{"success":true,"data":{"author":"Multimodal Universe Collaboration (Polymathic AI, UniverseTBD)","bucketAccessType":"public","bucketName":"UniverseTBD/mmu_btsbot","bucketPrefix":"","category":"Astronomy & Space","cloudProvider":"huggingface","createdAt":"2026-11-14T01:01:19.000Z","description":"Zwicky Transient Facility (ZTF) alert images and alert-packet features from the training set of BTSbot, a multimodal convolutional neural network that automates source selection for the ZTF Bright Transient Survey (Rehemtulla et al. 2024, arXiv:2401.15167), packaged as part of the Multimodal Universe collection of machine-learning-ready astronomical data. The modality is time-domain imaging with tabular metadata: each of 818,214 alerts carries image cutouts by band and view (science, reference and difference images), together with photometry (magpsf, sigmapsf, magap), real-bogus scores (drb), star-galaxy scores and distances to nearby Pan-STARRS and Gaia sources, light-curve summaries such as peakmag and days_since_peak, and labels such as is_SN. The README lists 92 columns in 2,078 HEALPix partitions and 18.9 GiB on disk. Listing the repository (measured 2026-11-13) shows the main catalog folder mmu_btsbot/ (dataset/, hats.properties, partition_info.csv, point_map.fits), the margin catalog mmu_btsbot_10arcs/ and collection.properties; about 21 GB in all. Data are a HATS catalog: Apache Parquet partitioned by HEALPix tile, with a 10 arcsecond margin catalog for cross-matching. Open with LSDB (lsdb.open_catalog on the Hugging Face URL, with cone searches and crossmatch), or read the Parquet with pandas, pyarrow, dask or DuckDB. Part of the Multimodal Universe (arXiv:2412.02527); released under CC-BY-4.0, cite the Multimodal Universe paper and the original survey.","displayTitle":"Multimodal Universe: BTSbot ZTF Bright Transient Survey Alert Images","id":"75dd9eb1-bd36-5254-b022-e4262fa67973","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/10839691","objectCountEstimate":2281,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2401.15167","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"UniverseTBD/mmu_btsbot\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"UniverseTBD/mmu_btsbot\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=UniverseTBD, license:cc-by-4.0, size_categories:100K<n<1M, format:parquet, downloads=1920"],"format":"mixed","generatedAt":"2026-11-14T01:01:24.255Z","layout":{"example":"mmu_btsbot/dataset/Norder=10/Dir=10000/Npix=18936.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"mmu_btsbot/dataset/Norder=10/Dir=10000/Npix=18936.parquet","truncatedAt":512}],"sampleObjects":["collection.properties","example_figure.png","mmu_btsbot/dataset/Norder=10/Dir=10000/Npix=18936.parquet","mmu_btsbot/dataset/Norder=10/Dir=10190000/Npix=10198969.parquet","mmu_btsbot/dataset/Norder=10/Dir=1020000/Npix=1027838.parquet"],"sidecars":[{"bytes":"---\r\nconfigs:\r\n- config_name: default\r\n  data_dir: mmu_btsbot/dataset\r\ntags:\r\n- astronomy\r\nlicense: cc-by-4.0\r\npretty_name: mmu_btsbot\r\nsize_categories:\r\n- 100K<n<1M\r\n---\r\n\r\n<div align=\"center\">\r\n<img src=\"example_figure.png\" width=\"600\">\r\n</div>\r\n\r\n# mmu_btsbot HATS Catalog Collection\r\n\r\nThis is the collection of HATS catalogs representing mmu_btsbot.\r\n\r\nThis dataset is part of the [Multimodal Universe](https://github.com/MultimodalUniverse/MultimodalUniverse),\r\na large-scale collection of multimodal astronomical data. For full details, see the paper:\r\n[The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TBs of Astronomical Scientific Data](https://arxiv.org/abs/2412.02527).\r\n\r\n### Access the catalog\r\n\r\nWe recommend the use of the [LSDB](https://lsdb.io) Python framework to access HATS catalogs.\r\nLSDB can be installed via `pip install lsdb` or `conda install conda-forge::lsdb`,\r\nsee more details [in the docs](https://docs.lsdb.io/).