{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.22770", "kind": "paper", "url": "https://arxiv.org/abs/2608.22770v1"}], "authors": ["Xuan Yao", "Shuping Li", "Yang Dai", "Yi Zhou", "Ke-Wei Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.22770", "source_url": "https://arxiv.org/abs/2608.22770"}, "categories": ["Finance", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates search-enabled LLMs on reconstructing security-level delisting events from public sources, using a 1,200-record benchmark with joint accuracy metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.22770v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.22770v1", "title": "DelistBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.22770", "modality": null, "name": "DelistBench", "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_delistbench_3f7c82bb", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "22b7062199094451a331cab92c215eade1a588cdd1c1b7f3390f549655615faa", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://arxiv.org/abs/2608.22770v1"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.22770", "source_url": "https://arxiv.org/abs/2608.22770v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-22770", "source": "claire_radar", "source_benchmark_id": "2608.22770", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Language & Knowledge", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-26T06:23:37.320575Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.22770", "observedAt": "2026-08-24T11:31:30.653116Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-26T06:23:37.320575Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses financial data quality and compares web-enabled LLMs, a topic of interest to both finance and NLP communities, but with narrow domain appeal.", "score": 54}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:18:56.318436Z", "inputHash": "351f2c39e6980a792ce99a4e5efa8306faba5149b83a4b4a752612eae00ed6f8", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "and DelistBench, a 1,200-record benchmark for security-level delisting announcements.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark defines a clear task, provides a fixed dataset, and evaluates multiple models under controlled conditions, making it reusable for further comparisons.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates search-enabled LLMs on reconstructing security-level delisting events from public sources, using a 1,200-record benchmark with joint accuracy metrics.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce Search-to-Record, a database-assurance task in which search-enabled large language models reconstruct institution-defined event records from public sources for a known security universe and historical cutoff, and DelistBench, a 1,200-record benchmark for security-level delisting announcements."}, "familyId": "bmf_24eacb532a62", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_delistbench_3f7c82bb", "indexedAt": "2026-08-25T16:42:57.448509Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "paper": "http://arxiv.org/abs/2608.22770v1", "pdf": "https://arxiv.org/pdf/2608.22770v1", "project": null, "report": "http://arxiv.org/abs/2608.22770v1"}, "metrics": [], "motivation": "Financial institutions need an independent way to detect missing, stale, and misclassified corporate-event records in vendor databases.", "name": "DelistBench", "oneLine": "Evaluates search-enabled LLMs on reconstructing security-level delisting events from public sources, using a 1,200-record benchmark with joint accuracy metrics.", "paperTitle": "DelistBench: Evaluating Search-Enabled LLMs for Auditable Corporate-Event Database Completion", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.22770v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T16:42:57.448509Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v12", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v12", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Xuan Yao", "Li Shuping", "Dai Yang", "Zhou Yi", "Ke-Wei Huang"], "categories": ["cs.CL"], "id": "2608.22770", "title": "DelistBench: Evaluating Search-Enabled LLMs for Auditable Corporate-Event Database Completion", "type": "arxiv", "url": "http://arxiv.org/abs/2608.22770v1"}, "sourceUpdatedAt": "2026-08-24T03:46:20Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Provides a standardized way to assess database assurance for corporate-event completeness, with practical guidance on model selection and triage."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
