{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QMPVIUBG5DBOY4XH7DIFOCZM2A","short_pith_number":"pith:QMPVIUBG","schema_version":"1.0","canonical_sha256":"831f545026e8c2ec72e7f8d0570b2cd00ebdbb2433360b7745632b3baecf9d68","source":{"kind":"arxiv","id":"2506.09226","version":2},"attestation_state":"computed","paper":{"title":"Terabyte-Scale Analytics in the Blink of an Eye","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.PF"],"primary_cat":"cs.DB","authors_text":"Bowen Wu, Carlo Curino, Matteo Interlandi, Rathijit Sen, Wei Cui","submitted_at":"2025-06-10T20:30:31Z","abstract_excerpt":"For the past two decades, the DB community has devoted substantial research to take advantage of cheap clusters of machines for distributed data analytics -- we believe that we are at the beginning of a paradigm shift. The scaling laws and popularity of AI models lead to the deployment of incredibly powerful GPU clusters in commercial data centers. Compared to CPU-only solutions, these clusters deliver impressive improvements in per-node compute, memory bandwidth, and inter-node interconnect performance. In this paper, we study the problem of scaling analytical SQL queries on distributed clust"},"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":"2506.09226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-06-10T20:30:31Z","cross_cats_sorted":["cs.DC","cs.PF"],"title_canon_sha256":"faf2e39bfb74d3abc7462629c1aef8d73d2ccb74a098a852957511043b4367b3","abstract_canon_sha256":"c335d4effdad43a37d4971d8289b0f2a1be0e4d6d46a837a99a81f44c932edd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:24.507459Z","signature_b64":"U9zzIVo0m70CdBPW4PpUsUd9Aue1n/Oa84P2hFl0OdR2OHVRN8sbAq8bXCDPFSArw/LqF2+XzANQw3mMyvTqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"831f545026e8c2ec72e7f8d0570b2cd00ebdbb2433360b7745632b3baecf9d68","last_reissued_at":"2026-07-05T11:47:24.506948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:24.506948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Terabyte-Scale Analytics in the Blink of an Eye","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.PF"],"primary_cat":"cs.DB","authors_text":"Bowen Wu, Carlo Curino, Matteo Interlandi, Rathijit Sen, Wei Cui","submitted_at":"2025-06-10T20:30:31Z","abstract_excerpt":"For the past two decades, the DB community has devoted substantial research to take advantage of cheap clusters of machines for distributed data analytics -- we believe that we are at the beginning of a paradigm shift. The scaling laws and popularity of AI models lead to the deployment of incredibly powerful GPU clusters in commercial data centers. Compared to CPU-only solutions, these clusters deliver impressive improvements in per-node compute, memory bandwidth, and inter-node interconnect performance. In this paper, we study the problem of scaling analytical SQL queries on distributed clust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09226","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/2506.09226/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":"2506.09226","created_at":"2026-07-05T11:47:24.507009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09226v2","created_at":"2026-07-05T11:47:24.507009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09226","created_at":"2026-07-05T11:47:24.507009+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMPVIUBG5DBO","created_at":"2026-07-05T11:47:24.507009+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMPVIUBG5DBOY4XH","created_at":"2026-07-05T11:47:24.507009+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMPVIUBG","created_at":"2026-07-05T11:47:24.507009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.02862","citing_title":"PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15957","citing_title":"To GPU or Not to GPU: Vector Search in Relational Engines","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22437","citing_title":"veScale-FSDP: Flexible and High-Performance FSDP at Scale","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A","json":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A.json","graph_json":"https://pith.science/api/pith-number/QMPVIUBG5DBOY4XH7DIFOCZM2A/graph.json","events_json":"https://pith.science/api/pith-number/QMPVIUBG5DBOY4XH7DIFOCZM2A/events.json","paper":"https://pith.science/paper/QMPVIUBG"},"agent_actions":{"view_html":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A","download_json":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A.json","view_paper":"https://pith.science/paper/QMPVIUBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09226&json=true","fetch_graph":"https://pith.science/api/pith-number/QMPVIUBG5DBOY4XH7DIFOCZM2A/graph.json","fetch_events":"https://pith.science/api/pith-number/QMPVIUBG5DBOY4XH7DIFOCZM2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A/action/storage_attestation","attest_author":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A/action/author_attestation","sign_citation":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A/action/citation_signature","submit_replication":"https://pith.science/pith/QMPVIUBG5DBOY4XH7DIFOCZM2A/action/replication_record"}},"created_at":"2026-07-05T11:47:24.507009+00:00","updated_at":"2026-07-05T11:47:24.507009+00:00"}