{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6KQKUIOZ2AVYES4YCAMQR67JQU","short_pith_number":"pith:6KQKUIOZ","schema_version":"1.0","canonical_sha256":"f2a0aa21d9d02b824b98101908fbe9850e02ebc254843925332fb543649b9186","source":{"kind":"arxiv","id":"2608.03794","version":1},"attestation_state":"computed","paper":{"title":"Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Dongsheng Shi, Gerard de Melo, Linlin Wang, Shunfan Zheng, Xin Yi, Yue Li","submitted_at":"2026-08-04T15:10:09Z","abstract_excerpt":"Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs). However, current evaluation benchmarks remain disproportionately fixated on Text-to-SQL tasks, neglecting the holistic Database Lifecycle-from initial schema design to post-deployment maintenance. This narrow focus fails to capture the diverse capabilities required for real-world database management. To bridge this gap, we introduce DBLifeBench, the first benchmark to evaluate LLMs across five critical lifecycle phases: Design, Imple"},"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":"2608.03794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-08-04T15:10:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"359f16a819c0d5621b8831a847cab660168119c3c89d37f729aa0ab7794b58f4","abstract_canon_sha256":"b4ae8f71e9e329c222a98463c09b9737398b80eb65b9fcfdbb1fe9ead1b2a286"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:08.071831Z","signature_b64":"Xe1JYlqN6ifOZGjLDkqORS8bZ1oiUdlPbz00/ePQfFhWa5OGjRjL6Tg06Q3EJ/+3wGmdAonLFV2ytEQo/OT5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a0aa21d9d02b824b98101908fbe9850e02ebc254843925332fb543649b9186","last_reissued_at":"2026-08-05T01:37:08.070319Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:08.070319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Dongsheng Shi, Gerard de Melo, Linlin Wang, Shunfan Zheng, Xin Yi, Yue Li","submitted_at":"2026-08-04T15:10:09Z","abstract_excerpt":"Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs). However, current evaluation benchmarks remain disproportionately fixated on Text-to-SQL tasks, neglecting the holistic Database Lifecycle-from initial schema design to post-deployment maintenance. This narrow focus fails to capture the diverse capabilities required for real-world database management. To bridge this gap, we introduce DBLifeBench, the first benchmark to evaluate LLMs across five critical lifecycle phases: Design, Imple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03794","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/2608.03794/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":"2608.03794","created_at":"2026-08-05T01:37:08.070855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03794v1","created_at":"2026-08-05T01:37:08.070855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03794","created_at":"2026-08-05T01:37:08.070855+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KQKUIOZ2AVY","created_at":"2026-08-05T01:37:08.070855+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KQKUIOZ2AVYES4Y","created_at":"2026-08-05T01:37:08.070855+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KQKUIOZ","created_at":"2026-08-05T01:37:08.070855+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/6KQKUIOZ2AVYES4YCAMQR67JQU","json":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU.json","graph_json":"https://pith.science/api/pith-number/6KQKUIOZ2AVYES4YCAMQR67JQU/graph.json","events_json":"https://pith.science/api/pith-number/6KQKUIOZ2AVYES4YCAMQR67JQU/events.json","paper":"https://pith.science/paper/6KQKUIOZ"},"agent_actions":{"view_html":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU","download_json":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU.json","view_paper":"https://pith.science/paper/6KQKUIOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03794&json=true","fetch_graph":"https://pith.science/api/pith-number/6KQKUIOZ2AVYES4YCAMQR67JQU/graph.json","fetch_events":"https://pith.science/api/pith-number/6KQKUIOZ2AVYES4YCAMQR67JQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU/action/storage_attestation","attest_author":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU/action/author_attestation","sign_citation":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU/action/citation_signature","submit_replication":"https://pith.science/pith/6KQKUIOZ2AVYES4YCAMQR67JQU/action/replication_record"}},"created_at":"2026-08-05T01:37:08.070855+00:00","updated_at":"2026-08-05T01:37:08.070855+00:00"}