DEVELOPING VERIFICATION SYSTEMS FOR BUILDING INFORMATION MODELS OF HERITAGE BUILDINGS WITH HETEROGENEOUS DATASETS
Bibliographic record
Abstract
Abstract. The digitization and abstraction of existing buildings into building information models requires the translation of heterogeneous datasets that may include CAD, technical reports, historic texts, archival drawings, terrestrial laser scanning, and photogrammetry into model elements. In this paper, we discuss a project undertaken by the Carleton Immersive Media Studio (CIMS) that explored the synthesis of heterogeneous datasets for the development of a building information model (BIM) for one of Canada’s most significant heritage assets – the Centre Block of the Parliament Hill National Historic Site. The scope of the project included the development of an as-found model of the century-old, six-story building in anticipation of specific model uses for an extensive rehabilitation program. The as-found Centre Block model was developed in Revit using primarily point cloud data from terrestrial laser scanning. The data was captured by CIMS in partnership with Heritage Conservation Services (HCS), Public Services and Procurement Canada (PSPC), using a Leica C10 and P40 (exterior and large interior spaces) and a Faro Focus (small to mid-sized interior spaces). Secondary sources such as archival drawings, photographs, and technical reports were referenced in cases where point cloud data was not available. As a result of working with heterogeneous data sets, a verification system was introduced in order to communicate to model users/viewers the source of information for each building element within the model.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.012 | 0.041 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".