{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P3BHKCMCEYYVBBLRARQQR4VFSS","short_pith_number":"pith:P3BHKCMC","schema_version":"1.0","canonical_sha256":"7ec27509822631508571046108f2a5949c985d5b31b99651f029007ac526ee98","source":{"kind":"arxiv","id":"1804.07501","version":2},"attestation_state":"computed","paper":{"title":"FITS Data Source for Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"astro-ph.IM","authors_text":"Christian Arnault, Julien Peloton, St\\'ephane Plaszczynski","submitted_at":"2018-04-20T09:08:10Z","abstract_excerpt":"We investigate the performance of Apache Spark, a cluster computing framework, for analyzing data from future LSST-like galaxy surveys. Apache Spark attempts to address big data problems have hitherto proved successful in the industry, but its use in the astronomical community still remains limited. We show how to manage complex binary data structures handled in astrophysics experiments such as binary tables stored in FITS files, within a distributed environment. To this purpose, we first designed and implemented a Spark connector to handle sets of arbitrarily large FITS files, called spark-fi"},"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":"1804.07501","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"astro-ph.IM","submitted_at":"2018-04-20T09:08:10Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"28e462eba903737b1b51dec85f695ab12563bb1f8c7468bdb8021c3eab373cfc","abstract_canon_sha256":"4e65a096c30417edd68716e4aa13dbe5b781decd3adf2df0db59951d7435f95a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:16.774645Z","signature_b64":"1Rn75UYwAAXBOSzxeZhKcQCrXEoYxaWAuFQ2nj8K1HwCSYDaF+Nzr3+KBJbNsP++BAnAKzS/kr9XZKSsHBDYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec27509822631508571046108f2a5949c985d5b31b99651f029007ac526ee98","last_reissued_at":"2026-05-18T00:03:16.774019Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:16.774019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FITS Data Source for Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"astro-ph.IM","authors_text":"Christian Arnault, Julien Peloton, St\\'ephane Plaszczynski","submitted_at":"2018-04-20T09:08:10Z","abstract_excerpt":"We investigate the performance of Apache Spark, a cluster computing framework, for analyzing data from future LSST-like galaxy surveys. Apache Spark attempts to address big data problems have hitherto proved successful in the industry, but its use in the astronomical community still remains limited. We show how to manage complex binary data structures handled in astrophysics experiments such as binary tables stored in FITS files, within a distributed environment. To this purpose, we first designed and implemented a Spark connector to handle sets of arbitrarily large FITS files, called spark-fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07501","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":""},"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":"1804.07501","created_at":"2026-05-18T00:03:16.774117+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07501v2","created_at":"2026-05-18T00:03:16.774117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07501","created_at":"2026-05-18T00:03:16.774117+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3BHKCMCEYYV","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3BHKCMCEYYVBBLR","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3BHKCMC","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS","json":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS.json","graph_json":"https://pith.science/api/pith-number/P3BHKCMCEYYVBBLRARQQR4VFSS/graph.json","events_json":"https://pith.science/api/pith-number/P3BHKCMCEYYVBBLRARQQR4VFSS/events.json","paper":"https://pith.science/paper/P3BHKCMC"},"agent_actions":{"view_html":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS","download_json":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS.json","view_paper":"https://pith.science/paper/P3BHKCMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07501&json=true","fetch_graph":"https://pith.science/api/pith-number/P3BHKCMCEYYVBBLRARQQR4VFSS/graph.json","fetch_events":"https://pith.science/api/pith-number/P3BHKCMCEYYVBBLRARQQR4VFSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS/action/storage_attestation","attest_author":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS/action/author_attestation","sign_citation":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS/action/citation_signature","submit_replication":"https://pith.science/pith/P3BHKCMCEYYVBBLRARQQR4VFSS/action/replication_record"}},"created_at":"2026-05-18T00:03:16.774117+00:00","updated_at":"2026-05-18T00:03:16.774117+00:00"}