{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M72Q2VSOCWOEED5COTVR2BMRIO","short_pith_number":"pith:M72Q2VSO","schema_version":"1.0","canonical_sha256":"67f50d564e159c420fa274eb1d05914387756a897936c542febba1de3401c5ce","source":{"kind":"arxiv","id":"2412.02527","version":1},"attestation_state":"computed","paper":{"title":"The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.GA","astro-ph.SR"],"primary_cat":"astro-ph.IM","authors_text":"Aaron Do, Benjamin M. Boyd, Brian Cherinka, Connor Stone, David Chemaly, Erin E. Hayes, Francois Lanusse, Helen Qu, Henry W. Leung, Ioana Ciuc\\u{a}, Jeff Shen, Jeroen Audenaert, John F. Wu, Juan Rafael Mart\\'inez-Galarza, Kaisey Mandel, Kartheik G. Iyer, Liam H. Parker, Lucas Meyer, Maja Jablonska, Marc Huertas-Company, Matthew Grayling, Micah Bowles, Michael J. Smith, Mike Walmsley, Miles Cranmer, Peter Melchior, Shirley Ho, The Multimodal Universe Collaboration. Eirini Angeloudi, Tom Hehir","submitted_at":"2024-12-03T16:21:17Z","abstract_excerpt":"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 en"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.02527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2024-12-03T16:21:17Z","cross_cats_sorted":["astro-ph.GA","astro-ph.SR"],"title_canon_sha256":"ec32764224d93118c1137ddcaea86caf359058ca1f428a8806274a0cb6c812dd","abstract_canon_sha256":"d16aa9694a9e316bca25b9a8c46624b7406f60a404feb857e18ffc00f62a1dcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:51.262554Z","signature_b64":"1+0JPpZGM06cSUtrMv5ONYlZohauSsxwvZ0O9tMqMgQxnzKPE14Aph13BaTmrOlgAqeN195GIK/E0oCDBP0xAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f50d564e159c420fa274eb1d05914387756a897936c542febba1de3401c5ce","last_reissued_at":"2026-07-05T09:43:51.262052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:51.262052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.GA","astro-ph.SR"],"primary_cat":"astro-ph.IM","authors_text":"Aaron Do, Benjamin M. Boyd, Brian Cherinka, Connor Stone, David Chemaly, Erin E. Hayes, Francois Lanusse, Helen Qu, Henry W. Leung, Ioana Ciuc\\u{a}, Jeff Shen, Jeroen Audenaert, John F. Wu, Juan Rafael Mart\\'inez-Galarza, Kaisey Mandel, Kartheik G. Iyer, Liam H. Parker, Lucas Meyer, Maja Jablonska, Marc Huertas-Company, Matthew Grayling, Micah Bowles, Michael J. Smith, Mike Walmsley, Miles Cranmer, Peter Melchior, Shirley Ho, The Multimodal Universe Collaboration. Eirini Angeloudi, Tom Hehir","submitted_at":"2024-12-03T16:21:17Z","abstract_excerpt":"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 en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02527","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.02527/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.02527","created_at":"2026-07-05T09:43:51.262118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02527v1","created_at":"2026-07-05T09:43:51.262118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02527","created_at":"2026-07-05T09:43:51.262118+00:00"},{"alias_kind":"pith_short_12","alias_value":"M72Q2VSOCWOE","created_at":"2026-07-05T09:43:51.262118+00:00"},{"alias_kind":"pith_short_16","alias_value":"M72Q2VSOCWOEED5C","created_at":"2026-07-05T09:43:51.262118+00:00"},{"alias_kind":"pith_short_8","alias_value":"M72Q2VSO","created_at":"2026-07-05T09:43:51.262118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26320","citing_title":"MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23136","citing_title":"A Gaia-linked High-purity QSO Candidate Catalog in Selected Fields with Extinction-binned Calibration and Spectrum-informed Training","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO","json":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO.json","graph_json":"https://pith.science/api/pith-number/M72Q2VSOCWOEED5COTVR2BMRIO/graph.json","events_json":"https://pith.science/api/pith-number/M72Q2VSOCWOEED5COTVR2BMRIO/events.json","paper":"https://pith.science/paper/M72Q2VSO"},"agent_actions":{"view_html":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO","download_json":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO.json","view_paper":"https://pith.science/paper/M72Q2VSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02527&json=true","fetch_graph":"https://pith.science/api/pith-number/M72Q2VSOCWOEED5COTVR2BMRIO/graph.json","fetch_events":"https://pith.science/api/pith-number/M72Q2VSOCWOEED5COTVR2BMRIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO/action/storage_attestation","attest_author":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO/action/author_attestation","sign_citation":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO/action/citation_signature","submit_replication":"https://pith.science/pith/M72Q2VSOCWOEED5COTVR2BMRIO/action/replication_record"}},"created_at":"2026-07-05T09:43:51.262118+00:00","updated_at":"2026-07-05T09:43:51.262118+00:00"}