
Where the paper says it

therefore constrained by the same data scarcity this work targets: a large, structurally consistent synthetic corpus offers one route to the scale and variety such methods require (Nikolenko 2021). Synthetic data generation is well established in adjacent fields – from synthetic KGs and question-answering corpora to simulated sensor streams – but building informatics has lacked an equivalent resource.

” Proceedings of the 16th International Semantic Web Conference (ISWC), 210–218. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

U.S. Department of Energy (2024). p. 1

Where the paper says it

Department of Energy (DOE) Commercial Prototype Building Models (U. Department of Energy 2024), published specifications that define the HVAC system type, equipment counts, terminal unit configuration, and zone structure for eight representative commercial building types spanning three energy code vintages.

“Commercial prototype building models. p. 0
Where the paper says it

Department of Energy prototype models and sensor-placement patterns from real buildings. It spans eight commercial building types across three ASHRAE energy-code vintages, with five realizations per archetype varying URI naming, sensor-attachment predicates, and topology.

” Report no., U.S. Department of Energy, Office of Energy Efficiency and Renewable Energy, Building Technologies Office,. p. 1
Where the paper says it

The primary contributions of this paper are: 1. A publicly accessible dataset of 120 synthetic building KGs in the Brick Schema ontology, spanning eight commercial building types (small office, medium office, large office, primary school, hospital, hotel, strip mall, and outpatient healthcare), three ASHRAE energy code vintages, and various HVAC configurations; archetype coverage validated against the Commercial Buildings Energy Consumption Survey (CBECS) 2018 data – a national sample survey that details the stock of U.

U.S. Energy Information Administration (2020). p. 4

Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

“2018 commercial buildings energy consumption survey (CBECS): Public use microdata. p. 1
Where the paper says it

The primary contributions of this paper are: 1. A publicly accessible dataset of 120 synthetic building KGs in the Brick Schema ontology, spanning eight commercial building types (small office, medium office, large office, primary school, hospital, hotel, strip mall, and outpatient healthcare), three ASHRAE energy code vintages, and various HVAC configurations; archetype coverage validated against the Commercial Buildings Energy Consumption Survey (CBECS) 2018 data – a national sample survey that details the stock of U.

” Report no., U.S. Energy Information Administration,. p. 4
Where the paper says it

2 Synthetic Building Data Generation Prior work on generating building models falls into two categories distinct from semantic KG generation. Building information modeling (BIM) tools produce models in the Industry Foundation Classes (IFC) format (buildingSMART International 2013) capturing geometry and spatial hierarchy but not sensor attachments or typed semantic relationships; energy simulation tools such as EnergyPlus (Crawley et al.

Wang, Z., Sacks, R., and Yeung, T. (2022). “Exploring graph neural networks for semantic enrichment: Room type classification. p. 4

Where the paper says it

2018) – and all methods require existing building data as input rather than generating KGs from scratch. Moreover, these learning-based approaches – including graph-neural models for building semantic enrichment (Wang et al.

” Automation in Construction. p. 4
Where the paper says it

2001) produce thermodynamic outputs rather than RDF graphs. A parallel line of work infers semantic metadata from existing building automation system (BAS) deployments via signal processing and active learning (Gao et al.

Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., Ma, J., Li, I., Yao, Q., Roman, S., Zhang. Z. and Radev. D. (2018). “Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. p. 5

Where the paper says it

Synthetic data generation is well established in adjacent fields – from synthetic KGs and question-answering corpora to simulated sensor streams – but building informatics has lacked an equivalent resource. 3 Text-to-SPARQL for Building Systems Text-to-SPARQL has been studied extensively for general-purpose KGs, with large-scale benchmarks including Spider (Yu et al.

” Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3911–3921. p. 4
Where the paper says it

2015b; Koh et al. 2018) – and all methods require existing building data as input rather than generating KGs from scratch.

Zaveri, A., Rula, A., Maurino, A., Pietrobon, R., Lehmann, J., and Auer, S. (2016). “Quality assessment for linked data: A survey. p. 3

Where the paper says it

The appropriate measure is therefore query-centric: the Query Answerability Rate (QAR), defined as the fraction of applicable, semantically meaningful SPARQL queries that return at least one result row when executed against a building KG. A high QAR confirms that the A-box is structurally rich enough to support the full range of queries a downstream application would issue; a low QAR reveals coverage gaps – analogous to the query-based completeness dimension in linked data quality literature (Zaveri et al.

” Semantic Web.

Table 7

Table 7 reports SPARQL benchmark query categories.

