{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.24456", "kind": "paper", "url": "https://arxiv.org/abs/2605.24456"}], "authors": ["Jinzhao Li", "Yinuo Chen", "Dongxu Piao", "Panwang Pan", "Yifan Yu", "Dong Wang", "Honglei Yan", "Liang Yue", "Shaofei Wang", "Yixin Chen", "Siyuan Huang", "Miao Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.24456", "source_url": "https://arxiv.org/abs/2605.24456"}, "categories": ["General AI", "Geometric reasoning", "Reasoning", "Vision & 3D"], "description": {"en": "EgoProx evaluates multimodal large language models on egocentric 3D proximity reasoning, with tasks organized along a cognitive hierarchy covering intention, exploration, exploitation, and chain-of-actions reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.24456", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.24456", "title": "EgoProx"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["ByteDance (China)", "Tsinghua University", "Beijing Institute for General Artificial Intelligence"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.24456", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.24456", "source_url": "https://openalex.org/W7162410807"}, "key": "claire-radar:2605.24456", "modality": null, "name": "EgoProx", "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_egoprox_628390c5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "33331cad632e30b2b9a548adf3d79109fb4bb58be82b35f06a2b7ce7427d41d0", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.24456"}, "publisher": null, "released": "2026-05-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.24456", "source_url": "https://arxiv.org/abs/2605.24456"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-24456", "source": "claire_radar", "source_benchmark_id": "2605.24456", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2605.24456", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Reasoning", "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": "0dd961362af71913f44d54eaf7cad948ed6e418826fcf3159123ab8a92688ad7", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EgoProx evaluates multimodal large language models on egocentric 3D proximity reasoning, with tasks organized along a cognitive hierarchy covering intention, exploration, exploitation, and chain-of-actions reasoning.", "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": "To this end, we introduce EgoProx, a benchmark for egocentric 3D proximity reasoning."}, "familyId": "bmf_c4115f8c172a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_egoprox_628390c5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.24456", "paper": "https://arxiv.org/abs/2605.24456", "pdf": "https://arxiv.org/pdf/2605.24456", "project": null, "report": "https://arxiv.org/abs/2605.24456"}, "metrics": [], "motivation": "Humans constantly reason about 3D proximity, the relations between their body and surrounding objects, to guide perception and action in daily life.", "name": "EgoProx", "oneLine": "EgoProx evaluates multimodal large language models on egocentric 3D proximity reasoning, with tasks organized along a cognitive hierarchy covering intention, exploration, exploitation, and chain-of-actions reasoning.", "paperTitle": "EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to CVPR 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2605.24456", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "CVPR 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-23", "source": {"authors": ["Jinzhao Li", "Yinuo Chen", "Dongxu Piao", "Panwang Pan", "Yifan Yu", "Dong Wang", "Honglei Yan", "Liang Yue", "Shaofei Wang", "Yixin Chen", "Siyuan Huang", "Miao Liu"], "categories": ["cs.CV"], "id": "2605.24456", "title": "EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy", "type": "arxiv", "url": "https://arxiv.org/abs/2605.24456"}, "sourceUpdatedAt": "2026-05-26T08:53:56Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted to CVPR 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to CVPR 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2605.24456"}], "reviewStatus": "accepted", "venueName": "CVPR 2026"}], "whyItMatters": "It addresses the gap in assessing embodied 3D spatial reasoning in MLLMs, a capability important for robotics and augmented reality applications."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
