{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.06959", "kind": "paper", "url": "https://arxiv.org/abs/2606.06959"}, {"id": "gh:nellie179/hallucination-detection", "kind": "repo", "url": "https://github.com/Nellie179/Hallucination-Detection"}], "authors": ["Xinyi Li", "Zhen Fang", "Yongxin Deng", "Jinyuan Luo", "Hongnan Ma", "Changdae Oh", "Zijing Shi", "Shanshan Ye", "Hanchen Wang", "Shu-Lin Chen", "Yadan Luo", "Mengyue Yang", "Sean Du", "Sharon Li", "Ling Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.06959", "source_url": "https://arxiv.org/abs/2606.06959"}, "categories": ["Cybersecurity", "Vision & 3D", "cs.CL"], "description": {"en": "OpenHalDet is a unified benchmark for hallucination detection across 17 datasets, supporting black-box, gray-box, and white-box detectors with standardized pipelines, scoring via AUROC and Cost@N."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.06959", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.06959", "title": "OpenHalDet"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Technology Sydney", "University of Bristol", "University of Wisconsin–Madison", "The University of Queensland", "Nanyang Technological University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.06959", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.06959", "source_url": "https://openalex.org/W7163877177"}, "key": "claire-radar:2606.06959", "modality": null, "name": "OpenHalDet", "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_openhaldet_b75bc310", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7fcdff5eaecab8a48863b113f19bc217c0a7a0208946b4398d37185a8b42929c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.06959"}, "publisher": null, "released": "2026-06-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.06959", "source_url": "https://arxiv.org/abs/2606.06959"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-06959", "source": "claire_radar", "source_benchmark_id": "2606.06959", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Cybersecurity"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Nellie179/Hallucination-Detection", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2606.06959", "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": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "57feff3fcd46557bb0cf3612ee1ccaff2fa046913059bc2ed881172f376ab3a5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OpenHalDet is a unified benchmark for hallucination detection across 17 datasets, supporting black-box, gray-box, and white-box detectors with standardized pipelines, scoring via AUROC and Cost@N.", "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 OpenHalDet, a unified benchmark for hallucination detection across diverse generation scenarios."}, "familyId": "bmf_34d27080ff9a", "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/Nellie179/Hallucination-Detection", "url": "https://github.com/Nellie179/Hallucination-Detection"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Nellie179/Hallucination-Detection", "url": "https://huggingface.co/papers/2606.06959"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Nellie179/Hallucination-Detection", "url": "https://arxiv.org/abs/2606.06959"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Nellie179/Hallucination-Detection.", "url": "https://arxiv.org/abs/2606.06959"}], "scope": "project_repo", "url": "https://github.com/Nellie179/Hallucination-Detection", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_openhaldet_b75bc310", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Cybersecurity"], "links": {"code": "https://github.com/Nellie179/Hallucination-Detection", "data": null, "hfPaper": "https://huggingface.co/papers/2606.06959", "paper": "https://arxiv.org/abs/2606.06959", "pdf": "https://arxiv.org/pdf/2606.06959", "project": null, "report": "https://arxiv.org/abs/2606.06959"}, "metrics": [], "motivation": "Hallucination detection is essential for the reliable deployment of large language models (LLMs).", "name": "OpenHalDet", "oneLine": "OpenHalDet is a unified benchmark for hallucination detection across 17 datasets, supporting black-box, gray-box, and white-box detectors with standardized pipelines, scoring via AUROC and Cost@N.", "paperTitle": "OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.06959", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-05", "source": {"authors": ["Xinyi Li", "Zhen Fang", "Yongxin Deng", "Jinyuan Luo", "Hongnan Ma", "Changdae Oh", "Zijing Shi", "Shanshan Ye", "Hanchen Wang", "Shu-Lin Chen", "Yadan Luo", "Mengyue Yang", "Sean Du", "Sharon Li", "Ling Chen"], "categories": ["cs.CL", "cs.AI"], "id": "2606.06959", "title": "OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios", "type": "arxiv", "url": "https://arxiv.org/abs/2606.06959"}, "sourceUpdatedAt": "2026-06-05T06:38:40Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It standardizes hallucination detection evaluation, enabling fair comparison across diverse methods and providing a systematic view of detector performance in LLM applications, addressing inconsistencies and limited coverage."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
