{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.13560", "kind": "paper", "url": "https://arxiv.org/abs/2608.13560"}, {"id": "gh:yaxin9luo/autodesign", "kind": "repo", "url": "https://github.com/Yaxin9Luo/AutoDesign"}], "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "PosterBench evaluates academic paper-to-poster generation. It includes a 100-paper Main Track across five disciplines and a 10-paper mini subset, with automated scoring and human evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.13560", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.13560", "title": "PosterBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.13560", "modality": null, "name": "PosterBench", "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_posterbench_1bd5f76e", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "8fd1692c26de870c4ca6e30cf1d57b48da2a329b977c3d05fe71c0a691e0119f", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:14:52.836173Z", "source_url": "https://arxiv.org/abs/2608.13560"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.13560", "source_url": "https://arxiv.org/abs/2608.13560"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-13560", "source": "claire_radar", "source_benchmark_id": "2608.13560", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Yaxin9Luo/AutoDesign", "githubScope": "benchmark_repo", "githubStars": 231, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 64, "hfPaperUrl": "https://huggingface.co/papers/2608.13560", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark is tied to a novel framework with public code and dataset links, and the task of paper-to-poster generation has moderate community interest.", "score": 55}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:14:52.836173Z", "inputHash": "79f26d0006e8da6f0f68ec259e918a9d462e1bb44b089caeee2cd7b6ba29a583", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we focus on the academic paper-to-poster generation task and introduce PosterBench, comprising a 100-paper Main Track spanning five disciplines and PosterBench-mini, a shared 10-paper subset for controlled evaluation.", "canonicalNameSource": "abstract", "decisionReason": "PosterBench is introduced as a benchmark with a defined evaluation protocol and public dataset, enabling comparable scoring across systems.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:14:52.836173Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PosterBench evaluates academic paper-to-poster generation. It includes a 100-paper Main Track across five disciplines and a 10-paper mini subset, with automated scoring and human evaluation.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "evaluation protocol evidence", "public artifact URL", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "To instantiate and evaluate this framework, we focus on the academic paper-to-poster generation task and introduce PosterBench, comprising a 100-paper Main Track spanning five disciplines and PosterBench-mini, a shared 10-paper subset for controlled evaluation."}, "familyId": "bmf_0e909d54ed40", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_posterbench_1bd5f76e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Yaxin9Luo/AutoDesign", "data": null, "paper": "https://arxiv.org/abs/2608.13560", "pdf": "https://arxiv.org/pdf/2608.13560", "project": null, "report": "https://arxiv.org/abs/2608.13560"}, "metrics": [], "motivation": "Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system.", "name": "PosterBench", "oneLine": "PosterBench evaluates academic paper-to-poster generation. It includes a 100-paper Main Track across five disciplines and a 10-paper mini subset, with automated scoring and human evaluation.", "paperTitle": "AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.13560", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.7270415279068496, "value": 231}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.737591728492665, "value": 64}}, "confidence": "Medium", "coverage": 0.7, "rank": 9, "score": 66}, "method": "attention-ranking-v13", "rank": 9, "score": 66}}, "readiness": "Runnable", "recognitionConfidence": 0.55, "relation": "evaluates_only", "releasedAt": "2026-08-13", "source": {"authors": ["Yaxin Luo", "Haobin Jiang", "Jialv Zou", "Xu Huang", "Wenhao Yan", "Haodong Li", "Zhengrong Yue", "Jing Li", "Xiaofu Chen", "Xiaohan Zhao", "Jiacheng Liu", "Jiacheng Cui", "Zhiqiang Shen", "Xiaotong Li"], "categories": ["cs.CV", "cs.AI", "cs.CL"], "id": "2608.13560", "title": "AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design", "type": "arxiv", "url": "https://arxiv.org/abs/2608.13560"}, "sourceUpdatedAt": "2026-08-13T17:59:57Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "It provides a standardized way to compare agentic design systems on long-horizon multimodal generation, enabling measurement of quality and agent efficiency across different models and harnesses."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
