{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.10153", "kind": "paper", "url": "https://arxiv.org/abs/2609.10153"}], "authors": ["Mahmoud Reda", "Salam Khalifa", "Reham Marzouk", "Nizar Habash"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.10153", "source_url": "https://arxiv.org/abs/2609.10153"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "A benchmark for Arabic morphological generation across verbs, nouns, adjectives, cliticized forms, and invalid configurations, with over 600K entries."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.10153", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.10153", "title": "YallaMorph"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.10153", "modality": null, "name": "YallaMorph", "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": "false", "origin_record_id": "bm_yallamorph_68dfa730", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "cc409ed02de32650290bf2b9f5adbdabdb708c279bf7cb9688648067324bedce", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-11T00:52:53.785364Z", "source_url": "https://arxiv.org/abs/2609.10153"}, "publisher": null, "released": "2026-09-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.10153", "source_url": "https://arxiv.org/abs/2609.10153"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-10153", "source": "claire_radar", "source_benchmark_id": "2609.10153", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.10153", "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", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Arabic NLP is a niche but important area, and the absence of public resources slows adoption.", "score": 38}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-11T00:52:53.785364Z", "inputHash": "af70ffb42eb2b7f1bae1f16e51fca850c4f72945b70a03394dcd935d44dd2f31", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "No dataset or evaluation tooling link is provided in the supplied evidence.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-11T00:52:53.785364Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark for Arabic morphological generation across verbs, nouns, adjectives, cliticized forms, and invalid configurations, with over 600K entries.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations."}, "familyId": "bmf_d1eedcfd636d", "firstSeenAt": "2026-09-10", "heat": null, "id": "bm_yallamorph_68dfa730", "indexedAt": "2026-09-10T06:16:58.931316Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.10153", "pdf": "https://arxiv.org/pdf/2609.10153", "project": null, "report": "https://arxiv.org/abs/2609.10153"}, "metrics": [], "motivation": "Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control.", "name": "YallaMorph", "oneLine": "A benchmark for Arabic morphological generation across verbs, nouns, adjectives, cliticized forms, and invalid configurations, with over 600K entries.", "paperTitle": "YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.10153", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026", "verifiedAt": "2026-09-10T06:16:58.931316Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-09", "source": {"authors": ["Mahmoud Reda", "Salam Khalifa", "Reham Marzouk", "Nizar Habash"], "categories": ["cs.CL"], "id": "2609.10153", "title": "YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2609.10153"}, "sourceUpdatedAt": "2026-09-09T13:31:56Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-09-10T06:16:58.931316Z", "rawValue": "Accepted to EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.10153"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026"}], "whyItMatters": "Targets a low-resource language morphology challenge, but no public artifacts are available to confirm reusability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
