{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.13136", "kind": "paper", "url": "https://arxiv.org/abs/2608.13136"}], "authors": ["Chenrun Wang", "Mingxuan Zhu", "Tiancheng Huang", "Wenjie Li", "Yujie Zhang", "Zichen Zhu", "Zhiying Zou", "Kai Yu", "Lu Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.13136", "source_url": "https://arxiv.org/abs/2608.13136"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "LigBench is an automated evaluation benchmark for AI research idea generation, using fine-grained and reliable evaluation across generation distributions. It includes PAIR-IQ, a dataset for training pairwise idea judgment models."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.13136", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.13136", "title": "LigBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.13136", "modality": null, "name": "LigBench", "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": "unknown", "origin_record_id": "bm_ligbench_47189b6a", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "fdfee1a0d2e272e2e0dfd0cb633c3d1b247d524a4eea88e09d3f9790aaa85999", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.13136"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.13136", "source_url": "https://arxiv.org/abs/2608.13136"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-13136", "source": "claire_radar", "source_benchmark_id": "2608.13136", "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/2608.13136", "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"}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "e331c59c98129cd0071b460dfb9bb4845dc59ec2eceaedf25f39863c4730f9bf", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LigBench is an automated evaluation benchmark for AI research idea generation, using fine-grained and reliable evaluation across generation distributions. It includes PAIR-IQ, a dataset for training pairwise idea judgment models.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "To address this challenge, we propose LigBench, an automated evaluation benchmark that enables fine-grained and reliable evaluation of AI research ideas, consistently applicable across different generation distributions."}, "familyId": "bmf_4c9a86e62e01", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_ligbench_47189b6a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.13136", "paper": "https://arxiv.org/abs/2608.13136", "pdf": "https://arxiv.org/pdf/2608.13136", "project": null, "report": "https://arxiv.org/abs/2608.13136"}, "metrics": [], "motivation": "With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention.", "name": "LigBench", "oneLine": "LigBench is an automated evaluation benchmark for AI research idea generation, using fine-grained and reliable evaluation across generation distributions. It includes PAIR-IQ, a dataset for training pairwise idea judgment models.", "paperTitle": "LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.13136", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "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": 0.85, "relation": "introduces", "releasedAt": "2026-08-13", "source": {"authors": ["Chenrun Wang", "Mingxuan Zhu", "Tiancheng Huang", "Wenjie Li", "Yujie Zhang", "Zichen Zhu", "Zhiying Zou", "Kai Yu", "Lu Chen"], "categories": ["cs.CL", "cs.AI", "cs.DB", "cs.MA"], "id": "2608.13136", "title": "LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.13136"}, "sourceUpdatedAt": "2026-08-13T12:11:23Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Current evaluation of research idea generation is fragmented and lacks objective standards. LigBench aims to provide stable, interpretable, and expert-aligned assessments to support scalable and objective evaluation in this emerging area."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
