Identification keys and descriptive data

Interactive and multi-access identification keys, structured descriptive data (e.g. SDD) and character matrices, including hybrids with AI.

9 talks & discussions

Across rooms and sessions

Explore the conversation.

talk · 22 Sept · 11:39–⁠11:51 · SAL A

AI-assisted digitisation of printed identification keys: from book to structured data in minutes

An agentic LLM pipeline can turn printed keys and descriptions into a structured draft identification key for tens of dollars, shifting experts from transcribers to reviewers.

Wouter Koch ↗

talk · 22 Sept · 15:15–⁠15:30 · SAL C

Experience of collaborative management of the World Auchenorrhyncha Database in TaxonWorks

TaxonWorks turned a personal taxonomic database into a collaborative, well-connected resource feeding Catalogue of Life, GBIF and iNaturalist.

Dmitry Dmitriev ↗

talk · 24 Sept · 12:15–⁠12:27 · SAL B

Artificial Intelligence Amplifies Paleontology's Reproducibility Problem

AI can make uncertain paleontological data look clean and authoritative, so AI-ready data must also be verifiable back to evidence and interpretation.

Brooke Long-Fox ↗

talk · 24 Sept · 15:00–⁠15:15 · SAL C

LifeGate: Extending a Global Visual PhyloMap into a Structured Biodiversity Knowledge System

LifeGate's visual map of all described species will become an open, connected knowledge system with trait-based faceted search built from AI-assisted literature extraction.

Martin Freiberg, Birgitta König-Ries ↗

talk · 25 Sept · 08:30–⁠08:50 · SAL B

Ctrl+Alt+SDD: A Historical Review Toward a Standard Reboot

SDD is well-documented but dormant and imperfectly interoperable, and the Xper4 rebuild is an opportunity to reopen and modernise it together with the community.

Elie Saliba, Adeline Kerner ↗

talk · 25 Sept · 08:50–⁠09:04 · SAL B

Structured identification keys complementing AI: closing the corpus bottleneck with AI-assisted digitisation

AI and identification keys are complementary, and LLM-assisted digitisation of printed literature now makes it feasible to build structured keys at scale for expert review.

Wouter Koch ↗

talk · 25 Sept · 09:04–⁠09:18 · SAL B

Beyond traditional identification keys: hybrid deep learning and Xper3 keys for insect identification

Deep-learning pre-filtering of an interactive key keeps the key's explainability while greatly shortening identification paths.

Agathe Puissant ↗

talk · 25 Sept · 09:18–⁠09:32 · SAL B

Needs for data standards about sharing and analyzing identification tools usage

SDD should be extended so identification sessions (context, uncertain responses, backtracking and AI outputs) become open, shareable data, not just the keys.

Régine Vignes Lebbe ↗

talk · 25 Sept · 11:42–⁠11:54 · SAL A

Validating LLM-Extracted Biodiversity Data to Preserve Scientific Meaning

LLM extraction speeds up morphological matrix curation enormously, but errors, including fabrications, appear in almost every output, so expert validation is essential.

Brooke Long-Fox ↗