\r\nThe following code provides a minimal example of opening this catalog:\r\n\r\n```python\r\nimport lsdb\r\n\r\n# Full sky coverage.\r\ncatalog = lsdb.open_catalog(\"https://huggingface.co/datasets/UniverseTBD/mmu_btsbot\")\r\n# One-degree cone.\r\ncatalog = lsdb.open_catalog(\r\n    \"https://huggingface.co/datasets/UniverseTBD/mmu_btsbot\",\r\n    search_filter=lsdb.ConeSearch(ra=1.0, dec=78.0, radius_arcsec=3600.0),\r\n)\r\n```\r\n\r\nEach catalog in this collection is represented as a separate [Apache Parquet dataset](https://arrow.apache.org/docs/python/dataset.html) and can be accessed with a variety of tools, including `pandas`, `pyarrow`, `dask`, `Spark`, `DuckDB`.\r\n\r\n### File structure\r\n\r\nThis catalog is represented by the following files and directories:\r\n\r\n- [`collection.properties`](https://huggingface.co/datasets/UniverseTBD/mmu_btsbot/collection.properties) — textual metadata file describing the HATS collection of catalogs\r\n- [`mmu_btsbot`](https://huggingface.co/datasets/UniverseTBD/mmu_btsbot/mmu_btsbot) — main HATS catalog directory\r\n  - [`dataset/`](https://huggingface.co/datasets/UniverseTBD/mmu_btsbot/mmu_btsbot/dataset/) — Apache Parquet dataset directory for the main catalog\r\n    - ... parquet metadata and data files in sub directories ...\r\n  - [`hats.properties`](https://huggingface.co/datasets/UniverseTBD/mmu_btsbot/mmu_btsbot/hats.properties) — textual metadata file describing the main HATS catalog\r\n  - [`partition_info.csv`](https://huggingface.co/datasets/UniverseTBD/mmu_btsbot/mmu_btsbot/partition_info.csv) — CSV file with a list of catalog HEALPix tiles (catalog partitions)\r\n  - [`skymap.fits`](https://huggingface.co/datasets/UniverseTBD/mmu_btsbot/mmu_btsbot/skymap.fits) — HEALPix skymap FITS file with row-counts per HEALPix tile of fixed order 10\r\n- [`mmu_btsbot_10arcs/`](https://huggingface.co/datasets/UniverseTBD/mmu_btsbot/mmu_btsbot_10arcs) — default margin catalog to ensure data completeness in cross-matching, the margin threshold is 10.0 arcseconds\r\n  - ... margin catalog files and directories ...\r\n\r\n### Catalog metadata\r\n\r\nMetadata of the main HATS catalog, excluding margins and indexes:\r\n\r\n| **Number of rows** | **Number of columns** | **Number of partitions** | **Size on disk** | **HATS Builder** |\r\n| --- | --- | --- | --- | --- |\r\n| 818,214 | 92 | 2,078 | 18.9 GiB | hats-import v0.7.1, hats v0.7.1 |\r\n\r\n\r\n### Catalog columns\r\n\r\nThe main HATS catalog contains the following columns:\r\n\r\n| **Name** |  **`_healpix_29`** | **`band`** | **`view`** | **`array`** | **`scale`** | **`jd`** | **`diffmaglim`** | **`magpsf`** | **`sigmapsf`** | **`chipsf`** | **`magap`** | **`sigmagap`** | **`distnr`** | **`magnr`** | **`chinr`** | **`sharpnr`** | **`sky`** | **`magdiff`** | **`fwhm`** | **`classtar`** | **`mindtoedge`** | **`seeratio`** | **`magapbig`** | **`sigmagapbig`** | **`sgmag1`** | **`srmag1`** | **`simag1`** | **`szmag1`** | **`sgscore1`** | **`distpsnr1`** | **`jdstarthist`** | **`scorr`** | **`sgmag2`** | **`srmag2`** | **`simag2`** | **`szmag2`** | **`sgscore2`** | **`distpsnr2`** | **`sgmag3`** | **`srmag3`** | **`simag3`** | **`szmag3`** | **`sgscore3","encoding":"utf8","key":"README.md","name":"README.md","size":13011,"truncated":true}],"sourceObjectKey":"mmu_btsbot/dataset/Norder=10/Dir=10000/Npix=18936.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"UniverseTBD/mmu_btsbot\")\nprint(ds)","starterSamplePath":"example_figure.png","totalObjects":2281},"summary":"Zwicky Transient Facility (ZTF) alert images and alert-packet features from the training set of BTSbot, a multimodal convolutional neural network that automates source selection…","title":"Multimodal Universe: BTSbot ZTF Bright Transient Survey Alert Images","updatedAt":"2026-11-14T02:41:31.229Z","visibility":"public","websiteUrl":"https://github.com/MultimodalUniverse/MultimodalUniverse"}}