{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EQWEU7JEJ3MWKBN5IOG3SPMKVU","short_pith_number":"pith:EQWEU7JE","schema_version":"1.0","canonical_sha256":"242c4a7d244ed96505bd438db93d8aad38c1939bda4449981408b4b25aaae65c","source":{"kind":"arxiv","id":"1810.00511","version":2},"attestation_state":"computed","paper":{"title":"Chasing Similarity: Distribution-aware Aggregation Scheduling (Extended Version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anastasios Sidiropoulos, Ario Salmasi, Feilong Liu, Spyros Blanas","submitted_at":"2018-10-01T02:58:34Z","abstract_excerpt":"Parallel aggregation is a ubiquitous operation in data analytics that is expressed as GROUP BY in SQL, reduce in Hadoop, or segment in TensorFlow. Parallel aggregation starts with an optional local pre-aggregation step and then repartitions the intermediate result across the network. While local pre-aggregation works well for low-cardinality aggregations, the network communication cost remains significant for high-cardinality aggregations even after local pre-aggregation. The problem is that the repartition-based algorithm for high-cardinality aggregation does not fully utilize the network.\n  "},"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":"1810.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-01T02:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"d112e3427af9de0fba3e3c0824cfb102d1a0b8836d43cf8c2367d4d403831870","abstract_canon_sha256":"ed3b93340dc2fb372ce674ef340ff856297c830aba753e8540a87c044c431a0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:38.227756Z","signature_b64":"j3xJ1idJlbU0XKbD9d6ygQkA+3uA5ZQ5Qqfr2BccWmoEgU+8nbA64kyNQCYBya0agdBRcuxqKhWq1qxvUQvKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"242c4a7d244ed96505bd438db93d8aad38c1939bda4449981408b4b25aaae65c","last_reissued_at":"2026-05-17T23:59:38.227023Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:38.227023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chasing Similarity: Distribution-aware Aggregation Scheduling (Extended Version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anastasios Sidiropoulos, Ario Salmasi, Feilong Liu, Spyros Blanas","submitted_at":"2018-10-01T02:58:34Z","abstract_excerpt":"Parallel aggregation is a ubiquitous operation in data analytics that is expressed as GROUP BY in SQL, reduce in Hadoop, or segment in TensorFlow. Parallel aggregation starts with an optional local pre-aggregation step and then repartitions the intermediate result across the network. While local pre-aggregation works well for low-cardinality aggregations, the network communication cost remains significant for high-cardinality aggregations even after local pre-aggregation. The problem is that the repartition-based algorithm for high-cardinality aggregation does not fully utilize the network.\n  "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00511","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":"1810.00511","created_at":"2026-05-17T23:59:38.227132+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.00511v2","created_at":"2026-05-17T23:59:38.227132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00511","created_at":"2026-05-17T23:59:38.227132+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQWEU7JEJ3MW","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQWEU7JEJ3MWKBN5","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQWEU7JE","created_at":"2026-05-18T12:32:22.470017+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/EQWEU7JEJ3MWKBN5IOG3SPMKVU","json":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU.json","graph_json":"https://pith.science/api/pith-number/EQWEU7JEJ3MWKBN5IOG3SPMKVU/graph.json","events_json":"https://pith.science/api/pith-number/EQWEU7JEJ3MWKBN5IOG3SPMKVU/events.json","paper":"https://pith.science/paper/EQWEU7JE"},"agent_actions":{"view_html":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU","download_json":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU.json","view_paper":"https://pith.science/paper/EQWEU7JE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.00511&json=true","fetch_graph":"https://pith.science/api/pith-number/EQWEU7JEJ3MWKBN5IOG3SPMKVU/graph.json","fetch_events":"https://pith.science/api/pith-number/EQWEU7JEJ3MWKBN5IOG3SPMKVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/action/storage_attestation","attest_author":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/action/author_attestation","sign_citation":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/action/citation_signature","submit_replication":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/action/replication_record"}},"created_at":"2026-05-17T23:59:38.227132+00:00","updated_at":"2026-05-17T23:59:38.227132+00:00"}