{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DB5EMB6MYHBAI6IKWZUPJIUYWC","short_pith_number":"pith:DB5EMB6M","schema_version":"1.0","canonical_sha256":"187a4607ccc1c204790ab668f4a298b0b3818a7fedaf5075cd9df2966671d70a","source":{"kind":"arxiv","id":"2504.17181","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Learned Query Performance Prediction Models at LinkedIn: Challenges, Opportunities, and Findings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chujun Song, Daniel Abadi, Erik Krogen, Slim Bouguerra","submitted_at":"2025-04-24T01:35:34Z","abstract_excerpt":"Recent advancements in learning-based query performance prediction models have demonstrated remarkable efficacy. However, these models are predominantly validated using synthetic datasets focused on cardinality or latency estimations. This paper explores the application of these models to LinkedIn's complex real-world OLAP queries executed on Trino, addressing four primary research questions: (1) How do these models perform on real-world industrial data with limited information? (2) Can these models generalize to new tasks, such as CPU time prediction and classification? (3) What additional in"},"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":"2504.17181","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-04-24T01:35:34Z","cross_cats_sorted":[],"title_canon_sha256":"050164c674dc53f994bc81415ef1cae0e2a6340c19c6214e11ae31743b00fb8c","abstract_canon_sha256":"c29f87bc4f11d272f751a4869a9ab2ff5b5955e2b41c393bc0fe7cc3ec7b9077"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:23.823696Z","signature_b64":"eHCeedH2WqRT4TZM60iu47QMVgsVbqrlIZ/T03yHZWoQZa46iz5PFhGugKHlDWW5QiYQowLcZ4B+gcuKaAhSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"187a4607ccc1c204790ab668f4a298b0b3818a7fedaf5075cd9df2966671d70a","last_reissued_at":"2026-07-05T10:53:23.823306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:23.823306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Learned Query Performance Prediction Models at LinkedIn: Challenges, Opportunities, and Findings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chujun Song, Daniel Abadi, Erik Krogen, Slim Bouguerra","submitted_at":"2025-04-24T01:35:34Z","abstract_excerpt":"Recent advancements in learning-based query performance prediction models have demonstrated remarkable efficacy. However, these models are predominantly validated using synthetic datasets focused on cardinality or latency estimations. This paper explores the application of these models to LinkedIn's complex real-world OLAP queries executed on Trino, addressing four primary research questions: (1) How do these models perform on real-world industrial data with limited information? (2) Can these models generalize to new tasks, such as CPU time prediction and classification? (3) What additional in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17181","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/2504.17181/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":"2504.17181","created_at":"2026-07-05T10:53:23.823366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17181v1","created_at":"2026-07-05T10:53:23.823366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17181","created_at":"2026-07-05T10:53:23.823366+00:00"},{"alias_kind":"pith_short_12","alias_value":"DB5EMB6MYHBA","created_at":"2026-07-05T10:53:23.823366+00:00"},{"alias_kind":"pith_short_16","alias_value":"DB5EMB6MYHBAI6IK","created_at":"2026-07-05T10:53:23.823366+00:00"},{"alias_kind":"pith_short_8","alias_value":"DB5EMB6M","created_at":"2026-07-05T10:53:23.823366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07945","citing_title":"ScaleSense: Cost-Intelligent Scaling Framework via Learned Resource Estimation in Alibaba AnalyticDB","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC","json":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC.json","graph_json":"https://pith.science/api/pith-number/DB5EMB6MYHBAI6IKWZUPJIUYWC/graph.json","events_json":"https://pith.science/api/pith-number/DB5EMB6MYHBAI6IKWZUPJIUYWC/events.json","paper":"https://pith.science/paper/DB5EMB6M"},"agent_actions":{"view_html":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC","download_json":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC.json","view_paper":"https://pith.science/paper/DB5EMB6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17181&json=true","fetch_graph":"https://pith.science/api/pith-number/DB5EMB6MYHBAI6IKWZUPJIUYWC/graph.json","fetch_events":"https://pith.science/api/pith-number/DB5EMB6MYHBAI6IKWZUPJIUYWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC/action/storage_attestation","attest_author":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC/action/author_attestation","sign_citation":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC/action/citation_signature","submit_replication":"https://pith.science/pith/DB5EMB6MYHBAI6IKWZUPJIUYWC/action/replication_record"}},"created_at":"2026-07-05T10:53:23.823366+00:00","updated_at":"2026-07-05T10:53:23.823366+00:00"}