{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03273", "kind": "paper", "url": "https://arxiv.org/abs/2606.03273"}], "authors": ["Hang He", "Chuhuai Yue", "Chengqi Dong", "Chengcheng Wan", "Ting Su", "Haiying Sun", "Jiajun Chai", "Xiaohan Wang", "Guojun Yin"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03273", "source_url": "https://arxiv.org/abs/2606.03273"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "VistaHop is a benchmark for long-horizon Visual DeepSearch, evaluating repeated image inspection, visual-anchor grounding, and evidence traversal across 600 tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03273", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03273", "title": "VistaHop"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.03273", "modality": null, "name": "VistaHop", "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_vistahop_3279a79d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d589e6940147a725fc0323a953859cbd6049c7d87e54a8d15d665a671b235725", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03273"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03273", "source_url": "https://arxiv.org/abs/2606.03273"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03273", "source": "claire_radar", "source_benchmark_id": "2606.03273", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.03273", "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": "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": "180afcc020a05bbbda354309b8734010508c08b97e785fdf8964636cd10b2463", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VistaHop is a benchmark for long-horizon Visual DeepSearch, evaluating repeated image inspection, visual-anchor grounding, and evidence traversal across 600 tasks.", "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"], "snippet": "In this work, we introduce VistaHop, a benchmark designed specifically to evaluate Visual DeepSearch."}, "familyId": "bmf_acaea9923b4f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_vistahop_3279a79d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.03273", "paper": "https://arxiv.org/abs/2606.03273", "pdf": "https://arxiv.org/pdf/2606.03273", "project": null, "report": "https://arxiv.org/abs/2606.03273"}, "metrics": [], "motivation": "Visual DeepSearch tasks require multimodal large language models (MLLMs) to resolve complex visual queries by repeatedly inspecting image regions, grounding reasoning in visual evidence, and connecting fine-grained clues across multiple steps.", "name": "VistaHop", "oneLine": "VistaHop is a benchmark for long-horizon Visual DeepSearch, evaluating repeated image inspection, visual-anchor grounding, and evidence traversal across 600 tasks.", "paperTitle": "VistaHop: Benchmarking Long-Horizon Visual DeepSearch", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03273", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Hang He", "Chuhuai Yue", "Chengqi Dong", "Chengcheng Wan", "Ting Su", "Haiying Sun", "Jiajun Chai", "Xiaohan Wang", "Guojun Yin"], "categories": ["cs.CV", "cs.AI", "cs.CL"], "id": "2606.03273", "title": "VistaHop: Benchmarking Long-Horizon Visual DeepSearch", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03273"}, "sourceUpdatedAt": "2026-07-29T14:08:31Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Targets the gap in evaluating MLLMs' ability to iteratively revisit visual evidence and reason across multiple steps in complex visual queries."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
