{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RUMZ6BTDA7O3ZJ2YPANUO3EQ44","short_pith_number":"pith:RUMZ6BTD","schema_version":"1.0","canonical_sha256":"8d199f066307ddbca758781b476c90e733e8ed07519e2de8a8867e55f1da896a","source":{"kind":"arxiv","id":"2505.04153","version":2},"attestation_state":"computed","paper":{"title":"Global Hash Tables Strike Back! An Analysis of Parallel GROUP BY Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Daniel Xue, Ryan Marcus","submitted_at":"2025-05-07T06:06:46Z","abstract_excerpt":"Efficiently computing group aggregations (i.e., GROUP BY) on modern architectures is critical for analytic database systems. Hash-based approaches in today's engines predominantly use a partitioned approach, in which incoming data is partitioned by key values so that every row for a particular key is sent to the same thread. In this paper, we revisit a simpler strategy: a fully concurrent aggregation technique using a shared hash table. While approaches using general-purpose concurrent hash tables have generally been found to perform worse than partitioning-based approaches, we argue that the "},"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":"2505.04153","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-05-07T06:06:46Z","cross_cats_sorted":[],"title_canon_sha256":"a88e112a35ff2dfe7a57b98cb4ac28b0c4b758abbcf58259cc6e58fee26ccd6c","abstract_canon_sha256":"59c7931b04a9b1b5a99d86e6ac738d99ec79b9458c8dfc1a288b8bd7e22699b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:16.535542Z","signature_b64":"dAlLfiV7cBkaK8RkMr7MuPtinwAhdREypdC42ppBGEldmmtoEvaAwi8ARueOfUI8pSIp5i8FMD31XpmzkHYRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d199f066307ddbca758781b476c90e733e8ed07519e2de8a8867e55f1da896a","last_reissued_at":"2026-07-05T12:05:16.532755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:16.532755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Hash Tables Strike Back! An Analysis of Parallel GROUP BY Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Daniel Xue, Ryan Marcus","submitted_at":"2025-05-07T06:06:46Z","abstract_excerpt":"Efficiently computing group aggregations (i.e., GROUP BY) on modern architectures is critical for analytic database systems. Hash-based approaches in today's engines predominantly use a partitioned approach, in which incoming data is partitioned by key values so that every row for a particular key is sent to the same thread. In this paper, we revisit a simpler strategy: a fully concurrent aggregation technique using a shared hash table. While approaches using general-purpose concurrent hash tables have generally been found to perform worse than partitioning-based approaches, we argue that the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04153","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.04153/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2505.04153","created_at":"2026-07-05T12:05:16.534218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04153v2","created_at":"2026-07-05T12:05:16.534218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04153","created_at":"2026-07-05T12:05:16.534218+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUMZ6BTDA7O3","created_at":"2026-07-05T12:05:16.534218+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUMZ6BTDA7O3ZJ2Y","created_at":"2026-07-05T12:05:16.534218+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUMZ6BTD","created_at":"2026-07-05T12:05:16.534218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29099","citing_title":"One Ring to Shuffle Them All: Scalable Intra-Process Data Redistribution with Ring-Buffer Shuffle in Redpanda Oxla","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44","json":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44.json","graph_json":"https://pith.science/api/pith-number/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/graph.json","events_json":"https://pith.science/api/pith-number/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/events.json","paper":"https://pith.science/paper/RUMZ6BTD"},"agent_actions":{"view_html":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44","download_json":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44.json","view_paper":"https://pith.science/paper/RUMZ6BTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04153&json=true","fetch_graph":"https://pith.science/api/pith-number/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/graph.json","fetch_events":"https://pith.science/api/pith-number/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/action/storage_attestation","attest_author":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/action/author_attestation","sign_citation":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/action/citation_signature","submit_replication":"https://pith.science/pith/RUMZ6BTDA7O3ZJ2YPANUO3EQ44/action/replication_record"}},"created_at":"2026-07-05T12:05:16.534218+00:00","updated_at":"2026-07-05T12:05:16.534218+00:00"}