{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05744", "kind": "paper", "url": "https://arxiv.org/abs/2606.05744"}, {"id": "gh:zhuchichi56/planbench", "kind": "repo", "url": "https://github.com/zhuchichi56/PlanBench"}, {"kind": "website", "url": "https://plangpt.github.io"}], "authors": ["Minxin Chen", "He Zhu", "Junyou Su", "Wen Wang", "Yijie Deng", "Wenjia Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05744", "source_url": "https://arxiv.org/abs/2606.05744"}, "categories": ["General AI", "Multimodal", "Planning"], "description": {"en": "PlanBench-V evaluates vision-language models on spatial planning map interpretation through an expert-annotated dataset of 223 maps and 1629 question-answer pairs, assessing perception, reasoning, association, and implementation capabilities."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05744", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05744", "title": "PlanBench-V"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tongji University", "Peking University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05744", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05744", "source_url": "https://openalex.org/W7163701963"}, "key": "claire-radar:2606.05744", "modality": null, "name": "PlanBench-V", "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": "unknown", "origin_record_id": "bm_planbench-v_89620860", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3f329147a28ad725736473815eb14ef5102145041ef7623b8ce9d11c9f181d1b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05744"}, "publisher": null, "released": "2026-06-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05744", "source_url": "https://arxiv.org/abs/2606.05744"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05744", "source": "claire_radar", "source_benchmark_id": "2606.05744", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/zhuchichi56/PlanBench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.05744", "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", "state": "unavailable"}}, "status": "fresh"}, "capabilities": ["Planning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "3070dd12d830bab4e08ddd939d1b2d731af50c9816dcda640c3220c66362a9e2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PlanBench-V evaluates vision-language models on spatial planning map interpretation through an expert-annotated dataset of 223 maps and 1629 question-answer pairs, assessing perception, reasoning, association, and implementation capabilities.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce PlanBench-V, the first comprehensive benchmark for evaluating VLMs in spatial planning map interpretation."}, "familyId": "bmf_88e93d3be47e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 6, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/zhuchichi56/PlanBench", "url": "https://plangpt.github.io"}], "scope": "benchmark_repo", "url": "https://github.com/zhuchichi56/PlanBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_planbench-v_89620860", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/zhuchichi56/PlanBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.05744", "paper": "https://arxiv.org/abs/2606.05744", "pdf": "https://arxiv.org/pdf/2606.05744", "project": "https://plangpt.github.io", "report": "https://arxiv.org/abs/2606.05744"}, "metrics": [], "motivation": "Spatial planning maps are central to territorial governance, translating planning objectives, regulations, and spatial strategies into visual forms for decision-making, public communication, and institutional coordination.", "name": "PlanBench-V", "oneLine": "PlanBench-V evaluates vision-language models on spatial planning map interpretation through an expert-annotated dataset of 223 maps and 1629 question-answer pairs, assessing perception, reasoning, association, and implementation capabilities.", "paperTitle": "PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05744", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "PlanGPT", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://plangpt.github.io"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-04", "source": {"authors": ["Minxin Chen", "He Zhu", "Junyou Su", "Wen Wang", "Yijie Deng", "Wenjia Zhang"], "categories": ["cs.CL"], "id": "2606.05744", "title": "PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05744"}, "sourceUpdatedAt": "2026-06-04T06:17:11Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing multimodal benchmarks overlook domain-specific spatial planning tasks. PlanBench-V provides a theory-informed framework for evaluating VLM progress in professional planning contexts, identifying persistent limitations in implementation-oriented tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
