{"record": {"aliases": ["When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World"], "artifacts": [{"id": "arxiv:2608.23507", "kind": "paper", "url": "https://arxiv.org/abs/2608.23507v1"}], "authors": ["Xiang Chen", "Zeyu Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23507", "source_url": "https://arxiv.org/abs/2608.23507"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "A provenance-controlled benchmark for historical entity reconciliation, comprising a Name-only core of 396 pairs and a Source-grounded subset of 160 pairs with entity-disjoint splits."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23507v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23507v1", "title": "MHER"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Amsterdam University Medical Centers", "University of Amsterdam"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.23507", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.23507", "source_url": "https://openalex.org/W7204174132"}, "key": "claire-radar:2608.23507", "modality": null, "name": "MHER", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_when-names-cross-scripts-a-source-grounded_350cc333", "origin_source": "arxiv", "recognition_confidence": "0.45", "record_sha256": "de10d1e3568034f8086f39cc98045e62c571b4446e0245190f4d7e675ab71eb3", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://arxiv.org/abs/2608.23507v1"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23507", "source_url": "https://arxiv.org/abs/2608.23507v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23507", "source": "claire_radar", "source_benchmark_id": "2608.23507", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T16:48:55.714492Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.23507", "observedAt": "2026-08-24T11:31:30.653116Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-25T16:48:55.714492Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Niche historical NLP topic with limited breadth; without public artifacts, early visibility is restrained.", "score": 30}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:22:25.189955Z", "inputHash": "924efe094d5eb82a5cc1b26fa42cefcd1d75cc013ff79fe7d11cc4e87e34bfcc", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "We introduce MHER, a provenance-controlled benchmark for pairwise reconciliation", "canonicalNameSource": "abstract", "decisionReason": "The benchmark defines a stable pairwise evaluation protocol with entity-disjoint splits, but no explicit public artifact link or release statement is provided.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A provenance-controlled benchmark for historical entity reconciliation, comprising a Name-only core of 396 pairs and a Source-grounded subset of 160 pairs with entity-disjoint splits.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence"], "snippet": "We introduce MHER, a provenance-controlled benchmark for pairwise reconciliation of person-name attestations from the Mongol world."}, "familyId": "bmf_1a9235cff5b5", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_when-names-cross-scripts-a-source-grounded_350cc333", "indexedAt": "2026-08-25T16:21:05.134052Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "http://arxiv.org/abs/2608.23507v1", "pdf": "https://arxiv.org/pdf/2608.23507v1", "project": null, "report": "http://arxiv.org/abs/2608.23507v1"}, "metrics": [], "motivation": "Historical people may appear under different languages, scripts, and transcription traditions, while distinct individuals may share highly similar or even identical names.", "name": "MHER", "oneLine": "A provenance-controlled benchmark for historical entity reconciliation, comprising a Name-only core of 396 pairs and a Source-grounded subset of 160 pairs with entity-disjoint splits.", "paperTitle": "When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.23507v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T16:21:05.134052Z"}, "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-v11", "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-v11", "rank": null, "score": null}, "today": {"confidence": "Low", "coverage": 0.4, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}, "llmAttentionForecast": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 2, "historyDate": "2026-08-24", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}, "llmAttentionForecast": {"percentile": 0.3, "value": 30}}, "confidence": "Low", "coverage": 0.4, "rank": 17, "score": 42}, "method": "attention-ranking-v11", "rank": 17, "score": 42}}, "readiness": "Paper only", "recognitionConfidence": 0.45, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Xiang Chen", "Zeyu Zhang"], "categories": ["cs.CL", "cs.AI"], "id": "2608.23507", "title": "When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World", "type": "arxiv", "url": "http://arxiv.org/abs/2608.23507v1"}, "sourceUpdatedAt": "2026-08-24T17:10:36Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Provides controlled framework to study evidence use and failure modes in historical NLP, showing that source-grounded evidence substantially improves identity resolution over names alone."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
