{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NRQT7WMEYVFFHYHQXAMR5AIAS","short_pith_number":"pith:6NRQT7WM","schema_version":"1.0","canonical_sha256":"f36309fecc262a529f0785c0c8f40804b226aa231985065ff349e1da1661ac58","source":{"kind":"arxiv","id":"2408.05924","version":2},"attestation_state":"computed","paper":{"title":"Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Daniele Gammelli, Ethan Foss, Justin Kruger, Marco Pavone, Matthew Foutter, Praneet Bhoj, Simone D'Amico, Tommaso Guffanti","submitted_at":"2024-08-12T05:07:24Z","abstract_excerpt":"Foundation Models (FMs), e.g., large language models, possess attributes of intelligence which offer promise to endow a robot with the contextual understanding necessary to navigate complex, unstructured tasks in the wild. We see three core challenges in the future of space robotics that motivate building an FM for the space robotics community: 1) Scalability of ground-in-the-loop operations; 2) Generalizing prior knowledge to novel environments; and 3) Multi-modality in tasks and sensor data. As a first-step towards a space foundation model, we programmatically augment three extraterrestrial "},"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":"2408.05924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-08-12T05:07:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ef82f8e11552e8833e2eb89913325d97476946148b1abbe2b3c73b444a5f4b0","abstract_canon_sha256":"290df4e01dff78a44fdb988e34456ad971daa84e6971b7182a9b5308498b0fd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:50.373217Z","signature_b64":"OCf+2YBJmJgSntX2siU40WWsfYudDhq68dgz/jtRbqS+oXHj7jwa943qONFZx78Jpkzxmo7DGuG6E9lveIseCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f36309fecc262a529f0785c0c8f40804b226aa231985065ff349e1da1661ac58","last_reissued_at":"2026-07-05T10:02:50.372656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:50.372656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Daniele Gammelli, Ethan Foss, Justin Kruger, Marco Pavone, Matthew Foutter, Praneet Bhoj, Simone D'Amico, Tommaso Guffanti","submitted_at":"2024-08-12T05:07:24Z","abstract_excerpt":"Foundation Models (FMs), e.g., large language models, possess attributes of intelligence which offer promise to endow a robot with the contextual understanding necessary to navigate complex, unstructured tasks in the wild. We see three core challenges in the future of space robotics that motivate building an FM for the space robotics community: 1) Scalability of ground-in-the-loop operations; 2) Generalizing prior knowledge to novel environments; and 3) Multi-modality in tasks and sensor data. As a first-step towards a space foundation model, we programmatically augment three extraterrestrial "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05924","kind":"arxiv","version":2},"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/2408.05924/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":"2408.05924","created_at":"2026-07-05T10:02:50.372720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05924v2","created_at":"2026-07-05T10:02:50.372720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05924","created_at":"2026-07-05T10:02:50.372720+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NRQT7WMEYVF","created_at":"2026-07-05T10:02:50.372720+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NRQT7WMEYVFFHYH","created_at":"2026-07-05T10:02:50.372720+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NRQT7WM","created_at":"2026-07-05T10:02:50.372720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.27112","citing_title":"RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14399","citing_title":"SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08539","citing_title":"OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS","json":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS.json","graph_json":"https://pith.science/api/pith-number/6NRQT7WMEYVFFHYHQXAMR5AIAS/graph.json","events_json":"https://pith.science/api/pith-number/6NRQT7WMEYVFFHYHQXAMR5AIAS/events.json","paper":"https://pith.science/paper/6NRQT7WM"},"agent_actions":{"view_html":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS","download_json":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS.json","view_paper":"https://pith.science/paper/6NRQT7WM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05924&json=true","fetch_graph":"https://pith.science/api/pith-number/6NRQT7WMEYVFFHYHQXAMR5AIAS/graph.json","fetch_events":"https://pith.science/api/pith-number/6NRQT7WMEYVFFHYHQXAMR5AIAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS/action/storage_attestation","attest_author":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS/action/author_attestation","sign_citation":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS/action/citation_signature","submit_replication":"https://pith.science/pith/6NRQT7WMEYVFFHYHQXAMR5AIAS/action/replication_record"}},"created_at":"2026-07-05T10:02:50.372720+00:00","updated_at":"2026-07-05T10:02:50.372720+00:00"}