{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.24821", "kind": "paper", "url": "https://arxiv.org/abs/2607.24821"}, {"id": "gh:nju-link/ave-compass", "kind": "repo", "url": "https://github.com/NJU-LINK/AVE-Compass"}], "authors": ["Yuqing Wen", "Yukai Huang", "Qianqian Xie", "Jiangtao Wu", "Yibin Lin", "Yikai Gu", "Jialu Chen", "Yuanxing Zhang", "Jiaheng Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.24821", "source_url": "https://arxiv.org/abs/2607.24821"}, "categories": ["General AI", "Vision & 3D", "cs.MM"], "description": {"en": "AVE-Compass evaluates audio-visual editing models on 145 source videos and 196 instructions with 2,688 checklist items, scoring Instruction Following, Fidelity Preserving, Realism, and Editing Intent via MLLM judging and automated metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.24821", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.24821", "title": "AVE-Compass"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["National University of Singapore", "Beijing University of Posts and Telecommunications", "Nanjing University", "Xi'an Jiaotong University", "University of Illinois Urbana-Champaign", "Kuaishou (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.24821", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.24821", "source_url": "https://openalex.org/W7171630113"}, "key": "claire-radar:2607.24821", "modality": null, "name": "AVE-Compass", "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_ave-compass_477a3826", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3cc49e95dfb742b4c49f220176ce89d1691bff3c506355713d748a4ab3384df8", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.24821"}, "publisher": null, "released": "2026-07-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.24821", "source_url": "https://arxiv.org/abs/2607.24821"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-24821", "source": "claire_radar", "source_benchmark_id": "2607.24821", "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/NJU-LINK/AVE-Compass", "githubScope": "benchmark_repo", "githubStars": 9, "hfDailySubmittedAt": "2026-08-06T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 17, "hfPaperUrl": "https://huggingface.co/papers/2607.24821", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "40d4b0b484cd6f1adade0e713f9f134250f79ecdab3a5792daef44fac5d87f71", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AVE-Compass evaluates audio-visual editing models on 145 source videos and 196 instructions with 2,688 checklist items, scoring Instruction Following, Fidelity Preserving, Realism, and Editing Intent via MLLM judging and automated metrics.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We introduce AVE-Compass, a comprehensive benchmark with 145 curated source videos, 196 audio-visually coupled editing instructions, and 2,688 fine-grained checklist items."}, "familyId": "bmf_7977347d6b84", "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/NJU-LINK/AVE-Compass", "url": "https://github.com/NJU-LINK/AVE-Compass"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/NJU-LINK/AVE-Compass", "url": "https://huggingface.co/papers/2607.24821"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/NJU-LINK/AVE-Compass", "url": "https://huggingface.co/api/papers/2607.24821"}], "scope": "benchmark_repo", "url": "https://github.com/NJU-LINK/AVE-Compass", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_ave-compass_477a3826", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/NJU-LINK/AVE-Compass", "data": null, "hfPaper": "https://huggingface.co/papers/2607.24821", "paper": "https://arxiv.org/abs/2607.24821", "pdf": "https://arxiv.org/pdf/2607.24821", "project": null, "report": "https://arxiv.org/abs/2607.24821"}, "metrics": [], "motivation": "While instruction-based video editing has advanced rapidly, real-world videos contain tightly coupled audio and visual signals, and editing one modality often requires coordinated changes in the other.", "name": "AVE-Compass", "oneLine": "AVE-Compass evaluates audio-visual editing models on 145 source videos and 196 instructions with 2,688 checklist items, scoring Instruction Following, Fidelity Preserving, Realism, and Editing Intent via MLLM judging and automated metrics.", "paperTitle": "AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.24821", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "NJU-LINK", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/NJU-LINK/AVE-Compass"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.30735371836622627, "value": 9}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.5107131090274512, "value": 17}}, "confidence": "Medium", "coverage": 0.7, "rank": 140, "score": 40}, "method": "attention-ranking-v13", "rank": 140, "score": 40}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-17", "source": {"authors": ["Yuqing Wen", "Yukai Huang", "Qianqian Xie", "Jiangtao Wu", "Yibin Lin", "Yikai Gu", "Jialu Chen", "Yuanxing Zhang", "and Jiaheng Liu"], "categories": ["cs.MM", "cs.CV", "cs.SD"], "id": "2607.24821", "title": "AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities", "type": "arxiv", "url": "https://arxiv.org/abs/2607.24821"}, "sourceUpdatedAt": "2026-07-17T12:40:13Z", "topics": ["cs.MM"], "venueAttempts": [], "whyItMatters": "This benchmark addresses the gap in evaluating coordinated audio-visual edits, providing a structured way to measure cross-modal consistency and non-target preservation, which is critical for advancing real-world video editing systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
