{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D65JUSRBLYOECG7FTDHNA6WPMF","short_pith_number":"pith:D65JUSRB","schema_version":"1.0","canonical_sha256":"1fba9a4a215e1c411be598ced07acf6157f634e48307ca14b662784976fa91e4","source":{"kind":"arxiv","id":"2506.02802","version":1},"attestation_state":"computed","paper":{"title":"A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Andr\\'as Strausz, Ioana Giurgiu, Niels Pardon","submitted_at":"2025-06-03T12:32:56Z","abstract_excerpt":"Lakehouse systems enable the same data to be queried with multiple execution engines. However, selecting the engine best suited to run a SQL query still requires a priori knowledge of the query computational requirements and an engine capability, a complex and manual task that only becomes more difficult with the emergence of new engines and workloads. In this paper, we address this limitation by proposing a cross-engine optimizer that can automate engine selection for diverse SQL queries through a learned cost model. Optimized with hints, a query plan is used for query cost prediction and rou"},"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":"2506.02802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.DB","submitted_at":"2025-06-03T12:32:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"814ae2dde2e249bbb334f72694580e3104babc6ce59fc8f05d652fa0a8e88ac2","abstract_canon_sha256":"22156d5b4cb2713d3db9f2160668fad8f1684432a84e434970a0cbcb2b70f1f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:09.388053Z","signature_b64":"hn+UtFxsCIxD8rkECiN7+ABudXH6DGuG8RfysBZLrSxetTeIe1qDRGGnb4vU9DKq1bZLYoM/tcRlgZT/F104Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fba9a4a215e1c411be598ced07acf6157f634e48307ca14b662784976fa91e4","last_reissued_at":"2026-07-05T11:15:09.387646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:09.387646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Andr\\'as Strausz, Ioana Giurgiu, Niels Pardon","submitted_at":"2025-06-03T12:32:56Z","abstract_excerpt":"Lakehouse systems enable the same data to be queried with multiple execution engines. However, selecting the engine best suited to run a SQL query still requires a priori knowledge of the query computational requirements and an engine capability, a complex and manual task that only becomes more difficult with the emergence of new engines and workloads. In this paper, we address this limitation by proposing a cross-engine optimizer that can automate engine selection for diverse SQL queries through a learned cost model. Optimized with hints, a query plan is used for query cost prediction and rou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02802","kind":"arxiv","version":1},"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/2506.02802/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":"2506.02802","created_at":"2026-07-05T11:15:09.387707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02802v1","created_at":"2026-07-05T11:15:09.387707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02802","created_at":"2026-07-05T11:15:09.387707+00:00"},{"alias_kind":"pith_short_12","alias_value":"D65JUSRBLYOE","created_at":"2026-07-05T11:15:09.387707+00:00"},{"alias_kind":"pith_short_16","alias_value":"D65JUSRBLYOECG7F","created_at":"2026-07-05T11:15:09.387707+00:00"},{"alias_kind":"pith_short_8","alias_value":"D65JUSRB","created_at":"2026-07-05T11:15:09.387707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.11001","citing_title":"Rethinking Query Optimization for Multi-Agent Systems [Vision]","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF","json":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF.json","graph_json":"https://pith.science/api/pith-number/D65JUSRBLYOECG7FTDHNA6WPMF/graph.json","events_json":"https://pith.science/api/pith-number/D65JUSRBLYOECG7FTDHNA6WPMF/events.json","paper":"https://pith.science/paper/D65JUSRB"},"agent_actions":{"view_html":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF","download_json":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF.json","view_paper":"https://pith.science/paper/D65JUSRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02802&json=true","fetch_graph":"https://pith.science/api/pith-number/D65JUSRBLYOECG7FTDHNA6WPMF/graph.json","fetch_events":"https://pith.science/api/pith-number/D65JUSRBLYOECG7FTDHNA6WPMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF/action/storage_attestation","attest_author":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF/action/author_attestation","sign_citation":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF/action/citation_signature","submit_replication":"https://pith.science/pith/D65JUSRBLYOECG7FTDHNA6WPMF/action/replication_record"}},"created_at":"2026-07-05T11:15:09.387707+00:00","updated_at":"2026-07-05T11:15:09.387707+00:00"}