{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MAAE26E7TCF7PIFV7XCK6CZK37","short_pith_number":"pith:MAAE26E7","schema_version":"1.0","canonical_sha256":"60004d789f988bf7a0b5fdc4af0b2adfdec806a1d319fc985841a01fccfab6fe","source":{"kind":"arxiv","id":"2607.22165","version":1},"attestation_state":"computed","paper":{"title":"DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Junming Chen, Junyang Jiang, Kai Zheng, Xu Chen, Zibo Liang","submitted_at":"2026-07-24T10:11:24Z","abstract_excerpt":"LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation and production operations: live-environment fidelity (multi-turn read-write interaction with a running database); observation-space scale and complexity (causal diagnosis across thousands of time series, business logs, and concurrent activity); solution-space openness (multiple remediations with different operational trade-offs); and scenario complexity and coverage (faults cascading across internal mechanisms and operational domains). We present "},"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":"2607.22165","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-24T10:11:24Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ddade5fb4b3c59b2277bcd99a80d7b839034851611fffb74136cb3e40ca17dca","abstract_canon_sha256":"b89176aac6505b6a4626df5b2482ccd0581d66a220a33fcc3f7db8ce63d8877d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:51.512248Z","signature_b64":"C2WV+CgM/xbxDuudlQifZctFJWGUk8O6s5ShSE2PAR02vdDnRVATsReU7JAMEuc7AvBdcknpq7wEyPBjDxy1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60004d789f988bf7a0b5fdc4af0b2adfdec806a1d319fc985841a01fccfab6fe","last_reissued_at":"2026-07-27T01:20:51.511069Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:51.511069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Junming Chen, Junyang Jiang, Kai Zheng, Xu Chen, Zibo Liang","submitted_at":"2026-07-24T10:11:24Z","abstract_excerpt":"LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation and production operations: live-environment fidelity (multi-turn read-write interaction with a running database); observation-space scale and complexity (causal diagnosis across thousands of time series, business logs, and concurrent activity); solution-space openness (multiple remediations with different operational trade-offs); and scenario complexity and coverage (faults cascading across internal mechanisms and operational domains). We present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22165","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/2607.22165/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":"2607.22165","created_at":"2026-07-27T01:20:51.511752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22165v1","created_at":"2026-07-27T01:20:51.511752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22165","created_at":"2026-07-27T01:20:51.511752+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAAE26E7TCF7","created_at":"2026-07-27T01:20:51.511752+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAAE26E7TCF7PIFV","created_at":"2026-07-27T01:20:51.511752+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAAE26E7","created_at":"2026-07-27T01:20:51.511752+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/MAAE26E7TCF7PIFV7XCK6CZK37","json":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37.json","graph_json":"https://pith.science/api/pith-number/MAAE26E7TCF7PIFV7XCK6CZK37/graph.json","events_json":"https://pith.science/api/pith-number/MAAE26E7TCF7PIFV7XCK6CZK37/events.json","paper":"https://pith.science/paper/MAAE26E7"},"agent_actions":{"view_html":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37","download_json":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37.json","view_paper":"https://pith.science/paper/MAAE26E7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22165&json=true","fetch_graph":"https://pith.science/api/pith-number/MAAE26E7TCF7PIFV7XCK6CZK37/graph.json","fetch_events":"https://pith.science/api/pith-number/MAAE26E7TCF7PIFV7XCK6CZK37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37/action/storage_attestation","attest_author":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37/action/author_attestation","sign_citation":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37/action/citation_signature","submit_replication":"https://pith.science/pith/MAAE26E7TCF7PIFV7XCK6CZK37/action/replication_record"}},"created_at":"2026-07-27T01:20:51.511752+00:00","updated_at":"2026-07-27T01:20:51.511752+00:00"}