{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E2C4SJLGK3XS76JKVPCWEO3WVZ","short_pith_number":"pith:E2C4SJLG","schema_version":"1.0","canonical_sha256":"2685c9256656ef2ff92aabc5623b76ae61775a5c3176c695daf8d0f50b707d44","source":{"kind":"arxiv","id":"2307.08700","version":1},"attestation_state":"computed","paper":{"title":"Fast model inference and training on-board of Satellites","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Andrew Markham, Chris Bridges, Chris Brunskill, Cormac Purcell, Gonzalo Mateo-Garc\\'ia, Nicolas Long\\'ep\\'e, V\\'it R\\r{u}\\v{z}i\\v{c}ka","submitted_at":"2023-07-17T17:59:09Z","abstract_excerpt":"Artificial intelligence onboard satellites has the potential to reduce data transmission requirements, enable real-time decision-making and collaboration within constellations. This study deploys a lightweight foundational model called RaVAEn on D-Orbit's ION SCV004 satellite. RaVAEn is a variational auto-encoder (VAE) that generates compressed latent vectors from small image tiles, enabling several downstream tasks. In this work we demonstrate the reliable use of RaVAEn onboard a satellite, achieving an encoding time of 0.110s for tiles of a 4.8x4.8 km$^2$ area. In addition, we showcase fast "},"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":"2307.08700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-07-17T17:59:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bdfd616f70a635f0ab00c15e15e6f1f9da07c31f398f72fc4784bdf25131abb1","abstract_canon_sha256":"475fcd1c3d2f9276aa4aa123b17d89717b7d848f5204b2b3b2e44238a0a7016a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:27.851403Z","signature_b64":"+QfHaU8c20YOz7kEHrMgwov+xVLXpTEpMt2z5riwYEAi0Q64s66MBP62AvFOuBE/sd0ts1HkSyT/rRd5jEgOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2685c9256656ef2ff92aabc5623b76ae61775a5c3176c695daf8d0f50b707d44","last_reissued_at":"2026-07-05T06:31:27.850874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:27.850874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast model inference and training on-board of Satellites","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Andrew Markham, Chris Bridges, Chris Brunskill, Cormac Purcell, Gonzalo Mateo-Garc\\'ia, Nicolas Long\\'ep\\'e, V\\'it R\\r{u}\\v{z}i\\v{c}ka","submitted_at":"2023-07-17T17:59:09Z","abstract_excerpt":"Artificial intelligence onboard satellites has the potential to reduce data transmission requirements, enable real-time decision-making and collaboration within constellations. This study deploys a lightweight foundational model called RaVAEn on D-Orbit's ION SCV004 satellite. RaVAEn is a variational auto-encoder (VAE) that generates compressed latent vectors from small image tiles, enabling several downstream tasks. In this work we demonstrate the reliable use of RaVAEn onboard a satellite, achieving an encoding time of 0.110s for tiles of a 4.8x4.8 km$^2$ area. In addition, we showcase fast "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08700","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/2307.08700/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":"2307.08700","created_at":"2026-07-05T06:31:27.850932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08700v1","created_at":"2026-07-05T06:31:27.850932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08700","created_at":"2026-07-05T06:31:27.850932+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2C4SJLGK3XS","created_at":"2026-07-05T06:31:27.850932+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2C4SJLGK3XS76JK","created_at":"2026-07-05T06:31:27.850932+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2C4SJLG","created_at":"2026-07-05T06:31:27.850932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03728","citing_title":"SAT-Edge-Agent: Hardware-in-the-Loop Edge-Agent Orchestration for Onboard Satellite Intelligence","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ","json":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ.json","graph_json":"https://pith.science/api/pith-number/E2C4SJLGK3XS76JKVPCWEO3WVZ/graph.json","events_json":"https://pith.science/api/pith-number/E2C4SJLGK3XS76JKVPCWEO3WVZ/events.json","paper":"https://pith.science/paper/E2C4SJLG"},"agent_actions":{"view_html":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ","download_json":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ.json","view_paper":"https://pith.science/paper/E2C4SJLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08700&json=true","fetch_graph":"https://pith.science/api/pith-number/E2C4SJLGK3XS76JKVPCWEO3WVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/E2C4SJLGK3XS76JKVPCWEO3WVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ/action/storage_attestation","attest_author":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ/action/author_attestation","sign_citation":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ/action/citation_signature","submit_replication":"https://pith.science/pith/E2C4SJLGK3XS76JKVPCWEO3WVZ/action/replication_record"}},"created_at":"2026-07-05T06:31:27.850932+00:00","updated_at":"2026-07-05T06:31:27.850932+00:00"}