{"record": {"aliases": ["Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?"], "artifacts": [{"id": "arxiv:2608.21827", "kind": "paper", "url": "https://arxiv.org/abs/2608.21827v1"}], "authors": ["Tian Lan", "Shanshan Wang", "Zehua Duo", "Jiang Li", "Guanglai Gao", "Derek F. Wong", "Xiangdong Su"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.21827", "source_url": "https://arxiv.org/abs/2608.21827"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates poetic logic in modern Chinese poetry through four tasks across stanza, line, and imagery levels using six mainstream LLMs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.21827v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.21827v1", "title": "Peony"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Kyoto University", "University of Macau", "National Library of the Philippines", "Inner Mongolia University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.21827", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.21827", "source_url": "https://openalex.org/W7204197557"}, "key": "claire-radar:2608.21827", "modality": null, "name": "Peony", "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_do-large-language-models-perform-well-on-c_54280d5e", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "0e49c87446af582ef649e0396c84ce9ba54120fbcda51ea752b5f493f6e6511c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-25T23:28:56.873215Z", "source_url": "https://arxiv.org/abs/2608.21827v1"}, "publisher": null, "released": "2026-08-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.21827", "source_url": "https://arxiv.org/abs/2608.21827v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-21827", "source": "claire_radar", "source_benchmark_id": "2608.21827", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?"], "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/2608.21827", "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": "Novelty in evaluating poetic logic in Chinese poetry may attract interest, but lack of public artifacts and niche scope limit early attention.", "score": 40}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T23:28:56.873215Z", "inputHash": "30d9768c401ef43dea65623210e649b9dd31ce8cced5608939e6aa1c785bbbea", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we propose Peony, the first benchmark specifically designed for evaluating the poetic logic of modern Chinese poetry", "canonicalNameSource": "abstract", "decisionReason": "Insufficient evidence of a public release path or formal benchmark infrastructure; only promise of data/code availability without concrete artifacts.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T23:28:56.873215Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates poetic logic in modern Chinese poetry through four tasks across stanza, line, and imagery levels using six mainstream LLMs.", "displayEligible": false, "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": "To address this gap, we propose Peony, the first benchmark specifically designed for evaluating the poetic logic of modern Chinese poetry."}, "familyId": "bmf_6d385d6932a3", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_do-large-language-models-perform-well-on-c_54280d5e", "indexedAt": "2026-08-25T17:37:25.889905Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "http://arxiv.org/abs/2608.21827v1", "pdf": "https://arxiv.org/pdf/2608.21827v1", "project": null, "report": "http://arxiv.org/abs/2608.21827v1"}, "metrics": [], "motivation": "Large Language Models (LLMs) have achieved significant progress across a wide range of natural language processing (NLP) tasks, yet their ability to understand literary texts, particularly modern Chinese poetry, remains largely unexplored.", "name": "Peony", "oneLine": "Evaluates poetic logic in modern Chinese poetry through four tasks across stanza, line, and imagery levels using six mainstream LLMs.", "paperTitle": "Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.21827v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T17:37:25.889905Z"}, "publications": [], "ranking": {"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": 0.6, "relation": "introduces", "releasedAt": "2026-08-22", "source": {"authors": ["Tian Lan", "Shanshan Wang", "Zehua Duo", "Jiang Li", "Guanglai Gao", "Derek F. Wong", "Xiangdong Su"], "categories": ["cs.CL"], "id": "2608.21827", "title": "Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?", "type": "arxiv", "url": "http://arxiv.org/abs/2608.21827v1"}, "sourceUpdatedAt": "2026-08-22T07:52:00Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the lack of benchmarks for literary reasoning, specifically the holistic understanding required for modern Chinese poetry beyond superficial semantics."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