Table 8 reports QAR ablation by pipeline stage. p. 8

Where the paper says it

Approximately 85% of sensors in each building carry a timeseries reference, reflecting realistic deployment scenarios where some sensors may be offline or unregistered. 5 Methodology and Data Collection The BuildGraph generation pipeline proceeds through five stages (Figure 3): (1) archetype definition – DOE prototype parameters are encoded as Python dataclasses; (2) specification construction – each archetype is instantiated into a BuildingSpec intermediate representation with sampled structural parameters; (3) graph building – the Brick builder consumes the spec and produces an RDF graph with full topology, sensor attachments, and metadata; (4) serialization – the graph is written to RDF Turtle; and (5) validation – generation-time structural checks and the full SPARQL benchmark confirm structural completeness (Section 6).

Table 9 reports CBECS coverage by BuildGraph archetype group. p. 6

Where the paper says it

20015123 Table 3. BuildGraph archetype coverage.

Table 10 reports Sensor attachment rate comparison. p. 0

Where the paper says it

Department of Energy prototype models and sensor-placement patterns from real buildings. It spans eight commercial building types across three ASHRAE energy-code vintages, with five realizations per archetype varying URI naming, sensor-attachment predicates, and topology.

Table 11 reports Sensor-composition fidelity against real Mortar buildings. p. 1

Where the paper says it

commercial building simulation research. Second, sensor placement probabilities are calibrated against real buildings from the Mortar corpus (Fierro et al.

Table 12 reports QAR by tier and query category for the full released dataset. p. 5

Where the paper says it

BuildGraph is built to fill this gap: it spans a balanced 8 × 3 × 5 factorial of eight building types, three vintages, and five independent seeds (120 buildings), each released with its full provenance (archetype, vintage, seed) and exact equipment and sensor inventory, and with naming scheme, attachment predicate, and topology varied across seeds by design—the same heterogeneity real corpora exhibit, but here labeled and reproducible. It ships with a reusable 75-query QAR benchmark that runs across all 120 buildings, and, because the generator is released, it is not a fixed corpus but an open, extensible resource: users can create additional buildings—new archetypes, vintages, sizes, and naming or predicate conventions—at any scale.

Table 13 reports QAR comparison: 59-building Brick corpus and BuildGraph. p. 5

Where the paper says it

BuildGraph is built to fill this gap: it spans a balanced 8 × 3 × 5 factorial of eight building types, three vintages, and five independent seeds (120 buildings), each released with its full provenance (archetype, vintage, seed) and exact equipment and sensor inventory, and with naming scheme, attachment predicate, and topology varied across seeds by design—the same heterogeneity real corpora exhibit, but here labeled and reproducible. It ships with a reusable 75-query QAR benchmark that runs across all 120 buildings, and, because the generator is released, it is not a fixed corpus but an open, extensible resource: users can create additional buildings—new archetypes, vintages, sizes, and naming or predicate conventions—at any scale.

Table 14 reports QAR ablation by pipeline stage. p. 8

Where the paper says it

Approximately 85% of sensors in each building carry a timeseries reference, reflecting realistic deployment scenarios where some sensors may be offline or unregistered. 5 Methodology and Data Collection The BuildGraph generation pipeline proceeds through five stages (Figure 3): (1) archetype definition – DOE prototype parameters are encoded as Python dataclasses; (2) specification construction – each archetype is instantiated into a BuildingSpec intermediate representation with sampled structural parameters; (3) graph building – the Brick builder consumes the spec and produces an RDF graph with full topology, sensor attachments, and metadata; (4) serialization – the graph is written to RDF Turtle; and (5) validation – generation-time structural checks and the full SPARQL benchmark confirm structural completeness (Section 6).

Table 15 reports Text-to-SPARQL Row-Matching F1 by query category. p. 2

Where the paper says it

Downstream validation via a text-to-SPARQL evaluation using Gemma 4 (26B) (Gemma Team, Google DeepMind 2026) on 12 held-out buildings, demonstrating that few-shot prompting with cross-building BuildGraph text-to-SPARQL examples achieves 27. 3% Row-Matching F1 (the harmonic mean of precision and recall over the set of result rows a query returns— measuring whether the query returns the correct answer independent of SPARQL surface form, and defined in Section 6.

Overall QAR

Overall QAR 87.5% 96.9% 92.9% 96.5% 91.5%.

Category Overall QAR 87. p. 1

Where the paper says it

First, a 75-query SPARQL benchmark measures the Query Answerability Rate (QAR) – the fraction of applicable queries returning at least one result row – across five query categories and four building complexity tiers. BuildGraph achieves an overall QAR of 91.

