{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:Y3TYZ4QPPQJ62ZRYL37DB6POV2","short_pith_number":"pith:Y3TYZ4QP","schema_version":"1.0","canonical_sha256":"c6e78cf20f7c13ed66385efe30f9eeaeb2a8c1f95063b01786100f8add8a052d","source":{"kind":"arxiv","id":"1507.02321","version":1},"attestation_state":"computed","paper":{"title":"On the Evaluation of RDF Distribution Algorithms Implemented over Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bernd Amann, Hubert Naacke, Mohamed-Amine Baazizi, Olivier Cur\\'e","submitted_at":"2015-07-08T21:51:11Z","abstract_excerpt":"Querying very large RDF data sets in an efficient manner requires a sophisticated distribution strategy. Several innovative solutions have recently been proposed for optimizing data distribution with predefined query workloads. This paper presents an in-depth analysis and experimental comparison of five representative and complementary distribution approaches. For achieving fair experimental results, we are using Apache Spark as a common parallel computing framework by rewriting the concerned algorithms using the Spark API. Spark provides guarantees in terms of fault tolerance, high availabili"},"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":"1507.02321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-07-08T21:51:11Z","cross_cats_sorted":[],"title_canon_sha256":"f21dfeba67cc5d493e96a0c2054d89e3934f713166d12924bfce91c47f2e0196","abstract_canon_sha256":"8c2b2af00c8e34ea03438d9874de8f868d96021b1810a29c0e646d7ea825ac63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:07.003782Z","signature_b64":"R5jUf7UHP9fPr4ZNv08NMPvwo4MiQf1YcysUFfUs4KBxqKUn1rCMXBIy9OQgR2kYJhxPHhkHcJRq9xsMO8msCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6e78cf20f7c13ed66385efe30f9eeaeb2a8c1f95063b01786100f8add8a052d","last_reissued_at":"2026-05-18T01:37:07.003263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:07.003263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Evaluation of RDF Distribution Algorithms Implemented over Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bernd Amann, Hubert Naacke, Mohamed-Amine Baazizi, Olivier Cur\\'e","submitted_at":"2015-07-08T21:51:11Z","abstract_excerpt":"Querying very large RDF data sets in an efficient manner requires a sophisticated distribution strategy. Several innovative solutions have recently been proposed for optimizing data distribution with predefined query workloads. This paper presents an in-depth analysis and experimental comparison of five representative and complementary distribution approaches. For achieving fair experimental results, we are using Apache Spark as a common parallel computing framework by rewriting the concerned algorithms using the Spark API. Spark provides guarantees in terms of fault tolerance, high availabili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.02321","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":""},"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":"1507.02321","created_at":"2026-05-18T01:37:07.003352+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.02321v1","created_at":"2026-05-18T01:37:07.003352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.02321","created_at":"2026-05-18T01:37:07.003352+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3TYZ4QPPQJ6","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3TYZ4QPPQJ62ZRY","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3TYZ4QP","created_at":"2026-05-18T12:29:50.041715+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/Y3TYZ4QPPQJ62ZRYL37DB6POV2","json":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2.json","graph_json":"https://pith.science/api/pith-number/Y3TYZ4QPPQJ62ZRYL37DB6POV2/graph.json","events_json":"https://pith.science/api/pith-number/Y3TYZ4QPPQJ62ZRYL37DB6POV2/events.json","paper":"https://pith.science/paper/Y3TYZ4QP"},"agent_actions":{"view_html":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2","download_json":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2.json","view_paper":"https://pith.science/paper/Y3TYZ4QP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.02321&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3TYZ4QPPQJ62ZRYL37DB6POV2/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3TYZ4QPPQJ62ZRYL37DB6POV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2/action/storage_attestation","attest_author":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2/action/author_attestation","sign_citation":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2/action/citation_signature","submit_replication":"https://pith.science/pith/Y3TYZ4QPPQJ62ZRYL37DB6POV2/action/replication_record"}},"created_at":"2026-05-18T01:37:07.003352+00:00","updated_at":"2026-05-18T01:37:07.003352+00:00"}