A Public Dataset of Annotated Orcinus orca Acoustic Signals for Detection and Ecotype Classification
Bibliographic record
Abstract
Killer whales (Orcinus orca) exhibit significant ecological and genetic diversity, with three primary sympatric populations in the Northeast Pacific: Resident, Bigg's (Transient), and Offshore. Each population is characterized by distinct foraging habits, social structures, and vocal repertoires, which complicate accurate monitoring and conservation efforts. This dataset, compiled from diverse sources, provides a comprehensive resource for the detection and classification of killer whale vocalizations. The dataset includes annotated acoustic recordings spanning 11 years from various locations in Alaska, British Columbia, and Washington, collected using multiple hydrophone systems. It addresses the challenge of differentiating killer whale calls from other marine species and environmental noise, including specific instances of confounding signals that may help enhance model robustness. Detailed annotations capture a diverse suite of vocalizations and their associated metadata, facilitating the development of advanced machine learning models for ecological monitoring. This curated dataset aims to improve the accuracy of killer whale detection algorithms, support conservation efforts, and advance our understanding of killer whale acoustic communication across different populations.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 0.012 |
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".