{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:FQRR5X7L3JHBJN5ADE2UYQ3F32","short_pith_number":"pith:FQRR5X7L","schema_version":"1.0","canonical_sha256":"2c231edfebda4e14b7a019354c4365de8728c6fbfc1a1fd12b46b0dce3f30431","source":{"kind":"arxiv","id":"1507.03325","version":2},"attestation_state":"computed","paper":{"title":"Scientific Computing Meets Big Data Technology: An Astronomy Use Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"David A. Patterson, Evan Sparks, Frank Austin Nothaft, Kyle Barbary, Michael J. Franklin, Oliver Zahn, Saul Perlmutter, Zhao Zhang","submitted_at":"2015-07-13T04:47:04Z","abstract_excerpt":"Scientific analyses commonly compose multiple single-process programs into a dataflow. An end-to-end dataflow of single-process programs is known as a many-task application. Typically, tools from the HPC software stack are used to parallelize these analyses. In this work, we investigate an alternate approach that uses Apache Spark -- a modern big data platform -- to parallelize many-task applications. We present Kira, a flexible and distributed astronomy image processing toolkit using Apache Spark. We then use the Kira toolkit to implement a Source Extractor application for astronomy images, c"},"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":"1507.03325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2015-07-13T04:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"331de92b37c74ddeb0f0e0a923be089f1a3aebd08474f853e61fea63bc5374e7","abstract_canon_sha256":"5e578ab498213b0f0e2d62df39585288485c726075d35a5cc89708f9b8c70858"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:12.011892Z","signature_b64":"Evh3McJj7T0WqekSzTi5nXBQsJDhaPSuIR1/vIEIYnWk12B9NTLGzXzDmxqkIiq+O18hSHsHBqnWrsUTDlefAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c231edfebda4e14b7a019354c4365de8728c6fbfc1a1fd12b46b0dce3f30431","last_reissued_at":"2026-05-18T01:19:12.011149Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:12.011149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scientific Computing Meets Big Data Technology: An Astronomy Use Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"David A. Patterson, Evan Sparks, Frank Austin Nothaft, Kyle Barbary, Michael J. Franklin, Oliver Zahn, Saul Perlmutter, Zhao Zhang","submitted_at":"2015-07-13T04:47:04Z","abstract_excerpt":"Scientific analyses commonly compose multiple single-process programs into a dataflow. An end-to-end dataflow of single-process programs is known as a many-task application. Typically, tools from the HPC software stack are used to parallelize these analyses. In this work, we investigate an alternate approach that uses Apache Spark -- a modern big data platform -- to parallelize many-task applications. We present Kira, a flexible and distributed astronomy image processing toolkit using Apache Spark. We then use the Kira toolkit to implement a Source Extractor application for astronomy images, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.03325","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":"1507.03325","created_at":"2026-05-18T01:19:12.011271+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.03325v2","created_at":"2026-05-18T01:19:12.011271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.03325","created_at":"2026-05-18T01:19:12.011271+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQRR5X7L3JHB","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQRR5X7L3JHBJN5A","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQRR5X7L","created_at":"2026-05-18T12:29:22.688609+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/FQRR5X7L3JHBJN5ADE2UYQ3F32","json":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32.json","graph_json":"https://pith.science/api/pith-number/FQRR5X7L3JHBJN5ADE2UYQ3F32/graph.json","events_json":"https://pith.science/api/pith-number/FQRR5X7L3JHBJN5ADE2UYQ3F32/events.json","paper":"https://pith.science/paper/FQRR5X7L"},"agent_actions":{"view_html":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32","download_json":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32.json","view_paper":"https://pith.science/paper/FQRR5X7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.03325&json=true","fetch_graph":"https://pith.science/api/pith-number/FQRR5X7L3JHBJN5ADE2UYQ3F32/graph.json","fetch_events":"https://pith.science/api/pith-number/FQRR5X7L3JHBJN5ADE2UYQ3F32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32/action/storage_attestation","attest_author":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32/action/author_attestation","sign_citation":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32/action/citation_signature","submit_replication":"https://pith.science/pith/FQRR5X7L3JHBJN5ADE2UYQ3F32/action/replication_record"}},"created_at":"2026-05-18T01:19:12.011271+00:00","updated_at":"2026-05-18T01:19:12.011271+00:00"}