{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CK6KOFS4QQGPBQZPQLNMM4WGQB","short_pith_number":"pith:CK6KOFS4","schema_version":"1.0","canonical_sha256":"12bca7165c840cf0c32f82dac672c6807d1cddb0e1aa3dcda11ce5a7eb9feccb","source":{"kind":"arxiv","id":"1703.01148","version":3},"attestation_state":"computed","paper":{"title":"Runtime Optimization of Join Location in Parallel Data Management Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.DB","authors_text":"Bikash Chandra, S. Sudarshan","submitted_at":"2017-03-03T13:21:25Z","abstract_excerpt":"Applications running on parallel systems often need to join a streaming relation or a stored relation with data indexed in a parallel data storage system. Some applications also compute UDFs on the joined tuples. The join can be done at the data storage nodes, corresponding to reduce side joins, or by fetching data from the storage system to compute nodes, corresponding to map side join. Both may be suboptimal: reduce side joins may cause skew, while map side joins may lead to a lot of data being transferred and replicated.\n  In this paper, we present techniques to make runtime decisions betwe"},"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":"1703.01148","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-03T13:21:25Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"a5b4c9b8ad2c1c1fbe9858f924540731bd4876f3c6181617ff6285de78b3775c","abstract_canon_sha256":"06e4dae040fb1d3342ac2a9c4256c8dad3e3f7a5480ee7202761fb7af3bb01f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:12.614277Z","signature_b64":"Qxi1zDJLJ2+8nfWGkwzN45gfZS7Wkll08J+tLXkCQ5lruZDOa+YcTBT2kDWJFMosjYQMg8AMj7egDUVnhwgiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12bca7165c840cf0c32f82dac672c6807d1cddb0e1aa3dcda11ce5a7eb9feccb","last_reissued_at":"2026-05-18T00:39:12.613683Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:12.613683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Runtime Optimization of Join Location in Parallel Data Management Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.DB","authors_text":"Bikash Chandra, S. Sudarshan","submitted_at":"2017-03-03T13:21:25Z","abstract_excerpt":"Applications running on parallel systems often need to join a streaming relation or a stored relation with data indexed in a parallel data storage system. Some applications also compute UDFs on the joined tuples. The join can be done at the data storage nodes, corresponding to reduce side joins, or by fetching data from the storage system to compute nodes, corresponding to map side join. Both may be suboptimal: reduce side joins may cause skew, while map side joins may lead to a lot of data being transferred and replicated.\n  In this paper, we present techniques to make runtime decisions betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01148","kind":"arxiv","version":3},"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":"1703.01148","created_at":"2026-05-18T00:39:12.613773+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01148v3","created_at":"2026-05-18T00:39:12.613773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01148","created_at":"2026-05-18T00:39:12.613773+00:00"},{"alias_kind":"pith_short_12","alias_value":"CK6KOFS4QQGP","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CK6KOFS4QQGPBQZP","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CK6KOFS4","created_at":"2026-05-18T12:31:10.602751+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/CK6KOFS4QQGPBQZPQLNMM4WGQB","json":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB.json","graph_json":"https://pith.science/api/pith-number/CK6KOFS4QQGPBQZPQLNMM4WGQB/graph.json","events_json":"https://pith.science/api/pith-number/CK6KOFS4QQGPBQZPQLNMM4WGQB/events.json","paper":"https://pith.science/paper/CK6KOFS4"},"agent_actions":{"view_html":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB","download_json":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB.json","view_paper":"https://pith.science/paper/CK6KOFS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01148&json=true","fetch_graph":"https://pith.science/api/pith-number/CK6KOFS4QQGPBQZPQLNMM4WGQB/graph.json","fetch_events":"https://pith.science/api/pith-number/CK6KOFS4QQGPBQZPQLNMM4WGQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB/action/storage_attestation","attest_author":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB/action/author_attestation","sign_citation":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB/action/citation_signature","submit_replication":"https://pith.science/pith/CK6KOFS4QQGPBQZPQLNMM4WGQB/action/replication_record"}},"created_at":"2026-05-18T00:39:12.613773+00:00","updated_at":"2026-05-18T00:39:12.613773+00:00"}