{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.06771", "kind": "paper", "url": "https://arxiv.org/abs/2609.06771"}, {"id": "gh:mao-code/authbench", "kind": "repo", "url": "https://github.com/mao-code/AuthBench"}, {"id": "hf:maoxun/authbench", "kind": "dataset", "url": "https://huggingface.co/datasets/MaoXun/AuthBench"}], "authors": ["MaoXun Huang", "Zhenxing Zhang", "Claire Cardie"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.06771", "source_url": "https://arxiv.org/abs/2609.06771"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "A multilingual authorship representation benchmark with 428,150 documents across 10 languages, 9 primary genres, and four length buckets, supporting same-author retrieval and verification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.06771", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.06771", "title": "AuthBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Cornell University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.06771", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.06771", "source_url": "https://openalex.org/W7212040824"}, "key": "claire-radar:2609.06771", "modality": null, "name": "AuthBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "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_authbench_049afd70", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "069a82b28a36b2b607daf590dfc18c181278620e5508bb6b1e72fcd66202b53a", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-09T06:27:57.312318Z", "source_url": "https://arxiv.org/abs/2609.06771"}, "publisher": null, "released": "2026-09-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.06771", "source_url": "https://arxiv.org/abs/2609.06771"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-06771", "source": "claire_radar", "source_benchmark_id": "2609.06771", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/mao-code/AuthBench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": "MaoXun/AuthBench", "hfDatasetDownloads": 116, "hfDatasetLikes": 2, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2609.06771", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Large-scale multilingual benchmark with comprehensive coverage is likely to attract NLP and forensics researchers.", "score": 61}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T06:27:57.312318Z", "inputHash": "8c8684a52e3401cc82383a9e4da1f5c1e21ec9a8779c74800aa5ad63ed15d34a", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genres and Lengths", "canonicalNameSource": "paper_title", "decisionReason": "Fully released dataset and tools with standard metrics, offering a clear external path for model evaluation.", "evaluationEvidence": {"reuse": "AuthBench, its evaluation toolkit, and benchmark data are released at https://github.com/mao-code/AuthBench and https://huggingface.co/datasets/MaoXun/AuthBench.", "scoring": "Evaluation uses zero-shot protocol with Success@5 for retrieval and EER/ROC-AUC for verification.", "task": "AuthBench contains 428,150 documents written by 153,825 individuals across ten languages, 9 primary genres, 66 fine-grained genres, and four document-length buckets, supporting authorship attribution as same-author retrieval and authorship verification as binary decision."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T06:27:57.312318Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A multilingual authorship representation benchmark with 428,150 documents across 10 languages, 9 primary genres, and four length buckets, supporting same-author retrieval and verification.", "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", "public artifact URL"], "snippet": "We introduce AuthBench, a large-scale multilingual benchmark for authorship representation that is designed to make this evaluation broad, standardized, and realistic."}, "familyId": "bmf_f6274cf4b2dc", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_authbench_049afd70", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": [], "links": {"code": "https://github.com/mao-code/AuthBench", "data": "https://huggingface.co/datasets/MaoXun/AuthBench", "paper": "https://arxiv.org/abs/2609.06771", "pdf": "https://arxiv.org/pdf/2609.06771", "project": null, "report": "https://arxiv.org/abs/2609.06771"}, "metrics": [], "motivation": "Authorship signals matter in settings where writing style carries identity: digital forensics, plagiarism analysis, account linking, misinformation investigation, and machine-generated text detection.", "name": "AuthBench", "oneLine": "A multilingual authorship representation benchmark with 428,150 documents across 10 languages, 9 primary genres, and four length buckets, supporting same-author retrieval and verification.", "paperTitle": "AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genres and Lengths", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.06771", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "publishers": [{"name": "AuthBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/mao-code/AuthBench"}], "ranking": {"30d": {"confidence": "High", "coverage": 1.0, "datasetDownloadRank": 25, "datasetRankPopulation": 34, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.10220105459060908, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.5734624305000471, "value": 116}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "High", "coverage": 1.0, "rank": 222, "score": 14}, "method": "attention-ranking-v13", "rank": 222, "score": 14}, "90d": {"confidence": "High", "coverage": 1.0, "datasetDownloadRank": 55, "datasetRankPopulation": 85, "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": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.4904083045630754, "value": 116}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "High", "coverage": 1.0, "rank": 560, "score": 20}, "method": "attention-ranking-v13", "rank": 560, "score": 20}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-06", "source": {"authors": ["MaoXun Huang", "Zhenxing Zhang", "Claire Cardie"], "categories": ["cs.CL", "cs.AI"], "id": "2609.06771", "title": "AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genres and Lengths", "type": "arxiv", "url": "https://arxiv.org/abs/2609.06771"}, "sourceUpdatedAt": "2026-09-06T18:24:27Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Unifies fragmented authorship evaluation across languages, genres, and document lengths, enabling broad comparison of modern text representations."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
