{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.26394", "kind": "paper", "url": "https://arxiv.org/abs/2605.26394"}], "authors": ["Ravi Kumar Tummalapenta", "Suman Addanki"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.26394", "source_url": "https://arxiv.org/abs/2605.26394"}, "categories": ["Agents & Tool Use", "Software & AI Compute", "cs.CL"], "description": {"en": "EnterpriseMem-Bench is a multi-turn Text-to-SQL benchmark with 300 sessions and 1,400 turns across three enterprise domains, featuring deterministic ground truth and per-turn memory-critical annotations."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.26394", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.26394", "title": "EnterpriseMem-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["JPMorgan Chase & Co (United States)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.26394", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.26394", "source_url": "https://openalex.org/W7162498655"}, "key": "claire-radar:2605.26394", "modality": null, "name": "EnterpriseMem-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_enterprisemem-bench_96086215", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "88dbe88f794d94123454d30c8f19969a26e3936a63dd76596628be20f9af8428", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.26394"}, "publisher": null, "released": "2026-05-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.26394", "source_url": "https://arxiv.org/abs/2605.26394"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-26394", "source": "claire_radar", "source_benchmark_id": "2605.26394", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2605.26394", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "dafbef18e13b541cae79dce70f6abdeb427944fc926fdef83e553e75f706e941", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EnterpriseMem-Bench is a multi-turn Text-to-SQL benchmark with 300 sessions and 1,400 turns across three enterprise domains, featuring deterministic ground truth and per-turn memory-critical annotations.", "domainCuration": {"method": "primary-source-review-v1", "state": "reviewed"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "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."}, "familyId": "bmf_78a3d7491203", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_enterprisemem-bench_96086215", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.26394", "paper": "https://arxiv.org/abs/2605.26394", "pdf": "https://arxiv.org/pdf/2605.26394", "project": null, "report": "https://arxiv.org/abs/2605.26394"}, "metrics": [], "motivation": "Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings.", "name": "EnterpriseMem-Bench", "oneLine": "EnterpriseMem-Bench is a multi-turn Text-to-SQL benchmark with 300 sessions and 1,400 turns across three enterprise domains, featuring deterministic ground truth and per-turn memory-critical annotations.", "paperTitle": "Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.26394", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-25", "source": {"authors": ["Ravi Kumar Tummalapenta and Suman Addanki"], "categories": ["cs.CL"], "id": "2605.26394", "title": "Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study", "type": "arxiv", "url": "https://arxiv.org/abs/2605.26394"}, "sourceUpdatedAt": "2026-05-25T23:52:15Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It addresses the lack of multi-turn evaluation in Text-to-SQL, providing insights into memory architecture effects and model performance degradation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
