Creating Domain-Specific Datasets for Intelligent Environmental Feature Comparison
Bibliographic record
Abstract
Coastal environments are dynamic and ecologically significant, yet monitoring across multiple sites and analysis remain challenging due to the lack of domain-specific datasets tailored to their unique features. General-purpose models, including those used for scene graph generation, often fail to capture the semantic details necessary for meaningful comparisons in this context. This paper outlines the process of creating a domain-specific dataset for coastal environments, focusing on the challenges posed by crowdsourced imagery, such as variability in image sizes, lighting conditions, and camera quality. By leveraging scene graph generation to capture semantic meaning, this research seeks to create a domain-specific dataset suitable for the comparison of coastal environments. This work demonstrates how domain-specific datasets can drive innovation in computer vision and semantic understanding, contributing to the broader field of artificial intelligence by bridging the gap between generalized tools and specialized applications. Ultimately, this effort lays the groundwork for future planned research to develop a pipeline capable of generating comparison metrics based on the semantic content of scenes. Using raw standardized images of coastal environments from the Coastie Initiative, this pipeline aims to go beyond superficial appearance comparisons, offering more meaningful analyses that could enhance our understanding and support conservation efforts.
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 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.007 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".