{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.29543", "kind": "paper", "url": "https://arxiv.org/abs/2608.29543"}], "authors": ["Yujia Liu", "Jiayan Lin", "Zijin Hong", "Zheng Yuan", "Shengyuan Chen", "Hao Chen", "Qinggang Zhang", "Xiao Huang", "Feiran Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.29543", "source_url": "https://arxiv.org/abs/2608.29543"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates conversational text-to-SQL on 1,542 samples built from 514 BIRD SQLs, measuring chain identification, drift recognition-resolution, and execution accuracy."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.29543", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.29543", "title": "TIDE-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.29543", "modality": null, "name": "TIDE-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": "true", "origin_record_id": "bm_tide-bench_a28d078a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b4b879a0838dd6527b051c3194af26e604a36ba42aeb0a9647eb08e51bceafae", "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/2608.29543"}, "publisher": null, "released": "2026-08-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.29543", "source_url": "https://arxiv.org/abs/2608.29543"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-29543", "source": "claire_radar", "source_benchmark_id": "2608.29543", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.29543", "observedAt": "2026-08-31T04:56:28.279469Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Targets a niche but growing conversational text-to-SQL area with a named benchmark and public code, likely attracting moderate attention from relevant researchers.", "score": 68}, "capabilities": [], "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": "96db20dc1792797149aabda4b26827b32fca73db5a106c62a11cdda9ccd58ac3", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce TIDE-Bench, a benchmark for conversational text-to-SQL under chain ambiguity and intent drift evaluation", "canonicalNameSource": "abstract", "decisionReason": "Explicitly introduced as a benchmark with released code, defined metrics, and a sample-based evaluation protocol.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates conversational text-to-SQL on 1,542 samples built from 514 BIRD SQLs, measuring chain identification, drift recognition-resolution, and execution accuracy.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this, we introduce TIDE-Bench, a benchmark for conversational text-to-SQL under chain ambiguity and intent drift evaluation, targeting two recurring patterns: chain ambiguity, where an underspecified question triggers layered clarification with conditional dependencies, and intent drift, where the user retracts and replaces a previously committed request element."}, "familyId": "bmf_f5522616a31e", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_tide-bench_a28d078a", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.29543", "pdf": "https://arxiv.org/pdf/2608.29543", "project": null, "report": "https://arxiv.org/abs/2608.29543"}, "metrics": [], "motivation": "Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, often involving multiple turns of clarification and revision.", "name": "TIDE-Bench", "oneLine": "Evaluates conversational text-to-SQL on 1,542 samples built from 514 BIRD SQLs, measuring chain identification, drift recognition-resolution, and execution accuracy.", "paperTitle": "Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to EMNLP2026 Main", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.29543", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP2026 Main", "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-30", "source": {"authors": ["Yujia Liu", "Jiayan Lin", "Zijin Hong", "Zheng Yuan", "Shengyuan Chen", "Hao Chen", "Qinggang Zhang", "Xiao Huang", "Feiran Huang"], "categories": ["cs.CL", "cs.AI", "cs.DB"], "id": "2608.29543", "title": "Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift", "type": "arxiv", "url": "https://arxiv.org/abs/2608.29543"}, "sourceUpdatedAt": "2026-08-30T04:24:08Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP2026 Main", "evidence": [{"level": "author-claim", "observedAt": "2026-09-02T05:21:06.631990Z", "rawValue": "Accepted to EMNLP2026 Main", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.29543"}], "reviewStatus": "accepted", "venueName": "EMNLP2026 Main"}], "whyItMatters": "Existing benchmarks focus on execution accuracy and miss intent dynamics; TIDE-Bench isolates chain ambiguity and intent drift, revealing LLM failure modes in multi-turn user interactions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
