{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z5Q66KDBKT4YQQCLGBB2LC4UKX","short_pith_number":"pith:Z5Q66KDB","schema_version":"1.0","canonical_sha256":"cf61ef286154f988404b3043a58b9455c82ae7f80436224eec62f2f70a421415","source":{"kind":"arxiv","id":"2412.01709","version":1},"attestation_state":"computed","paper":{"title":"Query Performance Explanation through Large Language Model for HTAP Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Haibo Xiu, Jianjun Chen, Jun Yang, Li Zhang, Tieying Zhang","submitted_at":"2024-12-02T16:55:07Z","abstract_excerpt":"In hybrid transactional and analytical processing (HTAP) systems, users often struggle to understand why query plans from one engine (OLAP or OLTP) perform significantly slower than those from another. Although optimizers provide plan details via the EXPLAIN function, these explanations are frequently too technical for non-experts and offer limited insights into performance differences across engines. To address this, we propose a novel framework that leverages large language models (LLMs) to explain query performance in HTAP systems. Built on Retrieval-Augmented Generation (RAG), our framewor"},"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":"2412.01709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-12-02T16:55:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"274353bea7acaba6a3966c2c7f66cc9608117cce2996db36c127ac788f517eef","abstract_canon_sha256":"9d99405ffca00dcc4a8d32560f958d783831580fff6f472d3cc57bc20b9d5354"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:17.813153Z","signature_b64":"hDhJo6j6WXPY4LiLaKyoCyyUQjXYnJZ8768ksWO+DiyEa1TkbD3ZmkRv12WzfVmR52TbT+v96RFFQN4ygZSKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf61ef286154f988404b3043a58b9455c82ae7f80436224eec62f2f70a421415","last_reissued_at":"2026-07-05T09:43:17.810924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:17.810924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query Performance Explanation through Large Language Model for HTAP Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Haibo Xiu, Jianjun Chen, Jun Yang, Li Zhang, Tieying Zhang","submitted_at":"2024-12-02T16:55:07Z","abstract_excerpt":"In hybrid transactional and analytical processing (HTAP) systems, users often struggle to understand why query plans from one engine (OLAP or OLTP) perform significantly slower than those from another. Although optimizers provide plan details via the EXPLAIN function, these explanations are frequently too technical for non-experts and offer limited insights into performance differences across engines. To address this, we propose a novel framework that leverages large language models (LLMs) to explain query performance in HTAP systems. Built on Retrieval-Augmented Generation (RAG), our framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01709","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/2412.01709/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":"2412.01709","created_at":"2026-07-05T09:43:17.812499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01709v1","created_at":"2026-07-05T09:43:17.812499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01709","created_at":"2026-07-05T09:43:17.812499+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5Q66KDBKT4Y","created_at":"2026-07-05T09:43:17.812499+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5Q66KDBKT4YQQCL","created_at":"2026-07-05T09:43:17.812499+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5Q66KDB","created_at":"2026-07-05T09:43:17.812499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06298","citing_title":"MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX","json":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX.json","graph_json":"https://pith.science/api/pith-number/Z5Q66KDBKT4YQQCLGBB2LC4UKX/graph.json","events_json":"https://pith.science/api/pith-number/Z5Q66KDBKT4YQQCLGBB2LC4UKX/events.json","paper":"https://pith.science/paper/Z5Q66KDB"},"agent_actions":{"view_html":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX","download_json":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX.json","view_paper":"https://pith.science/paper/Z5Q66KDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01709&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5Q66KDBKT4YQQCLGBB2LC4UKX/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5Q66KDBKT4YQQCLGBB2LC4UKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX/action/storage_attestation","attest_author":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX/action/author_attestation","sign_citation":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX/action/citation_signature","submit_replication":"https://pith.science/pith/Z5Q66KDBKT4YQQCLGBB2LC4UKX/action/replication_record"}},"created_at":"2026-07-05T09:43:17.812499+00:00","updated_at":"2026-07-05T09:43:17.812499+00:00"}