{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.22597", "kind": "paper", "url": "https://arxiv.org/abs/2606.22597"}, {"id": "gh:vi-sri/mapreason-osm", "kind": "repo", "url": "https://github.com/Vi-Sri/mapreason-osm"}], "authors": ["Srinivas Venkatanarayanan", "Clement Pakkam Isaac"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.22597", "source_url": "https://arxiv.org/abs/2606.22597"}, "categories": ["Logistics & Operations", "Multimodal"], "description": {"en": "MapReason-OSM evaluates vision-language models on graph-verifiable mobility decisions from self-rendered OpenStreetMap panels. It covers 12 tasks in routing, facility location, and visual disambiguation, with structured outputs scored against hidden oracles for validity, legality, optimality, and constraint satisfaction, plus cross-zoom consistency."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.22597", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.22597", "title": "MapReason-OSM"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Central Florida", "University of South Florida"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.22597", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.22597", "source_url": "https://openalex.org/W7165678292"}, "key": "claire-radar:2606.22597", "modality": null, "name": "MapReason-OSM", "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_mapreason-osm_48426257", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3270a8ec40e5bd8e29f3fecbb63fcb251d49f1ad813141b924bd9f2586f5183d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.22597"}, "publisher": null, "released": "2026-06-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.22597", "source_url": "https://arxiv.org/abs/2606.22597"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-22597", "source": "claire_radar", "source_benchmark_id": "2606.22597", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Logistics & Operations"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Vi-Sri/mapreason-osm", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.22597", "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": "2026-10-04", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "805fbe51bda3d2baa37217f3de7124299a9f0d3715ee546ff553f515c8261a57", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MapReason-OSM evaluates vision-language models on graph-verifiable mobility decisions from self-rendered OpenStreetMap panels. It covers 12 tasks in routing, facility location, and visual disambiguation, with structured outputs scored against hidden oracles for validity, legality, optimality, and constraint satisfaction, plus cross-zoom consistency.", "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": "We present MapReason-OSM, a benchmark and evaluation harness for graph-verifiable mobility decisions on self-rendered OpenStreetMap panels."}, "familyId": "bmf_f407dc71cb3b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Vi-Sri/mapreason-osm", "url": "https://github.com/Vi-Sri/mapreason-osm"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Vi-Sri/mapreason-osm", "url": "https://huggingface.co/papers/2606.22597"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Vi-Sri/mapreason-osm", "url": "https://arxiv.org/abs/2606.22597"}], "scope": "benchmark_repo", "url": "https://github.com/Vi-Sri/mapreason-osm", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_mapreason-osm_48426257", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Logistics"], "links": {"code": "https://github.com/Vi-Sri/mapreason-osm", "data": null, "hfPaper": "https://huggingface.co/papers/2606.22597", "paper": "https://arxiv.org/abs/2606.22597", "pdf": "https://arxiv.org/pdf/2606.22597", "project": null, "report": "https://arxiv.org/abs/2606.22597"}, "metrics": [], "motivation": "Vision-language models (VLMs) are increasingly used to read maps for logistics, delivery, and accessible navigation, where the output is an actionable decision (a route, a pin, a parking choice) that must respect the road network.", "name": "MapReason-OSM", "oneLine": "MapReason-OSM evaluates vision-language models on graph-verifiable mobility decisions from self-rendered OpenStreetMap panels. It covers 12 tasks in routing, facility location, and visual disambiguation, with structured outputs scored against hidden oracles for validity, legality, optimality, and constraint satisfaction, plus cross-zoom consistency.", "paperTitle": "MapReason-OSM: Can Vision-Language Models Make Graph-Verifiable Mobility Decisions from Street Maps ?", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.22597", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Vi-Sri", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Vi-Sri/mapreason-osm"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-21", "source": {"authors": ["Srinivas Venkatanarayanan", "Clement Pakkam Isaac"], "categories": ["cs.CV"], "id": "2606.22597", "title": "MapReason-OSM: Can Vision-Language Models Make Graph-Verifiable Mobility Decisions from Street Maps ?", "type": "arxiv", "url": "https://arxiv.org/abs/2606.22597"}, "sourceUpdatedAt": "2026-06-23T04:17:28Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing map benchmarks often rely on free-text or multiple-choice answers that cannot be verified against road networks. This benchmark provides a reproducible, exact scoring contract for decision-making tasks, supporting comparison of VLM capabilities in logistics, delivery, and accessible navigation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
