{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2T4J7ABPWQYDPSAE776UVJFGSA","short_pith_number":"pith:2T4J7ABP","schema_version":"1.0","canonical_sha256":"d4f89f802fb43037c804fffd4aa4a690062a61f2e1cfa8e47ace0fb431d4d942","source":{"kind":"arxiv","id":"2605.26394","version":1},"attestation_state":"computed","paper":{"title":"Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ravi Kumar Tummalapenta, Suman Addanki","submitted_at":"2026-05-25T23:52:15Z","abstract_excerpt":"Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings. We introduce EnterpriseMem-Bench, a multi-turn Text-to-SQL benchmark of 300 sessions and 1,400 turns built programmatically from three enterprise domains (BIRD financial, SEC EDGAR, Northwind), with deterministic ground truth and per-turn memory-critical annotation. We evaluate five frontier models -- GPT-5 mini, GPT-5.2, Claude Sonnet 4.5, Sonnet 4.6, and Opus 4.6 -- across five memory conditions enabling a three-way ablation isolating working-memory window size, episodic ret"},"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":"2605.26394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T23:52:15Z","cross_cats_sorted":[],"title_canon_sha256":"0f5cd071bd8cf692b39fbda70d178c68d7817dfcbae95caf4b3cae2bc1fbe878","abstract_canon_sha256":"9c8bd0d175c307bba7bdb922117784552b060734e60dd067f4c63b70f12d52bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:15.802232Z","signature_b64":"X2yN2a+axpeP7flZ11xMv/JzTU0Ue7HJKj+Yt8tr+hG0fDG1DECi2PFH3ClmRbELxhZ6KzQPW9y+mDcX+ljpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4f89f802fb43037c804fffd4aa4a690062a61f2e1cfa8e47ace0fb431d4d942","last_reissued_at":"2026-05-27T01:05:15.801387Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:15.801387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ravi Kumar Tummalapenta, Suman Addanki","submitted_at":"2026-05-25T23:52:15Z","abstract_excerpt":"Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings. We introduce EnterpriseMem-Bench, a multi-turn Text-to-SQL benchmark of 300 sessions and 1,400 turns built programmatically from three enterprise domains (BIRD financial, SEC EDGAR, Northwind), with deterministic ground truth and per-turn memory-critical annotation. We evaluate five frontier models -- GPT-5 mini, GPT-5.2, Claude Sonnet 4.5, Sonnet 4.6, and Opus 4.6 -- across five memory conditions enabling a three-way ablation isolating working-memory window size, episodic ret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26394","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/2605.26394/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":"2605.26394","created_at":"2026-05-27T01:05:15.801528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26394v1","created_at":"2026-05-27T01:05:15.801528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26394","created_at":"2026-05-27T01:05:15.801528+00:00"},{"alias_kind":"pith_short_12","alias_value":"2T4J7ABPWQYD","created_at":"2026-05-27T01:05:15.801528+00:00"},{"alias_kind":"pith_short_16","alias_value":"2T4J7ABPWQYDPSAE","created_at":"2026-05-27T01:05:15.801528+00:00"},{"alias_kind":"pith_short_8","alias_value":"2T4J7ABP","created_at":"2026-05-27T01:05:15.801528+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/2T4J7ABPWQYDPSAE776UVJFGSA","json":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA.json","graph_json":"https://pith.science/api/pith-number/2T4J7ABPWQYDPSAE776UVJFGSA/graph.json","events_json":"https://pith.science/api/pith-number/2T4J7ABPWQYDPSAE776UVJFGSA/events.json","paper":"https://pith.science/paper/2T4J7ABP"},"agent_actions":{"view_html":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA","download_json":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA.json","view_paper":"https://pith.science/paper/2T4J7ABP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26394&json=true","fetch_graph":"https://pith.science/api/pith-number/2T4J7ABPWQYDPSAE776UVJFGSA/graph.json","fetch_events":"https://pith.science/api/pith-number/2T4J7ABPWQYDPSAE776UVJFGSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA/action/storage_attestation","attest_author":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA/action/author_attestation","sign_citation":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA/action/citation_signature","submit_replication":"https://pith.science/pith/2T4J7ABPWQYDPSAE776UVJFGSA/action/replication_record"}},"created_at":"2026-05-27T01:05:15.801528+00:00","updated_at":"2026-05-27T01:05:15.801528+00:00"}