arXiv-v1

notebooks/xx_data_checks.ipynb

@@ -0,0 +1,124 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from astroquery.mast import Observations\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5\n",
+      "20\n"
+     ]
+    }
+   ],
+   "source": [
+    "proposal_id = 15354\n",
+    "\n",
+    "# Query MAST for observations\n",
+    "obs_table = Observations.query_criteria(\n",
+    "    obs_collection=\"HST\",\n",
+    "    proposal_id=[f\"{proposal_id}\"],\n",
+    "    dataRights=\"PUBLIC\",\n",
+    ")\n",
+    "\n",
+    "print(len(obs_table))\n",
+    "\n",
+    "# Get preview products\n",
+    "products = Observations.get_product_list(obs_table)\n",
+    "products = products[products[\"productType\"] == \"PREVIEW\"]\n",
+    "\n",
+    "match = \"total\"\n",
+    "exclude = \"color\"\n",
+    "match_mask = [match in row[\"productFilename\"] for row in products]\n",
+    "exclude_mask = [exclude not in row[\"productFilename\"] for row in products]\n",
+    "mask = [m and e for m, e in zip(match_mask, exclude_mask)]\n",
+    "\n",
+    "seed = 42\n",
+    "n_max_images = 20\n",
+    "\n",
+    "products = products[mask][np.random.RandomState(seed=seed).choice(np.arange(len(products[mask])), n_max_images)]\n",
+    "\n",
+    "print(len(products))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO: 19 of 20 products were duplicates. Only downloading 1 unique product(s). [astroquery.mast.observations]\n",
+      "Downloading URL https://mast.stsci.edu/api/v0.1/Download/file?uri=mast:HST/product/hst_15354_01_acs_wfc_total_jdi601_drc.jpg to download_dir/mastDownload/HST/hst_15354_01_acs_wfc_total_jdi601/hst_15354_01_acs_wfc_total_jdi601_drc.jpg ... [Done]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "download_dir = 'download_dir'\n",
+    "\n",
+    "Observations.download_products(\n",
+    "    products,\n",
+    "    extension=[\"jpg\", \"jpeg\"],\n",
+    "    productType=\"PREVIEW\",\n",
+    "    download_dir=download_dir,\n",
+    ")\n",
+    "\n",
+    "# Recursively find all images in \"total_images\" directory and bring them up to \"total_images\"\n",
+    "for root, dirs, files in os.walk(download_dir):\n",
+    "    for file in files:\n",
+    "        if file.endswith((\".jpg\", \".jpeg\")):\n",
+    "            source = os.path.join(root, file)\n",
+    "            destination = os.path.join(download_dir, file)\n",
+    "\n",
+    "            # Check if file already exists in the destination\n",
+    "            if not os.path.exists(destination):\n",
+    "                os.rename(source, destination)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

paper/hubble_paperclip.bib

@@ -464,4 +464,43 @@ @article{akhmetzhanova2024data
   pages     = {7459--7481},
   year      = {2024},
   publisher = {Oxford University Press}
+}
+
+@article{Birk:2024knn,
+  author        = {Birk, Joschka and Hallin, Anna and Kasieczka, Gregor},
+  title         = {{OmniJet-$\alpha$: The first cross-task foundation model for particle physics}},
+  eprint        = {2403.05618},
+  archiveprefix = {arXiv},
+  primaryclass  = {hep-ph},
+  month         = {3},
+  year          = {2024}
+}
+
+@article{heinrich2024masked,
+  title   = {Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models},
+  author  = {Heinrich, Lukas and Kagan, Michael and Klein, Samuel and Leigh, Matthew and Golling, Tobias and Raine, John Andrew and Osadchy, Margarita},
+  journal = {arXiv preprint arXiv:2401.13537},
+  year    = {2024}
+}
+
+@article{mccabe2023multiple,
+  title   = {Multiple physics pretraining for physical surrogate models},
+  author  = {McCabe, Michael and Blancard, Bruno R{\'e}galdo-Saint and Parker, Liam Holden and Ohana, Ruben and Cranmer, Miles and Bietti, Alberto and Eickenberg, Michael and Golkar, Siavash and Krawezik, Geraud and Lanusse, Francois and others},
+  journal = {arXiv preprint arXiv:2310.02994},
+  year    = {2023}
+}
+
+@article{vaswani2017attention,
+  title   = {Attention is all you need},
+  author  = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
+  journal = {Advances in neural information processing systems},
+  volume  = {30},
+  year    = {2017}
+}
+
+@article{dosovitskiy2020image,
+  title   = {An image is worth 16x16 words: Transformers for image recognition at scale},
+  author  = {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
+  journal = {arXiv preprint arXiv:2010.11929},
+  year    = {2020}
 }