{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.06229", "kind": "paper", "url": "https://arxiv.org/abs/2607.06229"}, {"id": "gh:leolty/spider2-aifunc", "kind": "repo", "url": "https://github.com/Leolty/Spider2-AIFunc"}], "authors": ["Tianyang Liu", "Canwen Xu", "Fangyu Lei", "Nikki Lijing Kuang", "Jixuan Chen", "Tao Yu", "Julian McAuley", "Zhewei Yao", "Yuxiong He"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.06229", "source_url": "https://arxiv.org/abs/2607.06229"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Extends text-to-SQL to AI-native SQL workflows with 465 instances across 125 real-world databases on Snowflake. Tasks require using AI functions like classification and sentiment analysis. Evaluates execution accuracy."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.06229", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.06229", "title": "Spider 2.0-AIFunc"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of California San Diego", "Snowflake Inc. (United States)", "University of Hong Kong"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.06229", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.06229", "source_url": "https://openalex.org/W7167686045"}, "key": "claire-radar:2607.06229", "modality": null, "name": "Spider 2.0-AIFunc", "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_spider-2-0-aifunc_d9873e24", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "bd8088655a4600c5d256bde15a2fe53dcf514bfecf17b15471c166e8d4a3dee5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.06229"}, "publisher": null, "released": "2026-07-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.06229", "source_url": "https://arxiv.org/abs/2607.06229"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-06229", "source": "claire_radar", "source_benchmark_id": "2607.06229", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Leolty/Spider2-AIFunc", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.06229", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b4de75b68993207d60c9728ecee5c188aba765d4980f4e90b8594f79cfab9fa0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Extends text-to-SQL to AI-native SQL workflows with 465 instances across 125 real-world databases on Snowflake. Tasks require using AI functions like classification and sentiment analysis. Evaluates execution accuracy.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce Spider 2.0-AIFunc, a benchmark of 465 verified instances across 125 real-world databases covering six types of AI functions on the Snowflake platform."}, "familyId": "bmf_020b339c7771", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Leolty/Spider2-AIFunc", "url": "https://github.com/Leolty/Spider2-AIFunc"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Leolty/Spider2-AIFunc", "url": "https://huggingface.co/papers/2607.06229"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Leolty/Spider2-AIFunc", "url": "https://arxiv.org/abs/2607.06229"}], "scope": "project_repo", "url": "https://github.com/Leolty/Spider2-AIFunc", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_spider-2-0-aifunc_d9873e24", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Leolty/Spider2-AIFunc", "data": null, "hfPaper": "https://huggingface.co/papers/2607.06229", "paper": "https://arxiv.org/abs/2607.06229", "pdf": "https://arxiv.org/pdf/2607.06229", "project": null, "report": "https://arxiv.org/abs/2607.06229"}, "metrics": [], "motivation": "Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filtering, sentiment analysis, extraction, similarity search, and aggregation within ordinary SQL queries.", "name": "Spider 2.0-AIFunc", "oneLine": "Extends text-to-SQL to AI-native SQL workflows with 465 instances across 125 real-world databases on Snowflake. Tasks require using AI functions like classification and sentiment analysis. Evaluates execution accuracy.", "paperTitle": "Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.06229", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Leolty", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Leolty/Spider2-AIFunc"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.18504537701418716, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.7, "rank": 367, "score": 25}, "method": "attention-ranking-v13", "rank": 367, "score": 25}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-07", "source": {"authors": ["Tianyang Liu", "Canwen Xu", "Fangyu Lei", "Nikki Lijing Kuang", "Jixuan Chen", "Tao Yu", "Julian McAuley", "Zhewei Yao", "Yuxiong He"], "categories": ["cs.CL", "cs.AI", "cs.DB"], "id": "2607.06229", "title": "Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows", "type": "arxiv", "url": "https://arxiv.org/abs/2607.06229"}, "sourceUpdatedAt": "2026-07-07T12:54:08Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the gap of benchmarks not covering AI-native SQL capabilities that are increasingly available in cloud platforms. Provides a reusable dataset and evaluation harness for a new task type."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
