{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.27391", "kind": "paper", "url": "https://arxiv.org/abs/2608.27391"}], "authors": ["Sil Hamilton", "Albert Yu Sun", "Oscar J. Romero", "Carl-Leander Henneking", "David Mimno", "Bishan Yang", "Igor Labutov"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.27391", "source_url": "https://arxiv.org/abs/2608.27391"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "LLMs are increasingly able to answer complex questions about enterprise-scale document collections."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.27391", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.27391", "title": "CorporateBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.27391", "modality": null, "name": "CorporateBench", "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_corporatebench_6a07b031", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "659e1c8a7c5c5325f4756db18629287ae6254d183ab80f354e99d1574f1b3198", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.27391"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.27391", "source_url": "https://arxiv.org/abs/2608.27391"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-27391", "source": "claire_radar", "source_benchmark_id": "2608.27391", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.27391", "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", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "stale"}, "capabilities": ["Factuality"], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "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 present CorporateBench (CB), a human-validated multi-task Q&A benchmark whose scale approaches the conditions LLMs encounter in corporate communication networks, with evaluation corpora surpassing 230,000 documents."}, "familyId": "bmf_dde41338c2b3", "firstSeenAt": "2026-08-30", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_corporatebench_6a07b031", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.27391", "paper": "https://arxiv.org/abs/2608.27391", "pdf": "https://arxiv.org/pdf/2608.27391", "project": null, "report": "https://arxiv.org/abs/2608.27391"}, "metrics": [], "motivation": "LLMs are increasingly able to answer complex questions about enterprise-scale document collections.", "name": "CorporateBench", "oneLine": "LLMs are increasingly able to answer complex questions about enterprise-scale document collections.", "paperTitle": "CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to EMNLP Findings", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.27391", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP Findings", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Sil Hamilton", "Albert Yu Sun", "Oscar J. Romero", "Carl-Leander Henneking", "David Mimno", "Bishan Yang", "Igor Labutov"], "categories": ["cs.AI", "cs.CL", "cs.IR", "cs.LG"], "id": "2608.27391", "title": "CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases", "type": "arxiv", "url": "https://arxiv.org/abs/2608.27391"}, "sourceUpdatedAt": "2026-08-27T17:23:04Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP Findings", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to EMNLP Findings", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.27391"}], "reviewStatus": "accepted", "venueName": "EMNLP Findings"}]}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
