How do we design data sets for Machine Learning astronomy?
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Many problems in astronomy and physics lend themselves to solutions from machine learning methods for the detection and classification of astronomical signals, and model inference from those signals. The historic presentation of machine learning methods as ‘black boxes’ has generated push back from some in the the physics/astronomy communities regarding how useful they are to truly uncover the physical laws that govern our world. Skepticism about the applicability of new computational methods in scientific inference is not new; we highlight connections between the machine learning contexts and previous computational paradigm shifts in astronomy. Moreover, several advances in methodologies challenge the assumption that machine learning ‘gives us answers that we can use but do not understand’ to standing physics questions. We summarize some astronomical machine learning data challenges used in astronomy and how we can use challenges on different scales to test different parts/use cases of our analysis methods.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.004 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it