{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04302", "kind": "paper", "url": "https://arxiv.org/abs/2608.04302"}, {"id": "gh:multimodal-intelligence-lab/clip-cc-bench", "kind": "repo", "url": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench"}], "authors": ["Mukhtiar Ali", "Harsh Dubey", "Sugam Mishra", "Chulwoo Pack"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04302", "source_url": "https://arxiv.org/abs/2608.04302"}, "categories": ["General AI", "Multimodal", "cs.CV"], "description": {"en": "CLIP-CC-Bench evaluates paragraph-level video description quality using 5-hour movie content and expert-written references. It scores 17 VLMs via coarse- and fine-grained semantic matching with five LLM-based embedding judges."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04302", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04302", "title": "CLIP-CC-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["South Dakota State University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.04302", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.04302", "source_url": "https://openalex.org/W7196977424"}, "key": "claire-radar:2608.04302", "modality": null, "name": "CLIP-CC-Bench", "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_clip-cc-bench_6e2be6c1", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "3f1e53c26e232453a318d893e3869048e5c8d53169ddf5d480913e33a0229f81", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.04302"}, "publisher": null, "released": "2026-08-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04302", "source_url": "https://arxiv.org/abs/2608.04302"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04302", "source": "claire_radar", "source_benchmark_id": "2608.04302", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": "2026-08-10T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 2, "hfPaperUrl": "https://huggingface.co/papers/2608.04302", "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": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "eab2cf54c1d7768789183433e46ea8b124eb03232526c372d3be4133bcf43833", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CLIP-CC-Bench evaluates paragraph-level video description quality using 5-hour movie content and expert-written references. It scores 17 VLMs via coarse- and fine-grained semantic matching with five LLM-based embedding judges.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce CLIP-CC-Bench, an evaluation suite for long-form video description built from 5 hours of movie content segmented into 90-second clips, each paired with an expert-written paragraph-style reference."}, "familyId": "bmf_250f7a769d65", "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/Multimodal-Intelligence-Lab/CLIP-CC-Bench", "url": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench", "url": "https://huggingface.co/papers/2608.04302"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench", "url": "https://huggingface.co/api/papers/2608.04302"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench", "url": "https://arxiv.org/abs/2608.04302"}], "scope": "benchmark_repo", "url": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_clip-cc-bench_6e2be6c1", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench", "data": null, "hfPaper": "https://huggingface.co/papers/2608.04302", "paper": "https://arxiv.org/abs/2608.04302", "pdf": "https://arxiv.org/pdf/2608.04302", "project": null, "report": "https://arxiv.org/abs/2608.04302"}, "metrics": [], "motivation": "Benchmarking video-language models has largely focused on short clips and single-sentence metrics, leaving open whether current systems can generate accurate long-form, paragraph-level descriptions.", "name": "CLIP-CC-Bench", "oneLine": "CLIP-CC-Bench evaluates paragraph-level video description quality using 5-hour movie content and expert-written references. It scores 17 VLMs via coarse- and fine-grained semantic matching with five LLM-based embedding judges.", "paperTitle": "CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models", "primaryDomain": "General AI", "publication": {"evidence": "Accepted and presented at EvalMG 2026, the Second Workshop on Evaluation for Multimodal Generation, co-located with ACM SIGIR 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.04302", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "and presented at EvalMG 2026, the Second Workshop on Evaluation for Multimodal Generation, co-located with ACM SIGIR 202", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Multimodal Intelligence Lab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench"}], "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": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.19411886932144953, "value": 2}}, "confidence": "Medium", "coverage": 0.7, "rank": 384, "score": 23}, "method": "attention-ranking-v13", "rank": 384, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-08-05", "source": {"authors": ["Mukhtiar Ali", "Harsh Dubey", "Sugam Mishra", "Chulwoo Pack"], "categories": ["cs.CV", "cs.IR", "cs.MM"], "id": "2608.04302", "title": "CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04302"}, "sourceUpdatedAt": "2026-08-05T00:20:23Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted and presented at EvalMG 2026, the Second Workshop on Evaluation for Multimodal Generation, co-located with ACM SIGIR 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted and presented at EvalMG 2026, the Second Workshop on Evaluation for Multimodal Generation, co-located with ACM SIGIR 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.04302"}], "reviewStatus": "accepted", "venueName": "and presented at EvalMG 2026, the Second Workshop on Evaluation for Multimodal Generation, co-located with ACM SIGIR 202"}], "whyItMatters": "It fills the gap in long-form video description benchmarks, providing a reliable framework with public scripts and data for reproducible evaluation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
