{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-multimodal-universe-enabling-large-scale","title":"The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data","arxiv_id":"2412.02527","date":"2024-12-03","proceeding":null,"authors":["The Multimodal Universe Collaboration","Jeroen Audenaert","Micah Bowles","Benjamin M. Boyd","David Chemaly","Brian Cherinka","Ioana Ciucă","Miles Cranmer","Aaron Do","Matthew Grayling","Erin E. Hayes","Tom Hehir","Shirley Ho","Marc Huertas-Company","Kartheik G. Iyer","Maja Jablonska","Francois Lanusse","Henry W. Leung","Kaisey Mandel","Juan Rafael Martínez-Galarza","Peter Melchior","Lucas Meyer","Liam H. Parker","Helen Qu","Jeff Shen","Michael J. Smith","Connor Stone","Mike Walmsley","John F. Wu"],"abstract":"We present the MULTIMODAL UNIVERSE, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, the MULTIMODAL UNIVERSE contains hundreds of millions of astronomical observations, constituting 100\\,TB of multi-channel and hyper-spectral images, spectra, multivariate time series, as well as a wide variety of associated scientific measurements and \"metadata\". In addition, we include a range of benchmark tasks representative of standard practices for machine learning methods in astrophysics. This massive dataset will enable the development of large multi-modal models specifically targeted towards scientific applications. All codes used to compile the MULTIMODAL UNIVERSE and a description of how to access the data is available at https://github.com/MultimodalUniverse/MultimodalUniverse","url_abs":"https://arxiv.org/abs/2412.02527v1","url_pdf":"https://arxiv.org/pdf/2412.02527v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"the-multimodal-universe-enabling-large-scale","repo_url":"https://github.com/multimodaluniverse/multimodaluniverse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.02527","atlas_url":"https://app.syntology.ai/?focus=2412.02527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02527"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/MultimodalUniverse/MultimodalUniverse","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/multimodaluniverse/multimodaluniverse","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f0a3007609b0f577","entry":"extract_acknowledgements","repo":"MultimodalUniverse/MultimodalUniverse","repo_kind":"official","path":"scripts/info.py","file_url":"https://github.com/MultimodalUniverse/MultimodalUniverse/blob/HEAD/scripts/info.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f0a3007609b0f577"}},{"code_sha256_prefix":"ff88353af1a886e1","entry":"conv1x1","repo":"multimodaluniverse/multimodaluniverse","repo_kind":"official","path":"experimental_benchmark/galaxy_properties/modules.py","file_url":"https://github.com/multimodaluniverse/multimodaluniverse/blob/HEAD/experimental_benchmark/galaxy_properties/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff88353af1a886e1"}},{"code_sha256_prefix":"db485754880e0747","entry":"conv3x3","repo":"multimodaluniverse/multimodaluniverse","repo_kind":"official","path":"experimental_benchmark/galaxy_properties/modules.py","file_url":"https://github.com/multimodaluniverse/multimodaluniverse/blob/HEAD/experimental_benchmark/galaxy_properties/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db485754880e0747"}},{"code_sha256_prefix":"9fab1dddd51579d7","entry":"create_attention_mask","repo":"multimodaluniverse/multimodaluniverse","repo_kind":"official","path":"baselines/plasticc/preprocess.py","file_url":"https://github.com/multimodaluniverse/multimodaluniverse/blob/HEAD/baselines/plasticc/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fab1dddd51579d7"}},{"code_sha256_prefix":"dace7f18ecd6d09e","entry":"get_config","repo":"multimodaluniverse/multimodaluniverse","repo_kind":"official","path":"baselines/plasticc/plasticc.py","file_url":"https://github.com/multimodaluniverse/multimodaluniverse/blob/HEAD/baselines/plasticc/plasticc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dace7f18ecd6d09e"}},{"code_sha256_prefix":"33252f39c1ee9922","entry":"gz10_cli","repo":"multimodaluniverse/multimodaluniverse","repo_kind":"official","path":"experimental_benchmark/galaxy10_decals/trainer.py","file_url":"https://github.com/multimodaluniverse/multimodaluniverse/blob/HEAD/experimental_benchmark/galaxy10_decals/trainer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"33252f39c1ee9922"}},{"code_sha256_prefix":"59c3d5e2ae6e0a8d","entry":"normalize_all","repo":"multimodaluniverse/multimodaluniverse","repo_kind":"official","path":"baselines/plasticc/preprocess.py","file_url":"https://github.com/multimodaluniverse/multimodaluniverse/blob/HEAD/baselines/plasticc/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59c3d5e2ae6e0a8d"}},{"code_sha256_prefix":"5f393d809299394f","entry":"normalize_by_channel","repo":"multimodaluniverse/multimodaluniverse","repo_kind":"official","path":"baselines/plasticc/preprocess.py","file_url":"https://github.com/multimodaluniverse/multimodaluniverse/blob/HEAD/baselines/plasticc/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f393d809299394f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}