{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.30584", "kind": "paper", "url": "https://arxiv.org/abs/2608.30584"}], "authors": ["Xingjian Wang", "Shijian Wang", "Yibo Wang", "Zihao Yu", "Runhao Fu", "Xuelian Cheng", "Zongyuan Ge"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.30584", "source_url": "https://arxiv.org/abs/2608.30584"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Benchmark for compositional spatio-temporal video grounding with difficulty levels based on temporal complexity and spatial interference."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.30584", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.30584", "title": "STVG-CompBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.30584", "modality": null, "name": "STVG-CompBench", "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_stvg-compbench_415f9719", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "53de7b135ded9733ad45b65e0bc80ec66551cb3fa4f8e6caa9fd664fa0185f73", "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/2608.30584"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.30584", "source_url": "https://arxiv.org/abs/2608.30584"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-30584", "source": "claire_radar", "source_benchmark_id": "2608.30584", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "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/2608.30584", "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": "Compositional video grounding is a growing area and synthetic data methods may draw interest, but absence of released resources limits initial traction.", "score": 38}, "capabilities": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "8587bd83e3df880107eef34d3a4fdc9a0a1eab332bbf5dcf3521ddf7f9069a29", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "No artifact links are provided, making the benchmark's availability uncertain.", "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": "Benchmark for compositional spatio-temporal video grounding with difficulty levels based on temporal complexity and spatial interference.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "Built on this engine, we introduce STVG-CompBench, a benchmark stratified by explicit difficulty levels that jointly capture temporal complexity and spatial interference."}, "familyId": "bmf_53850a59f3ae", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_stvg-compbench_415f9719", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.30584", "pdf": "https://arxiv.org/pdf/2608.30584", "project": null, "report": "https://arxiv.org/abs/2608.30584"}, "metrics": [], "motivation": "Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on simple queries.", "name": "STVG-CompBench", "oneLine": "Benchmark for compositional spatio-temporal video grounding with difficulty levels based on temporal complexity and spatial interference.", "paperTitle": "Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.30584", "source": "arxiv-metadata", "status": "unverified", "venue": null, "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": ["Xingjian Wang", "Shijian Wang", "Yibo Wang", "Zihao Yu", "Runhao Fu", "Xuelian Cheng", "Zongyuan Ge"], "categories": ["cs.CV"], "id": "2608.30584", "title": "Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum", "type": "arxiv", "url": "https://arxiv.org/abs/2608.30584"}, "sourceUpdatedAt": "2026-08-31T11:01:31Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Highlights performance drops on compositional queries that are obscured by overall averages."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
