{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.03370", "kind": "paper", "url": "https://arxiv.org/abs/2609.03370"}, {"id": "gh:sasanolab/framebench", "kind": "repo", "url": "https://github.com/SasanoLab/FrameBench"}], "authors": ["Chihiro Yano", "Ryohei Sasano"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.03370", "source_url": "https://arxiv.org/abs/2609.03370"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "A multiple-choice benchmark for English and Japanese that tests whether models distinguish semantic frames evoked by the same verb across contexts, using FrameNet resources and generation-verification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.03370", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.03370", "title": "FrameBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.03370", "modality": null, "name": "FrameBench", "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": "true", "origin_record_id": "bm_framebench_0d2b1709", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "48a6107ed23032896859a486fdb622c0f748e4c182c65865524b91b1e7a48829", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-07T00:42:15.394147Z", "source_url": "https://arxiv.org/abs/2609.03370"}, "publisher": null, "released": "2026-09-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.03370", "source_url": "https://arxiv.org/abs/2609.03370"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-03370", "source": "claire_radar", "source_benchmark_id": "2609.03370", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-05", "attemptedAt": "2026-09-05T01:35:52.848019Z", "githubRepo": "https://github.com/SasanoLab/FrameBench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.03370", "observedAt": "2026-09-05T01:35:52.848019Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-05T01:35:52.848019Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-05T01:35:52.848019Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark targets a specialized theoretical NLP construct with bilingual resources and public code, likely attracting niche interest from semantic evaluation researchers.", "score": 30}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-07T00:42:15.394147Z", "inputHash": "cc1269420f40732839b6fc7dcc18a8f68a12d136766c3d7cb9f135270abb9f95", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "FrameBench:A Language Understanding Benchmark Based on Frame Semantics", "canonicalNameSource": "paper_title", "decisionReason": "The paper provides a GitHub repository with code and Hugging Face datasets for the benchmark, and describes a fixed evaluation protocol, supporting a reusable public benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-07T00:42:15.394147Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A multiple-choice benchmark for English and Japanese that tests whether models distinguish semantic frames evoked by the same verb across contexts, using FrameNet resources and generation-verification.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this question, we introduce FrameBench, a benchmark grounded in frame semantics."}, "familyId": "bmf_23a98ab20bbb", "firstSeenAt": "2026-09-04", "heat": null, "id": "bm_framebench_0d2b1709", "indexedAt": "2026-09-04T00:41:56.430646Z", "industrySectors": [], "links": {"code": "https://github.com/SasanoLab/FrameBench", "data": null, "paper": "https://arxiv.org/abs/2609.03370", "pdf": "https://arxiv.org/pdf/2609.03370", "project": null, "report": "https://arxiv.org/abs/2609.03370"}, "metrics": [], "motivation": "In frame semantics, sentence comprehension is assumed to proceed by relating lexical meaning to background knowledge called semantic frames, thereby enabling readers to implicitly enrich the text with unstated information.", "name": "FrameBench", "oneLine": "A multiple-choice benchmark for English and Japanese that tests whether models distinguish semantic frames evoked by the same verb across contexts, using FrameNet resources and generation-verification.", "paperTitle": "FrameBench:A Language Understanding Benchmark Based on Frame Semantics", "primaryDomain": "General AI", "publication": {"evidence": "Accepted in EMNLP Findings 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.03370", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "in EMNLP Findings 2026", "verifiedAt": "2026-09-04T00:41:56.430646Z"}, "publications": [], "publishers": [{"name": "SasanoLab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/SasanoLab/FrameBench"}], "ranking": {"30d": {"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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 125, "score": 23}, "method": "attention-ranking-v13", "rank": 125, "score": 23}, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 320, "score": 23}, "method": "attention-ranking-v13", "rank": 320, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-03", "source": {"authors": ["Chihiro Yano and Ryohei Sasano"], "categories": ["cs.CL"], "id": "2609.03370", "title": "FrameBench:A Language Understanding Benchmark Based on Frame Semantics", "type": "arxiv", "url": "https://arxiv.org/abs/2609.03370"}, "sourceUpdatedAt": "2026-09-03T04:59:13Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted in EMNLP Findings 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-09-04T00:41:56.430646Z", "rawValue": "Accepted in EMNLP Findings 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.03370"}], "reviewStatus": "accepted", "venueName": "in EMNLP Findings 2026"}], "whyItMatters": "It probes implicit knowledge enrichment in frame semantics, a core aspect of human language understanding that standard benchmarks rarely isolate."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
