A wiki based portal to the biodiversity knowledge graph.
Bibliographic record
Abstract
We will present our botanical knowledge portal, which uses Semantic Mediawiki (SMW) to store and display structured data extracted from the Flora of North America (FNA), and to integrate this data with an open biodiversity knowledge graph. SMW provides users with a familiar interface for browsing, filtering, and querying semantic data without the need to learn (or even be aware of) semantic web technologies such as RDF (the Resource Description Framework) and SPARQL (the SPARQL Protocol and RDF Query Language). In the case of the portal, this allows users to query taxonomic treatments based on: the characters and character states of taxa, including phenology and habitat; invasiveness and conservation status; occurrences; and any other information contained in the knowledge graph. Data from other sources is integrated via an RDF triplestore, and the provenance of this data is managed by maintaining distinct named graphs for each source. We are planning to provide the ability to edit treatments, and to find and annotate associated resources We will describe our procedures for extracting knowledge from FNA and importing it into SMW, including a methodology we developed for classifying habitat descriptions (which are notoriously unstructured) along dimensions that are useful when querying and filtering, such as wet/dry; open/closed; sloped/flat; etc. We will also describe the structure of our biodiversity knowledge graph, demonstrate how human and software agents (such as the portal) can interact with it, and invite collaboration in its continued construction.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.007 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.007 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.027 | 0.015 |
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".