{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.08091", "kind": "paper", "url": "https://arxiv.org/abs/2606.08091"}, {"id": "gh:jianhuiwei7/videoweaver", "kind": "repo", "url": "https://github.com/JianhuiWei7/VideoWeaver"}], "authors": ["Jianhui Wei", "Yan Zhang", "Jie Tan", "Hengchuan Zhu", "Xiaotian Zhang", "Ziyi Chen", "Daoan Zhang", "Wei Xu", "Yeying Jin", "Zuozhu Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.08091", "source_url": "https://arxiv.org/abs/2606.08091"}, "categories": ["Agents", "General AI", "Vision & 3D"], "description": {"en": "VideoWeaver is an agent harness and benchmark for long video generation, with 16 task categories and 285 cases, evaluating agents via evidence-grounded judge on process and output."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.08091", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.08091", "title": "VideoWeaver"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["ByteDance (China)", "Zhejiang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.08091", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.08091", "source_url": "https://openalex.org/W7163994107"}, "key": "claire-radar:2606.08091", "modality": null, "name": "VideoWeaver", "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_videoweaver_b86f354a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a05cbfe433543d21683f2742620d3fbcdb740c87318d9b410068751627a53056", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.08091"}, "publisher": null, "released": "2026-06-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.08091", "source_url": "https://arxiv.org/abs/2606.08091"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-08091", "source": "claire_radar", "source_benchmark_id": "2606.08091", "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/JianhuiWei7/VideoWeaver", "githubScope": "benchmark_repo", "githubStars": 38, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.08091", "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": [], "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": "fdbb1580023e736af8479d8f50e230407c22dc1e90a1dded8e41bb195f62d981", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VideoWeaver is an agent harness and benchmark for long video generation, with 16 task categories and 285 cases, evaluating agents via evidence-grounded judge on process and output.", "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", "public artifact URL"], "snippet": "We introduce VideoWeaver, an agent harness and benchmark that evaluates and evolves skills for long video generation, where an agent turns a single instruction into a long video by composing foundation skills into its own workflow rather than following a predefined pipeline."}, "familyId": "bmf_339e1bf0a622", "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/JianhuiWei7/VideoWeaver", "url": "https://github.com/JianhuiWei7/VideoWeaver"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/JianhuiWei7/VideoWeaver", "url": "https://huggingface.co/papers/2606.08091"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/JianhuiWei7/VideoWeaver", "url": "https://arxiv.org/abs/2606.08091"}], "scope": "benchmark_repo", "url": "https://github.com/JianhuiWei7/VideoWeaver", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_videoweaver_b86f354a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/JianhuiWei7/VideoWeaver", "data": null, "hfPaper": "https://huggingface.co/papers/2606.08091", "paper": "https://arxiv.org/abs/2606.08091", "pdf": "https://arxiv.org/pdf/2606.08091", "project": null, "report": "https://arxiv.org/abs/2606.08091"}, "metrics": [], "motivation": "Recent agent frameworks such as Claude Code, Codex, and OpenClaw are strong at tool use and orchestration, but whether they can handle long video generation, a long-horizon multimodal task, remains underexplored.", "name": "VideoWeaver", "oneLine": "VideoWeaver is an agent harness and benchmark for long video generation, with 16 task categories and 285 cases, evaluating agents via evidence-grounded judge on process and output.", "paperTitle": "VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.08091", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "JianhuiWei7", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/JianhuiWei7/VideoWeaver"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-06", "source": {"authors": ["Jianhui Wei", "Jie Tan", "Hengchuan Zhu", "Xiaotian Zhang", "Yan Zhang", "Ziyi Chen", "Daoan Zhang", "Wei Xu", "Zuozhu Liu"], "categories": ["cs.CV"], "id": "2606.08091", "title": "VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2606.08091"}, "sourceUpdatedAt": "2026-06-06T10:35:28Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "General-purpose agents are underevaluated on long-horizon multimodal tasks; VideoWeaver offers a reproducible benchmark to assess and evolve agent skills for video generation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
