{"record": {"aliases": ["Cross-lingual Biography Enrichment via Claim Extraction and Alignment"], "artifacts": [{"id": "arxiv:2608.23390", "kind": "paper", "url": "https://arxiv.org/abs/2608.23390v1"}], "authors": ["Yifei Song", "Ziyang Chen", "Emil Sayilov", "Claire Gardent"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23390", "source_url": "https://arxiv.org/abs/2608.23390"}, "categories": ["General AI", "Language & Knowledge", "Safety"], "description": {"en": "Evaluates cross-lingual biography enrichment on 300 Wikipedia biography pairs with claim annotations and a fine-grained claim-pair relation corpus."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23390v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23390v1", "title": "CLAW-4L"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.23390", "modality": null, "name": "CLAW-4L", "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": "true", "origin_record_id": "bm_cross-lingual-biography-enrichment-via-cla_8d142b84", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "f346e40db0f419101e3e76adc766e67c0b4d79fee5748a5170daf24c68b7ad12", "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/2608.23390v1"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23390", "source_url": "https://arxiv.org/abs/2608.23390v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23390", "source": "claire_radar", "source_benchmark_id": "2608.23390", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Cross-lingual Biography Enrichment via Claim Extraction and Alignment"], "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/2608.23390", "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": "The benchmark targets cross-lingual knowledge enrichment with a modest dataset size and no immediate code or data link, limiting its likely attention in the first week.", "score": 48}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:18:56.318436Z", "inputHash": "3708376119f01f3c20dd4c3fedc1afc09a24b69b0befaf1a0ffd272f3aca68ec", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "introduce \\textsc{CLAW-4L}, a benchmark consisting of 300 Wikipedia biography pairs", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is formally introduced with annotated data and a clear task definition, and can be used by other researchers for claim extraction and alignment.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates cross-lingual biography enrichment on 300 Wikipedia biography pairs with claim annotations and a fine-grained claim-pair relation corpus.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "Focusing on women from non-English-speaking contexts, we introduce \\textsc{CLAW-4L}, a benchmark consisting of 300 Wikipedia biography pairs linking an English biography with its French, Chinese or Azerbaijani counterpart, along with claim annotations and a fine-grained claim-pair relation corpus."}, "familyId": "bmf_4ef127d105d2", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_cross-lingual-biography-enrichment-via-cla_8d142b84", "indexedAt": "2026-08-25T16:42:57.448509Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "http://arxiv.org/abs/2608.23390v1", "pdf": "https://arxiv.org/pdf/2608.23390v1", "project": null, "report": "http://arxiv.org/abs/2608.23390v1"}, "metrics": [], "motivation": "English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded information for long-tail figures.", "name": "CLAW-4L", "oneLine": "Evaluates cross-lingual biography enrichment on 300 Wikipedia biography pairs with claim annotations and a fine-grained claim-pair relation corpus.", "paperTitle": "Cross-lingual Biography Enrichment via Claim Extraction and Alignment", "primaryDomain": "General AI", "publication": {"evidence": "accepted by EMNLP 2026 main conference", "evidenceLevel": "author-claim", "evidenceUrl": "http://arxiv.org/abs/2608.23390v1", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026 main conference", "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-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": 0.5, "value": 50}}, "confidence": "Low", "coverage": 0.4, "rank": 6, "score": 50}, "method": "attention-ranking-v11", "rank": 6, "score": 50}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Yifei Song", "Ziyang Chen", "Emil Sayilov", "Claire Gardent"], "categories": ["cs.CL", "cs.AI"], "id": "2608.23390", "title": "Cross-lingual Biography Enrichment via Claim Extraction and Alignment", "type": "arxiv", "url": "http://arxiv.org/abs/2608.23390v1"}, "sourceUpdatedAt": "2026-08-24T15:36:53Z", "topics": ["Safety"], "venueAttempts": [{"decisionRaw": "accepted by EMNLP 2026 main conference", "evidence": [{"level": "author-claim", "observedAt": "2026-08-25T16:42:57.448509Z", "rawValue": "accepted by EMNLP 2026 main conference", "sourceType": "arxiv-comments", "sourceUrl": "http://arxiv.org/abs/2608.23390v1"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026 main conference"}], "whyItMatters": "Provides a resource for improving coverage of underrepresented biographies by leveraging non-English Wikipedia evidence."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
