{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F44TIMTDYU3PVVQ6Z3FN7OKZQP","short_pith_number":"pith:F44TIMTD","schema_version":"1.0","canonical_sha256":"2f39343263c536fad61ececadfb95983fa12966cdbb80f4c0e350a2a565d438b","source":{"kind":"arxiv","id":"2504.08583","version":1},"attestation_state":"computed","paper":{"title":"AstroLLaVA: towards the unification of astronomical data and natural language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Dimitrios Tanoglidis, Maja Jab{\\l}o\\'nska, Marc Huertas-Company, Matthieu Le Lain, Michael J. Smith, Michele Ginolfi, Pranav Khetarpal, Rishabh Chakrabarty, Sandor Kruk, Sergio Jos\\'e Rodr\\'iguez M\\'endez, Sharaf Zaman","submitted_at":"2025-04-11T14:36:31Z","abstract_excerpt":"We present AstroLLaVA, a vision language model for astronomy that enables interaction with astronomical imagery through natural dialogue. By fine-tuning the LLaVA model on a diverse dataset of $\\sim$30k images with captions and question-answer pairs sourced from NASA's `Astronomy Picture of the Day', the European Southern Observatory, and the NASA/ESA Hubble Space Telescope, we create a model capable of answering open-ended questions about astronomical concepts depicted visually. Our two-stage fine-tuning process adapts the model to both image captioning and visual question answering in the as"},"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":"2504.08583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2025-04-11T14:36:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0c8f3b18b8fe91707ba0fdf78e12727e674a5daf340343feeb5abaa9db5bbef0","abstract_canon_sha256":"dbbecfff64a52645021545e74a079938b2ef0d046a3524e150396659b957c49f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:51.205333Z","signature_b64":"WZ0oE6hwYvDLaNQpx6CfZXlF3UjRbtKhI4v0ra79EDvLPVnHH10TNICg1YFCVXT5HuZQJT0oGZ/dS5v0CEE6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f39343263c536fad61ececadfb95983fa12966cdbb80f4c0e350a2a565d438b","last_reissued_at":"2026-07-05T10:47:51.204914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:51.204914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AstroLLaVA: towards the unification of astronomical data and natural language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Dimitrios Tanoglidis, Maja Jab{\\l}o\\'nska, Marc Huertas-Company, Matthieu Le Lain, Michael J. Smith, Michele Ginolfi, Pranav Khetarpal, Rishabh Chakrabarty, Sandor Kruk, Sergio Jos\\'e Rodr\\'iguez M\\'endez, Sharaf Zaman","submitted_at":"2025-04-11T14:36:31Z","abstract_excerpt":"We present AstroLLaVA, a vision language model for astronomy that enables interaction with astronomical imagery through natural dialogue. By fine-tuning the LLaVA model on a diverse dataset of $\\sim$30k images with captions and question-answer pairs sourced from NASA's `Astronomy Picture of the Day', the European Southern Observatory, and the NASA/ESA Hubble Space Telescope, we create a model capable of answering open-ended questions about astronomical concepts depicted visually. Our two-stage fine-tuning process adapts the model to both image captioning and visual question answering in the as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08583","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/2504.08583/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":"2504.08583","created_at":"2026-07-05T10:47:51.204967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08583v1","created_at":"2026-07-05T10:47:51.204967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08583","created_at":"2026-07-05T10:47:51.204967+00:00"},{"alias_kind":"pith_short_12","alias_value":"F44TIMTDYU3P","created_at":"2026-07-05T10:47:51.204967+00:00"},{"alias_kind":"pith_short_16","alias_value":"F44TIMTDYU3PVVQ6","created_at":"2026-07-05T10:47:51.204967+00:00"},{"alias_kind":"pith_short_8","alias_value":"F44TIMTD","created_at":"2026-07-05T10:47:51.204967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07382","citing_title":"Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06305","citing_title":"Exploring Image-Text Alignment for Radio Galaxy Morphologies","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27295","citing_title":"Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07779","citing_title":"Do Vision-Language Models See Dwarf Galaxies the Way We Do?","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP","json":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP.json","graph_json":"https://pith.science/api/pith-number/F44TIMTDYU3PVVQ6Z3FN7OKZQP/graph.json","events_json":"https://pith.science/api/pith-number/F44TIMTDYU3PVVQ6Z3FN7OKZQP/events.json","paper":"https://pith.science/paper/F44TIMTD"},"agent_actions":{"view_html":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP","download_json":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP.json","view_paper":"https://pith.science/paper/F44TIMTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08583&json=true","fetch_graph":"https://pith.science/api/pith-number/F44TIMTDYU3PVVQ6Z3FN7OKZQP/graph.json","fetch_events":"https://pith.science/api/pith-number/F44TIMTDYU3PVVQ6Z3FN7OKZQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP/action/storage_attestation","attest_author":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP/action/author_attestation","sign_citation":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP/action/citation_signature","submit_replication":"https://pith.science/pith/F44TIMTDYU3PVVQ6Z3FN7OKZQP/action/replication_record"}},"created_at":"2026-07-05T10:47:51.204967+00:00","updated_at":"2026-07-05T10:47:51.204967+00:00"}