{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.03884", "kind": "paper", "url": "https://arxiv.org/abs/2608.03884"}], "authors": ["Sadab Shiper", "Tawsif Tashwar Dipto", "Mir Md Inzamam", "Eshat Tanzeem"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.03884", "source_url": "https://arxiv.org/abs/2608.03884"}, "categories": ["General AI", "Multimodal"], "description": {"en": "BanglaWild is a benchmark of 2,535 Bengali scene text images with verbatim gold transcriptions and diagnostic attributes. It evaluates OCR and vision-language models on in-the-wild scene text recognition."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.03884", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.03884", "title": "BanglaWild"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Islamic University of Technology", "BRAC University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.03884", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.03884", "source_url": "https://openalex.org/W7172513884"}, "key": "claire-radar:2608.03884", "modality": null, "name": "BanglaWild", "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_banglawild_bb99b93a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "109d2a3439566ec41b24a9001e79197a644914d723b9e0608cb0e206c4a0541f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.03884"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.03884", "source_url": "https://arxiv.org/abs/2608.03884"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-03884", "source": "claire_radar", "source_benchmark_id": "2608.03884", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.03884", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "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": "310fbe67f6a81ed656d1d8417f49aba8997fa40d7fb29735aa05d8a0c8d04162", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "BanglaWild is a benchmark of 2,535 Bengali scene text images with verbatim gold transcriptions and diagnostic attributes. It evaluates OCR and vision-language models on in-the-wild scene text recognition.", "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"], "snippet": "To address this gap, we introduce BANGLAWILD, a benchmark of 2,535 Bengali scene text images, each paired with a verbatim gold transcription, two categorical axes, four diagnostic attributes, and an orthographically standard form where the in-image text deviates from canonical spelling."}, "familyId": "bmf_14ca929f6ebd", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_banglawild_bb99b93a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.03884", "paper": "https://arxiv.org/abs/2608.03884", "pdf": "https://arxiv.org/pdf/2608.03884", "project": null, "report": "https://arxiv.org/abs/2608.03884"}, "metrics": [], "motivation": "In-the-wild Bengali scene text recognition is largely unmeasured: existing resources target handwritten documents or constrained sign-board parsing, report only aggregate edit-distance metrics, and evaluate either conventional OCR or VLMs, never both on the same in-the-wild data.", "name": "BanglaWild", "oneLine": "BanglaWild is a benchmark of 2,535 Bengali scene text images with verbatim gold transcriptions and diagnostic attributes. It evaluates OCR and vision-language models on in-the-wild scene text recognition.", "paperTitle": "BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.03884", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"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": "2026-08-04", "source": {"authors": ["Sadab Shiper", "Tawsif Tashwar Dipto", "Mir Md Inzamam", "Eshat Tanzeem"], "categories": ["cs.CV", "cs.CL"], "id": "2608.03884", "title": "BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.03884"}, "sourceUpdatedAt": "2026-08-04T16:20:53Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Fills the gap of measuring in-the-wild Bengali scene text recognition, providing a common testbed for OCR and VLMs and enabling analysis of error types."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
