{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.30451", "kind": "paper", "url": "https://arxiv.org/abs/2608.30451"}], "authors": ["Yi Zhang", "Yi Wang", "Yueting Wu", "Kaiyue Yang", "Yuejiao Su", "Lap-Pui Chau"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.30451", "source_url": "https://arxiv.org/abs/2608.30451"}, "categories": ["Geometric reasoning", "Reasoning", "Robotics & Embodied AI", "Vision & 3D"], "description": {"en": "3D visual grounding benchmark with sequence-aligned RGB observations and human-verified expressions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.30451", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.30451", "title": "SeqAlign3DVG"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.30451", "modality": null, "name": "SeqAlign3DVG", "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": "false", "origin_record_id": "bm_seqalign3dvg_20f971d6", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6c079741caa43c9fc310c13c8939f4d16b01cfe57eff6bc6aa935a2ecde9590c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.30451"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.30451", "source_url": "https://arxiv.org/abs/2608.30451"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-30451", "source": "claire_radar", "source_benchmark_id": "2608.30451", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Robotics & Embodied 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/2608.30451", "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"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "3D visual grounding is a focused topic with moderate interest; lack of released benchmark materials tempers expected attention.", "score": 35}, "capabilities": ["Reasoning", "Geometric reasoning"], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "e152dccf1778279d7299ad435d8075d6633a5790ef3519a01ddecb92d65d3453", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "No public code or dataset link is provided, despite claims of a new benchmark.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "3D visual grounding benchmark with sequence-aligned RGB observations and human-verified expressions.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce SeqAlign3DVG, a novel benchmark dedicated to temporally ordered and strictly observation-aligned image-based 3D visual grounding."}, "familyId": "bmf_c595a64604ea", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_seqalign3dvg_20f971d6", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.30451", "pdf": "https://arxiv.org/pdf/2608.30451", "project": null, "report": "https://arxiv.org/abs/2608.30451"}, "metrics": [], "motivation": "Image-based 3D visual grounding is critical for embodied agents, yet existing benchmarks suffer from loose text-observation alignment and neglect temporal ordering.", "name": "SeqAlign3DVG", "oneLine": "3D visual grounding benchmark with sequence-aligned RGB observations and human-verified expressions.", "paperTitle": "SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": "Accepted by ACM Multimedia 2026 (MM '26)", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.30451", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ACM Multimedia 2026 (MM '26)", "verifiedAt": "2026-09-01T06:35:20.746269Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-31", "source": {"authors": ["Yi Zhang", "Yi Wang", "Yueting Wu", "Kaiyue Yang", "Yuejiao Su", "Lap-Pui Chau"], "categories": ["cs.CV"], "id": "2608.30451", "title": "SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding", "type": "arxiv", "url": "https://arxiv.org/abs/2608.30451"}, "sourceUpdatedAt": "2026-08-31T08:38:29Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted by ACM Multimedia 2026 (MM '26)", "evidence": [{"level": "author-claim", "observedAt": "2026-09-01T06:35:20.746269Z", "rawValue": "Accepted by ACM Multimedia 2026 (MM '26)", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.30451"}], "reviewStatus": "accepted", "venueName": "ACM Multimedia 2026 (MM '26)"}], "whyItMatters": "Evaluates grounding under strict observation alignment, addressing limitations in existing benchmarks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