5% 91.7% 92.9% 96.5%.

Category T1 T2 T3 T4 Overall QAR 87. p. 1

Where the paper says it

First, a 75-query SPARQL benchmark measures the Query Answerability Rate (QAR) – the fraction of applicable queries returning at least one result row – across five query categories and four building complexity tiers. BuildGraph achieves an overall QAR of 91.

5% 91.7% 92.9% 96.5%].

Category Zero-shot QAR 9. p. 0

Where the paper says it

3% Row-Matching F1 (+17. 5 pp over zero-shot) on 12 held-out buildings.

8% Category 3-shot QAR ceiling. p. 7
Where the paper says it

3 Knowledge Graph Content Entity Classes The dataset uses 83 distinct Brick classes. Table 6 organizes the equipment entity classes by functional category.

Overall QAR 9. p. 1

Where the paper says it

First, a 75-query SPARQL benchmark measures the Query Answerability Rate (QAR) – the fraction of applicable queries returning at least one result row – across five query categories and four building complexity tiers. BuildGraph achieves an overall QAR of 91.

8% Category T1 T2 T3 T4 Overall QAR 97. p. 1
Where the paper says it

First, a 75-query SPARQL benchmark measures the Query Answerability Rate (QAR) – the fraction of applicable queries returning at least one result row – across five query categories and four building complexity tiers. BuildGraph achieves an overall QAR of 91.

1%.

Category 5 Zero-shot QAR 0. p. 0

Where the paper says it

3% Row-Matching F1 (+17. 5 pp over zero-shot) on 12 held-out buildings.

0% Category Multi-hop / Complex QAR ceiling. p. 2
Where the paper says it

Nodes (ovals) are building entities; labeled arrows are typed semantic relationships. Following the two brick:feeds arrows in sequence – from AHU-1 through VAV-3 to Zone-B – is an example of a multi-hop query.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Data Scarcity Mitigation via Synthetic Generation

The system can be improved by using BuildGraph as a testbed for portable analytics and natural-language interfaces to bridge the gap caused by proprietary data scarcity. This allows facility managers and digital-twin developers to test fault-detection and energy-analytics queries across many building types and vintages before applying them to their own sites.

  1. Enhanced Text-to-SPARQL Capability

The AI system can be improved by using BuildGraph examples in a few-shot setting, as demonstrated by Gemma 4 achieving 27.3% Row-Matching F1 (+17.5 pp over zero-shot) on held-out buildings. This capability allows the system to translate plain-English questions into building-database queries with improved accuracy than zero-shot methods alone.

  1. Structural Completeness Guarantee

The system can be improved by incorporating generation invariants from the BuildGraph pipeline, which includes checks like Every floor contains at least one zone (brick:hasPart) and Every AHU reaches at least one brick:HVAC Zone via brick:feeds+. This ensures that the data used for downstream tasks is structurally complete and reduces failures caused by missing relationships.

  1. Archetype Agnostic Analytics

The system can be improved by leveraging the dataset's cross-building nature, allowing a query written for one building to be executed across the full corpus without modification. This enables systematic evaluation of how well an analytics application generalizes across diverse building types and vintages.

  1. Domain Model Development Foundation

The system can be improved by using the structured metadata, such as triples like meta:buildingType records the archetype identifier combining type and vintage, to support any model that reasons about HVAC systems, equipment relationships, or sensor coverage. This provides a foundation for developing domain-specific language and reasoning models.

Abstract

Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations, from natural-language access to cross-building analytics, but such KGs are rarely public owing to proprietary, security, and cost barriers. BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U.S. Department of Energy prototype models and sensor-placement patterns from real buildings. It spans eight commercial building types across three ASHRAE energy-code vintages, with five realizations per archetype varying URI naming, sensor-attachment predicates, and topology. A 75-query SPARQL benchmark confirms structural completeness: BuildGraph reaches 91.5% Query Answerability Rate versus 35.8% for 59 real-world Brick files. Independently, it reproduces real buildings' sensor-type proportions on their shared vocabulary (cosine 0.86-0.94), evidence of realistic instrumentation where measurable. A downstream text-to-SPARQL experiment with Gemma 4 (26B) reaches 27.3% Row-Matching F1 (+17.5 pp over zero-shot) on 12 held-out buildings. BuildGraph gives facility managers and digital-twin developers a testbed for portable analytics and natural-language interfaces, and its dataset, generator, and benchmark are openly available at https://github.com/humanbuildingsynergy/BuildGraph.

Sources

Related papers