{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.29345", "kind": "paper", "url": "https://arxiv.org/abs/2608.29345"}, {"id": "gh:zjuidg/bird-history", "kind": "repo", "url": "https://github.com/zjuidg/BIRD-History"}], "authors": ["Yunfan Zhou", "Qiming Shi", "Yizhou Yang", "Di Weng", "Yingcai Wu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.29345", "source_url": "https://arxiv.org/abs/2608.29345"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates text-to-SQL systems on 1,393 tasks that require leveraging historical SQL logs, with fine-grained annotations for retrieval and knowledge utilization."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.29345", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.29345", "title": "BIRD-History"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.29345", "modality": null, "name": "BIRD-History", "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": "true", "origin_record_id": "bm_bird-history_67c9a405", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "091e6da085369a9bb4ddbd9a94b1e3b9c5eb55e6b5e03902b55d6fb484a1f52c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.29345"}, "publisher": null, "released": "2026-08-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.29345", "source_url": "https://arxiv.org/abs/2608.29345"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-29345", "source": "claire_radar", "source_benchmark_id": "2608.29345", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": "https://github.com/zjuidg/BIRD-History", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.29345", "observedAt": "2026-09-02T05:12:51.621571Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark extends the well-known BIRD text-to-SQL resource and includes public code and data, which is likely to interest the database and NLP communities looking for history-driven evaluation.", "score": 66}, "capabilities": ["Factuality"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "4c5877ba18be55f4fd309c213cdd2a2e8961b370df00ed2970629ca139560a0c", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce BIRD-History, a benchmark consisting of 1,393 tasks across 11 databases, designed to evaluate text-to-SQL systems' ability to ground underspecified natural language questions using historical SQL scripts.", "canonicalNameSource": "abstract", "decisionReason": "Formally named benchmark with a clear task definition, public code repository, and dataset files.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates text-to-SQL systems on 1,393 tasks that require leveraging historical SQL logs, with fine-grained annotations for retrieval and knowledge utilization.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce BIRD-History, a benchmark consisting of 1,393 tasks across 11 databases, designed to evaluate text-to-SQL systems' ability to ground underspecified natural language questions using historical SQL scripts."}, "familyId": "bmf_03f08ee0b231", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_bird-history_67c9a405", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": [], "links": {"code": "https://github.com/zjuidg/BIRD-History", "data": null, "hfPaper": "https://huggingface.co/papers/2608.29345", "paper": "https://arxiv.org/abs/2608.29345", "pdf": "https://arxiv.org/pdf/2608.29345", "project": null, "report": "https://arxiv.org/abs/2608.29345"}, "metrics": [], "motivation": "While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user queries implicitly rely on domain-specific knowledge, such as business logic, data conventions, and analytical practices, that is neither captured by the schema nor explicitly stated in the natural language question.", "name": "BIRD-History", "oneLine": "Evaluates text-to-SQL systems on 1,393 tasks that require leveraging historical SQL logs, with fine-grained annotations for retrieval and knowledge utilization.", "paperTitle": "BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at Findings of the Association for Computational Linguistics: EMNLP, 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.29345", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Findings of the Association for Computational Linguistics: EMNLP, 2026", "verifiedAt": "2026-09-02T00:50:41.903960Z"}, "publications": [], "publishers": [{"name": "ZJU IDG", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/zjuidg/BIRD-History"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 126, "score": 23}, "method": "attention-ranking-v13", "rank": 126, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 319, "score": 23}, "method": "attention-ranking-v13", "rank": 319, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-29", "source": {"authors": ["Yunfan Zhou", "Qiming Shi", "Yizhou Yang", "Di Weng", "Yingcai Wu"], "categories": ["cs.AI", "cs.CL"], "id": "2608.29345", "title": "BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations", "type": "arxiv", "url": "https://arxiv.org/abs/2608.29345"}, "sourceUpdatedAt": "2026-08-29T15:59:56Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "Accepted at Findings of the Association for Computational Linguistics: EMNLP, 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-09-02T00:50:41.903960Z", "rawValue": "Accepted at Findings of the Association for Computational Linguistics: EMNLP, 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.29345"}], "reviewStatus": "accepted", "venueName": "Findings of the Association for Computational Linguistics: EMNLP, 2026"}], "whyItMatters": "Fills a gap in text-to-SQL evaluation by testing knowledge grounding beyond schema and query, and provides a public dataset and plug-in retriever for reproducible comparisons."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
