{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.17895", "kind": "paper", "url": "https://arxiv.org/abs/2608.17895"}], "authors": ["Liubov Chubarova", "Alexandra Kuleshova", "Daniil Volkov", "Kirill Sultanov", "Alexey Zaytsev"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.17895", "source_url": "https://arxiv.org/abs/2608.17895"}, "categories": ["Bilingual reasoning", "Finance", "Multimodal", "Multimodal reasoning", "OCR-grounded reasoning", "Professional document reasoning", "Reasoning", "Scientific Research & AI for Science"], "description": {"en": "BEAR-Bench evaluates multimodal models on bilingual English-Russian text-dense business and scientific documents with 1,000 human-annotated questions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.17895", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.17895", "title": "BEAR-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.17895", "modality": null, "name": "BEAR-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_bear-bench_6aff8566", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "78862cbcd33f9f61b2b9287337c4621e86ed8a66eaf075675c7fe6b87624bd3b", "relation": "introduces", "review_state": "source-reviewed", "reviewed_at": "2026-08-20", "source_url": "https://arxiv.org/abs/2608.17895"}, "publisher": null, "released": "2026-08-18", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.17895", "source_url": "https://arxiv.org/abs/2608.17895"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-17895", "source": "claire_radar", "source_benchmark_id": "2608.17895", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance", "Scientific Research & AI for Science"], "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/2608.17895", "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"}, "availability": {"evaluatorStatus": "paper_spec_only", "githubStatus": "not_found", "hfDatasetStatus": "not_found", "paperStatus": "available", "submissionStatus": "not_found"}, "capabilities": ["Professional document reasoning", "Multimodal reasoning", "OCR-grounded reasoning", "Bilingual reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "BEAR-Bench describes bilingual question answering over business and scientific document pages, but no official benchmark artifact has been released yet.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "5ca9fb0fd596963ea1c90fe1ad7ee350039a840a6b14ae7ca9163a5e7e44f457", "model": "deepseek-v4-flash"}, "curation": {"reviewedAt": "2026-08-20", "sources": ["https://arxiv.org/abs/2608.17895", "https://arxiv.org/html/2608.17895v1"], "state": "source-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "BEAR-Bench evaluates multimodal models on bilingual English-Russian text-dense business and scientific documents with 1,000 human-annotated questions.", "detail": {"protocol": {"language": "English and Russian", "primaryMetric": "Accuracy using a semantic-equivalence judge", "tasks": "1,000 document-image questions", "version": "v1"}, "taskBreakdown": ["Business", "Science"]}, "displayEligible": false, "domainCuration": {"method": "primary-source-review-v1", "state": "reviewed"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "To address these limitations, we introduce BEAR-Bench (Bilingual Enterprise and Academic Reasoning), a self-contained, complex English-and-Russian benchmark comprising 1000 human-annotated questions based on text-rich business and scientific documents."}, "familyId": "bmf_a95253d365a4", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_bear-bench_6aff8566", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.17895", "paper": "https://arxiv.org/abs/2608.17895", "pdf": "https://arxiv.org/pdf/2608.17895", "project": null, "report": "https://arxiv.org/abs/2608.17895"}, "metrics": [], "motivation": "While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, professional documents remains incompletely evaluated.", "name": "BEAR-Bench", "oneLine": "Tests English–Russian multimodal reasoning over text-dense business and scientific document pages.", "paperTitle": "BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.17895", "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": 0.85, "relation": "introduces", "releasedAt": "2026-08-18", "source": {"authors": ["Liubov Chubarova", "Alexandra Kuleshova", "Daniil Volkov", "Kirill Sultanov", "Alexey Zaytsev"], "categories": ["cs.CL", "cs.AI"], "id": "2608.17895", "title": "BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.17895"}, "sourceUpdatedAt": "2026-08-18T15:29:09Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "Existing multimodal benchmarks underrepresent bilingual professional document reasoning; BEAR-Bench targets this gap for enterprise and academic use cases."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
