{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.24016", "kind": "paper", "url": "https://arxiv.org/abs/2607.24016"}, {"kind": "website", "url": "https://dailybench.github.io/"}], "authors": ["Xin Jiang", "Hao Tang", "Junyao Gao", "Zijie Yang", "Meiqi Cao", "Fei Shen", "Dongming Zhang", "Zechao Li", "Yongdong Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.24016", "source_url": "https://arxiv.org/abs/2607.24016"}, "categories": ["Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "DailyBench is a unified benchmark for evaluating AI-generated image detectors on modern full-image synthesis and object-level manipulation. It comprises FakeBench, with images from recent open-source and commercial generative models, and ManipulationBench, with subtle edits to real images. Detectors are scored by balanced accuracy."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.24016", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.24016", "title": "DailyBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.24016", "modality": null, "name": "DailyBench", "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_dailybench_da2d9ccf", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "d383e52a803532ef80705ddfff78d4005c4ef63b5746dfce522cf23cfc392dbd", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.24016"}, "publisher": null, "released": "2026-07-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.24016", "source_url": "https://arxiv.org/abs/2607.24016"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-24016", "source": "claire_radar", "source_benchmark_id": "2607.24016", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "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": 1, "hfPaperUrl": "https://huggingface.co/papers/2607.24016", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Robot manipulation"], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "829a2752de5a20de0a54a1781dc1e85fcb0bdf831538d19dd4c1a0eebd9e4c94", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DailyBench is a unified benchmark for evaluating AI-generated image detectors on modern full-image synthesis and object-level manipulation. It comprises FakeBench, with images from recent open-source and commercial generative models, and ManipulationBench, with subtle edits to real images. Detectors are scored by balanced accuracy.", "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": "To bridge this gap, we introduce DailyBench, a high-quality unified benchmark for evaluating whether AI-generated image detectors can generalize across both modern full-image synthesis and object-level manipulation."}, "familyId": "bmf_8f2e299ee284", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_dailybench_da2d9ccf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.24016", "paper": "https://arxiv.org/abs/2607.24016", "pdf": "https://arxiv.org/pdf/2607.24016", "project": "https://dailybench.github.io/", "report": "https://arxiv.org/abs/2607.24016"}, "metrics": [], "motivation": "Recent advances in generative models have shifted AI-generated image detection from identifying easily distinguishable, fully synthetic images to identifying highly realistic content generated by both modern generation and manipulation pipelines.", "name": "DailyBench", "oneLine": "DailyBench is a unified benchmark for evaluating AI-generated image detectors on modern full-image synthesis and object-level manipulation. It comprises FakeBench, with images from recent open-source and commercial generative models, and ManipulationBench, with subtle edits to real images. Detectors are scored by balanced accuracy.", "paperTitle": "DailyBench: A Unified Benchmark for AI-Generated and Manipulated Images from Modern Generative Models", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.24016", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "DailyBench Project", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://dailybench.github.io/"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.12247537038455211, "value": 1}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 44}, "method": "attention-ranking-v13", "rank": null, "score": 44}}, "readiness": "Inspectable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-07-27", "source": {"authors": ["Xin Jiang", "Hao Tang", "Junyao Gao", "Meiqi Cao", "Fei Shen", "Dongming Zhang", "Yongdong Zhang"], "categories": ["cs.CV"], "id": "2607.24016", "title": "DailyBench: A Unified Benchmark for AI-Generated and Manipulated Images from Modern Generative Models", "type": "arxiv", "url": "https://arxiv.org/abs/2607.24016"}, "sourceUpdatedAt": "2026-07-28T08:10:58Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Existing detection benchmarks lag behind current generative models, causing a gap between evaluation and real-world scenarios. DailyBench provides a realistic testbed to assess generalization to modern synthesis and manipulation, offering practical value for developing robust detectors."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
