AVES-bio
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-17.)
AVES-bio has 40 facts recorded in Dontopedia across 1 reference, with 7 live disagreements.
Mostly:has auc score on task(9), tp:verdict reason(6), rdf:type(3)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (3)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
comparesPerformanceOfCompares Performance of(2)
- Model Comparison
ex:model-comparison - Study Comparison
ex:study-comparison
comparesWithCompares With(1)
- Perch 2 0
ex:perch-2-0
Other facts (39)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Has Auc Score on Task | 0.88 | [1] |
| Has Auc Score on Task | 0.916 | [1] |
| Has Auc Score on Task | 0.825 | [1] |
| Has Auc Score on Task | 0.879 | [1] |
| Has Auc Score on Task | 0.965 | [1] |
| Has Auc Score on Task | 0.971 | [1] |
| Has Auc Score on Task | 0.893 | [1] |
| Has Auc Score on Task | 0.972 | [1] |
| Has Auc Score on Task | 0.979 | [1] |
| Tp:verdict Reason | The claimed model property matches the parsed model-property table in the staged manuscript. | [1] |
| Tp:verdict Reason | The reported AUC value is present in Table 2, but it was not recomputed from audio, labels, embeddings, and the few-shot sampling protocol. | [1] |
| Tp:verdict Reason | The claim is source-grounded in the manuscript, but the artifact-availability requirement is blocked by missing exact code/model-card/data URLs. | [1] |
| Tp:verdict Reason | The claimed model property conflicts with the parsed model-property table in the staged manuscript. | [1] |
| Tp:verdict Reason | The manuscript states the visualization interpretation, but no embeddings or figure-generation data are available for quantitative verification. | [1] |
| Tp:verdict Reason | The claim is source-grounded, but the unit's executable recomputation requirement is blocked by missing experiment artifacts. | [1] |
| Rdf:type | Model | [1] |
| Rdf:type | Embedding Model | [1] |
| Rdf:type | Bioacoustics Model | [1] |
| Tp:simulation Verdict | reproduced | [1] |
| Tp:simulation Verdict | inconclusive | [1] |
| Tp:simulation Verdict | contradicted | [1] |
| Has Sample Rate | 16000 | [1] |
| Has Sample Rate | 16 | [1] |
| Has Embedding Dimension | 589824 | [1] |
| Has Embedding Dimension | 768 | [1] |
| Has Model Parameter Count | 94.4M | [1] |
| Has Model Parameter Count | 94.4 | [1] |
| Has Window Size | Variable | [1] |
| Trained on Taxa | General Audio | [1] |
| Has Output Dimensions | 768 | [1] |
| Uses Mean Pooling | Sliding Window Output | [1] |
| Output Array Size Formula | ((window size (s) * 49) - 1, 768) | [1] |
| Has Open Source Tools | Transfer Learning Tools | [1] |
| Compared With | Perch 2 0 | [1] |
| Has Training Taxa | General Audio | [1] |
| Described in | Hagiwara 2023 | [1] |
| Published by | Hagiwara 2023 | [1] |
| Shows High Class Entanglement | true | [1] |
| Has Entanglement Issue With | Southern Resident Killer Whale | [1] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (1)
tp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims- full textchunk-009text/plain3 KB
doc:agent/chunk-009/f33235ee-7e4c-40ec-b809-de198012fc5fShow excerpt
nighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv [cs.LG], Jan. 2020. E. Mercado and S. Handel. Understanding the structure of humpback whale songs (l). The Jo…
- full textchunk-008text/plain3 KB
doc:agent/chunk-008/5506d265-7ff5-434b-b60e-b755c8a596d6Show excerpt
Marine Science, 11:1394695, 2024. J. A. Allen, E. C. Garland, C. Garrigue, R. A. Dunlop, and M. J. Noad. Song complexity is maintained during inter-population cultural transmission of humpback whale songs. Scientific reports, 12(1): 8999, 2…
- full textchunk-007text/plain3 KB
doc:agent/chunk-007/04710b2a-ba75-48cb-94b5-13d951854faaShow excerpt
