{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6ZGNYH2GKWIPXDQVBJWBXEVXI3","short_pith_number":"pith:6ZGNYH2G","schema_version":"1.0","canonical_sha256":"f64cdc1f465590fb8e150a6c1b92b746eb8c6926db9698fffec605d4ef4e5fc1","source":{"kind":"arxiv","id":"1707.03527","version":1},"attestation_state":"computed","paper":{"title":"Oseba: Optimization for Selective Bulk Analysis in Big Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jun Wang, Rui Wang","submitted_at":"2017-07-12T03:42:21Z","abstract_excerpt":"Selective bulk analyses, such as statistical learning on temporal/spatial data, are fundamental to a wide range of contemporary data analysis. However, with the increasingly larger data-sets, such as weather data and marketing transactions, the data organization/access becomes more challenging in selective bulk data processing with the use of current big data processing frameworks such as Spark or keyvalue stores. In this paper, we propose a method to optimize selective bulk analysis in big data processing and referred to as Oseba. Oseba maintains a super index for the data organization in mem"},"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":"1707.03527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-07-12T03:42:21Z","cross_cats_sorted":[],"title_canon_sha256":"e9329ff861dc2bd152837e3d4c6226b35ffed0c5cc536b889758524a1da92fca","abstract_canon_sha256":"c797661cb174aebbb9b6f5a96c6664f9b4c51493350428a238778962b59c0c0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:25.725175Z","signature_b64":"XfZNiEdnjMj8dCMsCDDr3rkJUUOHUz2891UhIuK2HclmfL595Zk5gQ3YZQi2V+1CeL5AE2csVHWYQBTNzYzrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f64cdc1f465590fb8e150a6c1b92b746eb8c6926db9698fffec605d4ef4e5fc1","last_reissued_at":"2026-05-18T00:40:25.724652Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:25.724652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Oseba: Optimization for Selective Bulk Analysis in Big Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jun Wang, Rui Wang","submitted_at":"2017-07-12T03:42:21Z","abstract_excerpt":"Selective bulk analyses, such as statistical learning on temporal/spatial data, are fundamental to a wide range of contemporary data analysis. However, with the increasingly larger data-sets, such as weather data and marketing transactions, the data organization/access becomes more challenging in selective bulk data processing with the use of current big data processing frameworks such as Spark or keyvalue stores. In this paper, we propose a method to optimize selective bulk analysis in big data processing and referred to as Oseba. Oseba maintains a super index for the data organization in mem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03527","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":"1707.03527","created_at":"2026-05-18T00:40:25.724721+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.03527v1","created_at":"2026-05-18T00:40:25.724721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03527","created_at":"2026-05-18T00:40:25.724721+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZGNYH2GKWIP","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZGNYH2GKWIPXDQV","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZGNYH2G","created_at":"2026-05-18T12:31:03.183658+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/6ZGNYH2GKWIPXDQVBJWBXEVXI3","json":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3.json","graph_json":"https://pith.science/api/pith-number/6ZGNYH2GKWIPXDQVBJWBXEVXI3/graph.json","events_json":"https://pith.science/api/pith-number/6ZGNYH2GKWIPXDQVBJWBXEVXI3/events.json","paper":"https://pith.science/paper/6ZGNYH2G"},"agent_actions":{"view_html":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3","download_json":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3.json","view_paper":"https://pith.science/paper/6ZGNYH2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.03527&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZGNYH2GKWIPXDQVBJWBXEVXI3/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZGNYH2GKWIPXDQVBJWBXEVXI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/action/storage_attestation","attest_author":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/action/author_attestation","sign_citation":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/action/citation_signature","submit_replication":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/action/replication_record"}},"created_at":"2026-05-18T00:40:25.724721+00:00","updated_at":"2026-05-18T00:40:25.724721+00:00"}