{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.17110", "kind": "paper", "url": "https://arxiv.org/abs/2608.17110"}, {"id": "gh:mgladkova/ov3d-bench", "kind": "repo", "url": "https://github.com/mgladkova/ov3d-bench"}], "authors": ["Mariia Gladkova", "Neehar Peri", "Ishan Khatri", "Deva Ramanan", "Daniel Cremers"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.17110", "source_url": "https://arxiv.org/abs/2608.17110"}, "categories": ["General AI", "Geometric reasoning", "Vision & 3D", "cs.CV"], "description": {"en": "OV3D-Bench is a diagnostic benchmark for open-vocabulary monocular 3D detection, evaluating localization, semantic robustness, and cross-domain transfer across seven datasets."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.17110", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.17110", "title": "OV3D-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Technical University of Munich", "Carnegie Mellon University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.17110", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.17110", "source_url": "https://openalex.org/W7203777746"}, "key": "claire-radar:2608.17110", "modality": null, "name": "OV3D-Bench", "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_ov3d-bench_dff2d230", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "8d42a03652023199c03b87ab879dcafc66180f59a9ddc9d6e2ef7b8764936dae", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.17110"}, "publisher": null, "released": "2026-08-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.17110", "source_url": "https://arxiv.org/abs/2608.17110"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-17110", "source": "claire_radar", "source_benchmark_id": "2608.17110", "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/mgladkova/ov3d-bench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.17110", "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": ["Geometric reasoning"], "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": "e51109fc713620a3a78a1d1190632650d677b085e585b55a4111434d1bb235a0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OV3D-Bench is a diagnostic benchmark for open-vocabulary monocular 3D detection, evaluating localization, semantic robustness, and cross-domain transfer across seven datasets.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this, we introduce OV3D-Bench, a diagnostic benchmark that compares open-vocabulary monocular 3D detectors under deployment-realistic conditions across seven indoor and outdoor datasets."}, "familyId": "bmf_dff0e2aa5738", "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/mgladkova/ov3d-bench", "url": "https://github.com/mgladkova/ov3d-bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/mgladkova/ov3d-bench", "url": "https://huggingface.co/papers/2608.17110"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/mgladkova/ov3d-bench", "url": "https://arxiv.org/abs/2608.17110"}], "scope": "benchmark_repo", "url": "https://github.com/mgladkova/ov3d-bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_ov3d-bench_dff2d230", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/mgladkova/ov3d-bench", "data": null, "hfPaper": "https://huggingface.co/papers/2608.17110", "paper": "https://arxiv.org/abs/2608.17110", "pdf": "https://arxiv.org/pdf/2608.17110", "project": null, "report": "https://arxiv.org/abs/2608.17110"}, "metrics": [], "motivation": "Open-vocabulary monocular 3D detectors report strong in-domain performance, but each evaluates under a different protocol, several rely on per-image category oracles unavailable at deployment, and all collapse geometry and semantics into a single AP metric.", "name": "OV3D-Bench", "oneLine": "OV3D-Bench is a diagnostic benchmark for open-vocabulary monocular 3D detection, evaluating localization, semantic robustness, and cross-domain transfer across seven datasets.", "paperTitle": "OV3D-Bench: A Diagnostic Benchmark for Open-Vocabulary Monocular 3D Detection", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to OpenSUN3D workshop at ECCV'26; benchmark is released on https://github.com/mgladkova/ov3d-bench", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.17110", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "OpenSUN3D workshop at ECCV'26", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "University of Ljubljana", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/mgladkova/ov3d-bench"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 337, "score": 28}, "method": "attention-ranking-v13", "rank": 337, "score": 28}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-17", "source": {"authors": ["Mariia Gladkova and Neehar Peri and Ishan Khatri and Deva Ramanan and Daniel Cremers"], "categories": ["cs.CV"], "id": "2608.17110", "title": "OV3D-Bench: A Diagnostic Benchmark for Open-Vocabulary Monocular 3D Detection", "type": "arxiv", "url": "https://arxiv.org/abs/2608.17110"}, "sourceUpdatedAt": "2026-08-17T20:38:57Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted to OpenSUN3D workshop at ECCV'26; benchmark is released on https://github.com/mgladkova/ov3d-bench", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to OpenSUN3D workshop at ECCV'26; benchmark is released on https://github.com/mgladkova/ov3d-bench", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.17110"}], "reviewStatus": "accepted", "venueName": "OpenSUN3D workshop at ECCV'26"}], "whyItMatters": "It reveals that open-vocabulary semantics is the primary bottleneck, providing a decoupled evaluation axis for detector diagnosis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
