{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.06254", "kind": "paper", "url": "https://arxiv.org/abs/2607.06254"}, {"id": "gh:sharayu-20/vendorbench-100", "kind": "repo", "url": "https://github.com/sharayu-20/vendorbench-100"}], "authors": ["Sharayu N. Deshmukh", "Md Rashidunnabi", "Nelton Tiago Gemo", "Kurundkar G. D.", "Mahamune M. R.", "Nilesh K. Deshmukh"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.06254", "source_url": "https://arxiv.org/abs/2607.06254"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates deepfake image detectors across three paradigms—commercial APIs, vision LLMs, and open-source detectors—on a fixed 100-image adversarial corpus. Uses a unified output schema and scores primarily by Matthews correlation coefficient with ROC-AUC."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.06254", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.06254", "title": "VendorBench-100"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Beira Interior", "Swami Ramanand Teerth Marathwada University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.06254", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.06254", "source_url": "https://openalex.org/W7167728139"}, "key": "claire-radar:2607.06254", "modality": null, "name": "VendorBench-100", "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_vendorbench-100_8cfd26ec", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7399e0a60f8f22e424bb3bb6c3a129481b64858b8aea8f6f7235f8a0e8b2220e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.06254"}, "publisher": null, "released": "2026-07-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.06254", "source_url": "https://arxiv.org/abs/2607.06254"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-06254", "source": "claire_radar", "source_benchmark_id": "2607.06254", "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/sharayu-20/vendorbench-100", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.06254", "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": "bd1b8e98e3b7544d6982fbf9b2e6e71e9d058d53e37115bd6d2068ad8605b349", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates deepfake image detectors across three paradigms—commercial APIs, vision LLMs, and open-source detectors—on a fixed 100-image adversarial corpus. Uses a unified output schema and scores primarily by Matthews correlation coefficient with ROC-AUC.", "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 VendorBench-100, a cross-paradigm benchmark that evaluates 36 representative models using a single adversarial 100-image corpus, a unified output schema, and a common evaluation framework."}, "familyId": "bmf_4b8f07b501cd", "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/sharayu-20/vendorbench-100", "url": "https://github.com/sharayu-20/vendorbench-100"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/sharayu-20/vendorbench-100", "url": "https://huggingface.co/papers/2607.06254"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/sharayu-20/vendorbench-100", "url": "https://arxiv.org/abs/2607.06254"}], "scope": "benchmark_repo", "url": "https://github.com/sharayu-20/vendorbench-100", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_vendorbench-100_8cfd26ec", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/sharayu-20/vendorbench-100", "data": null, "hfPaper": "https://huggingface.co/papers/2607.06254", "paper": "https://arxiv.org/abs/2607.06254", "pdf": "https://arxiv.org/pdf/2607.06254", "project": null, "report": "https://arxiv.org/abs/2607.06254"}, "metrics": [], "motivation": "Deepfake image detection is served by three fundamentally different paradigms - commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors - that are rarely evaluated under a common protocol, making direct comparison difficult.", "name": "VendorBench-100", "oneLine": "Evaluates deepfake image detectors across three paradigms—commercial APIs, vision LLMs, and open-source detectors—on a fixed 100-image adversarial corpus. Uses a unified output schema and scores primarily by Matthews correlation coefficient with ROC-AUC.", "paperTitle": "VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.06254", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Sharayu Deshmukh", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/sharayu-20/vendorbench-100"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 348, "score": 28}, "method": "attention-ranking-v13", "rank": 348, "score": 28}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-07", "source": {"authors": ["Sharayu N. Deshmukh", "Md Rashidunnabi", "Nelton Tiago Gemo", "Kurundkar G. D.", "Mahamune M. R.", "Nilesh K. Deshmukh"], "categories": ["cs.CV", "cs.AI"], "id": "2607.06254", "title": "VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection", "type": "arxiv", "url": "https://arxiv.org/abs/2607.06254"}, "sourceUpdatedAt": "2026-07-29T09:32:00Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Provides a common ground for comparing disparate detector types, addressing the lack of unified evaluation. Identifies metric correlation and calibration issues that matter for real-world deployment decisions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
