{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TDAMF4FIOORLX6ICSVPFTRLJZA","short_pith_number":"pith:TDAMF4FI","schema_version":"1.0","canonical_sha256":"98c0c2f0a873a2bbf902955e59c569c81d9310d460651c3e8f774210defede7d","source":{"kind":"arxiv","id":"2306.06798","version":2},"attestation_state":"computed","paper":{"title":"Kepler: Robust Learning for Faster Parametric Query Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Campbell Fraser, Deniz Altinb\\\"uken, Eugene Brevdo, Gaurav Jain, Haoyu Huang, Lyric Doshi, Ryan Marcus, Vincent Zhuang","submitted_at":"2023-06-11T22:39:28Z","abstract_excerpt":"Most existing parametric query optimization (PQO) techniques rely on traditional query optimizer cost models, which are often inaccurate and result in suboptimal query performance. We propose Kepler, an end-to-end learning-based approach to PQO that demonstrates significant speedups in query latency over a traditional query optimizer. Central to our method is Row Count Evolution (RCE), a novel plan generation algorithm based on perturbations in the sub-plan cardinality space. While previous approaches require accurate cost models, we bypass this requirement by evaluating candidate plans via ac"},"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":"2306.06798","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-06-11T22:39:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"187909ced6607fd412335b5a03324d9574354925236f9cd58f75f81eb9197cf4","abstract_canon_sha256":"657113f7f15807c5082be0ac5ae00e0bdceea7ae8fb0709bb88feac8ba5f2be2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:30.182330Z","signature_b64":"9HxuRdGpL09S5IZxyaKkHSJuPLpxLDoYOwkI2paKW2rvXIDVrpn/xNdyumXNqEpxAwRBnTYX8j/bQiJ/J730DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98c0c2f0a873a2bbf902955e59c569c81d9310d460651c3e8f774210defede7d","last_reissued_at":"2026-07-05T07:02:30.181833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:30.181833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kepler: Robust Learning for Faster Parametric Query Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Campbell Fraser, Deniz Altinb\\\"uken, Eugene Brevdo, Gaurav Jain, Haoyu Huang, Lyric Doshi, Ryan Marcus, Vincent Zhuang","submitted_at":"2023-06-11T22:39:28Z","abstract_excerpt":"Most existing parametric query optimization (PQO) techniques rely on traditional query optimizer cost models, which are often inaccurate and result in suboptimal query performance. We propose Kepler, an end-to-end learning-based approach to PQO that demonstrates significant speedups in query latency over a traditional query optimizer. Central to our method is Row Count Evolution (RCE), a novel plan generation algorithm based on perturbations in the sub-plan cardinality space. While previous approaches require accurate cost models, we bypass this requirement by evaluating candidate plans via ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06798","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/2306.06798/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":"2306.06798","created_at":"2026-07-05T07:02:30.181885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06798v2","created_at":"2026-07-05T07:02:30.181885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06798","created_at":"2026-07-05T07:02:30.181885+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDAMF4FIOORL","created_at":"2026-07-05T07:02:30.181885+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDAMF4FIOORLX6IC","created_at":"2026-07-05T07:02:30.181885+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDAMF4FI","created_at":"2026-07-05T07:02:30.181885+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/TDAMF4FIOORLX6ICSVPFTRLJZA","json":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA.json","graph_json":"https://pith.science/api/pith-number/TDAMF4FIOORLX6ICSVPFTRLJZA/graph.json","events_json":"https://pith.science/api/pith-number/TDAMF4FIOORLX6ICSVPFTRLJZA/events.json","paper":"https://pith.science/paper/TDAMF4FI"},"agent_actions":{"view_html":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA","download_json":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA.json","view_paper":"https://pith.science/paper/TDAMF4FI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06798&json=true","fetch_graph":"https://pith.science/api/pith-number/TDAMF4FIOORLX6ICSVPFTRLJZA/graph.json","fetch_events":"https://pith.science/api/pith-number/TDAMF4FIOORLX6ICSVPFTRLJZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA/action/storage_attestation","attest_author":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA/action/author_attestation","sign_citation":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA/action/citation_signature","submit_replication":"https://pith.science/pith/TDAMF4FIOORLX6ICSVPFTRLJZA/action/replication_record"}},"created_at":"2026-07-05T07:02:30.181885+00:00","updated_at":"2026-07-05T07:02:30.181885+00:00"}