atasets with thousands of classes can be high performing, even on out-of-domain down- stream tasks. Next, the ‘bittern lesson’ learned when training Perch 2.0 was that bird species classification in particular is a challenging su- pervision…
- full textchunk-006text/plain3 KB
doc:agent/chunk-006/44f49039-e92d-4aae-a989-a3343ce76194Show excerpt
= 8k = 16k = 8 k = 16k = 8 k = 16 GMWM0.8900.9140.7640.8210.9360.9540.868* 0.917*0.8230.855 SurfPerch 0.9320.9470.8590.9030.9810.9840.7960.8990.982* 0.986* Perch 1.0 0.9580.9680.9010.9310.9770.9810.8360.9050.9580.970 Perch 2.0 0.9…
- full textchunk-005text/plain3 KB
doc:agent/chunk-005/31b9995b-056a-4dab-a3da-ede4fabae094Show excerpt
V2.348 kHz3.0102420.0MBirds, Frogs AVES-bio16 kHzVariable768 2 94.4MGeneral Audio BirdAVES (large)16 kHzVariable1024 3 315.4MGeneral Audio + Birds 4 Comparison models. As our goal is to provide guidance on which pretrained embedding models …
- full textchunk-004text/plain3 KB
doc:agent/chunk-004/2ce1467e-29e9-40e4-a12c-ee1e34601ebcShow excerpt
ludes new classes unseen by the models. The classes used in the NOAA PIPAN evaluation set include anthropomorphic noise, unknown whale species, and the following baleen whale species: common minke whale, humpback whale, sei whale, blue whal…
- full textchunk-003text/plain3 KB
doc:agent/chunk-003/05e7df2c-afdb-4b38-8576-118d1c22e948Show excerpt
ained on log-mel spectrograms using a classification loss. Additionally, the model used a form of self-distillation and a self-supervised loss (in the form of source recording prediction) with the goal of producing strong embeddings that ar…
- full textchunk-002text/plain3 KB
doc:agent/chunk-002/6ad8a5fa-2898-42fc-95e1-ea78861375f7Show excerpt
ion as new sounds are discovered while not having large amounts of human labeled data. Despite these challenges, passive acoustic monitoring is a critical tool for marine conservation and ecology (Fleishman et al., 2023), and discoveries ab…
- full textchunk-001text/plain3 KB
doc:agent/chunk-001/2b871fa0-4034-4d77-a1ce-b818711dd372Show excerpt
Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind Abs…
- full textchunk-005text/plain3 KB
doc:agent/chunk-005/84c4d25d-a6fb-4da9-95ec-773c6e223fa2Show excerpt
monitoring. Ecol. Inform., 61(101236):101236, Mar. 2021. 6 J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv [cs.LG], Jan. 2020…
- full textchunk-004text/plain6 KB
doc:agent/chunk-004/597f88dd-b871-4083-99cd-a9a4484853abShow excerpt
e datasets with thousands of classes can be high performing, even on out-of-domain down- stream tasks. Next, the ‘bittern lesson’ learned when training Perch 2.0 was that bird species classification in particular is a challenging su- pervis…
- full textchunk-003text/plain6 KB
doc:agent/chunk-003/e23b9efa-8e61-4312-a564-68c6956429b2Show excerpt
ce on which pretrained embedding models should be used for agile modeling and transfer learning (with existing tools), we limit our comparisons to models supported in the Perch Hoplite Github repository 5 . We compare the performance of the…
- full textchunk-002text/plain6 KB
doc:agent/chunk-002/f0b400dc-caae-4eca-b34a-d5598b9eddf0Show excerpt
l of producing strong embeddings that are linearly separable for a wide range of bioacoustics tasks. Embeddings from the Perch model have shown successful generalization to tasks other than species classification (e.g., individual identific…
- full textchunk-001text/plain6 KB
doc:agent/chunk-001/ae1f6e1d-0812-43e1-93c6-1e7778c77d74Show excerpt
Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind Abs…
- full texttoiletpaper-smoke-paperapplication/pdf24 KB
tp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9Show excerpt
Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind A…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.