{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.27154", "kind": "paper", "url": "https://arxiv.org/abs/2608.27154"}], "authors": ["Bojun Zhang", "Junhong Liang", "Feifei Zhai", "Fengxian Ji", "Yu Zhou"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.27154", "source_url": "https://arxiv.org/abs/2608.27154"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates vision-language models on visual text error correction in real-world images, requiring models to identify and fix text errors grounded in visual context."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.27154", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.27154", "title": "ReViCo"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.27154", "modality": null, "name": "ReViCo", "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": "false", "origin_record_id": "bm_revico_34e02af8", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "bb6118b8c5691db70742e943c11313e8876055b40141eb832f0314dce5c40656", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-08T08:58:25.506689Z", "source_url": "https://arxiv.org/abs/2608.27154"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.27154", "source_url": "https://arxiv.org/abs/2608.27154"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-27154", "source": "claire_radar", "source_benchmark_id": "2608.27154", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-09-08", "attemptedAt": "2026-09-08T01:38:09.842216Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.27154", "observedAt": "2026-09-07T01:28:43.988909Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-08T01:38:09.842216Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The source presents a benchmark only as part of a single paper and lacks any public release or adoptable evaluation infrastructure.", "score": 0}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:58:25.506689Z", "inputHash": "937c896a2b91b7d21e39c45312df6c5e3cb400ed2eb5581b6d31fc0f6a4a19d5", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The benchmark is stated to be introduced in the paper, but no public artifact or comparison path is provided, making it primarily a viewpoint probe supporting the paper's findings.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-08T08:58:25.506689Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates vision-language models on visual text error correction in real-world images, requiring models to identify and fix text errors grounded in visual context.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "In this paper, we introduce ReViCo (Real Visual Correction), a benchmark designed to evaluate VLM text understanding through a novel task of visual text error correction."}, "familyId": "bmf_3ee719669886", "firstSeenAt": "2026-08-30", "heat": null, "id": "bm_revico_34e02af8", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.27154", "paper": "https://arxiv.org/abs/2608.27154", "pdf": "https://arxiv.org/pdf/2608.27154", "project": null, "report": "https://arxiv.org/abs/2608.27154"}, "metrics": [], "motivation": "Vision Language Models (VLMs) have shown great success in general visual tasks, yet they still struggle to deeply understand text within images.", "name": "ReViCo", "oneLine": "Evaluates vision-language models on visual text error correction in real-world images, requiring models to identify and fix text errors grounded in visual context.", "paperTitle": "ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.27154", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-08T06:12:53.942187Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Bojun Zhang", "Junhong Liang", "Feifei Zhai", "Fengxian Ji", "Yu Zhou"], "categories": ["cs.CV"], "id": "2608.27154", "title": "ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction", "type": "arxiv", "url": "https://arxiv.org/abs/2608.27154"}, "sourceUpdatedAt": "2026-08-27T14:06:11Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Highlights a gap in VLM text understanding within images, offering a distinctive error-correction evaluation that may inform more robust visual text comprehension."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
