{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JQQWWX4BFGBTR3FDC45VMX562C","short_pith_number":"pith:JQQWWX4B","schema_version":"1.0","canonical_sha256":"4c216b5f81298338eca3173b565fbed0ab3540dd24dd861c0a5fb9d29c1d7e20","source":{"kind":"arxiv","id":"2512.02862","version":2},"attestation_state":"computed","paper":{"title":"PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Carsten Binnig, Jigao Luo, Muhammad El-Hindi, Nils Boeschen","submitted_at":"2025-12-02T15:22:06Z","abstract_excerpt":"The AI hardware boom has led modern data centers to adopt HPC-style architectures centered on distributed, GPU-centric computation. Large GPU clusters interconnected by fast RDMA networks and backed by high-bandwidth NVMe storage enable scalable computation and rapid access to storage-resident data. Tensor computation runtimes (TCRs), such as PyTorch, originally designed for AI workloads, have recently been shown to accelerate analytical workloads. However, prior work has primarily considered settings where the data fits in aggregated GPU memory. In this paper, we systematically study how TCRs"},"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":"2512.02862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-12-02T15:22:06Z","cross_cats_sorted":[],"title_canon_sha256":"bf583989bb0db74c00c74217308b6457100e9c7819ae3e794792e0620e85cba5","abstract_canon_sha256":"1df4511dae883abb8731d5a824f1e4e76d2b0a30c4e3a651be40affc2e2ce1ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:07.338102Z","signature_b64":"/M//XJYGjUaID1N9XAYHb4HFiOlGJ7tZ82D8ggGHQIbLtMqjBuHY9wYyaD1pkvYLwS987fY8qBXkg8HKJZpSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c216b5f81298338eca3173b565fbed0ab3540dd24dd861c0a5fb9d29c1d7e20","last_reissued_at":"2026-05-20T01:06:07.337196Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:07.337196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Carsten Binnig, Jigao Luo, Muhammad El-Hindi, Nils Boeschen","submitted_at":"2025-12-02T15:22:06Z","abstract_excerpt":"The AI hardware boom has led modern data centers to adopt HPC-style architectures centered on distributed, GPU-centric computation. Large GPU clusters interconnected by fast RDMA networks and backed by high-bandwidth NVMe storage enable scalable computation and rapid access to storage-resident data. Tensor computation runtimes (TCRs), such as PyTorch, originally designed for AI workloads, have recently been shown to accelerate analytical workloads. However, prior work has primarily considered settings where the data fits in aggregated GPU memory. In this paper, we systematically study how TCRs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02862","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/2512.02862/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":"2512.02862","created_at":"2026-05-20T01:06:07.337332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.02862v2","created_at":"2026-05-20T01:06:07.337332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02862","created_at":"2026-05-20T01:06:07.337332+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQQWWX4BFGBT","created_at":"2026-05-20T01:06:07.337332+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQQWWX4BFGBTR3FD","created_at":"2026-05-20T01:06:07.337332+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQQWWX4B","created_at":"2026-05-20T01:06:07.337332+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/JQQWWX4BFGBTR3FDC45VMX562C","json":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C.json","graph_json":"https://pith.science/api/pith-number/JQQWWX4BFGBTR3FDC45VMX562C/graph.json","events_json":"https://pith.science/api/pith-number/JQQWWX4BFGBTR3FDC45VMX562C/events.json","paper":"https://pith.science/paper/JQQWWX4B"},"agent_actions":{"view_html":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C","download_json":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C.json","view_paper":"https://pith.science/paper/JQQWWX4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.02862&json=true","fetch_graph":"https://pith.science/api/pith-number/JQQWWX4BFGBTR3FDC45VMX562C/graph.json","fetch_events":"https://pith.science/api/pith-number/JQQWWX4BFGBTR3FDC45VMX562C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C/action/storage_attestation","attest_author":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C/action/author_attestation","sign_citation":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C/action/citation_signature","submit_replication":"https://pith.science/pith/JQQWWX4BFGBTR3FDC45VMX562C/action/replication_record"}},"created_at":"2026-05-20T01:06:07.337332+00:00","updated_at":"2026-05-20T01:06:07.337332+00:00"}