{"record": {"aliases": ["How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation"], "artifacts": [{"id": "arxiv:2609.01369", "kind": "paper", "url": "https://arxiv.org/abs/2609.01369"}], "authors": ["Elitsa Yotkova", "Violeta Kastreva", "Petar Velkov", "Hristo Boyanov", "Dimitar Dimitrov", "Ivan Koychev", "Preslav Nakov"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.01369", "source_url": "https://arxiv.org/abs/2609.01369"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates semantic correctness of open-domain QA answers using 8.8k examples derived from widely used QA datasets, with a framework for answer verification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.01369", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.01369", "title": "CAP-Correctness"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.01369", "modality": null, "name": "CAP-Correctness", "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": "true", "origin_record_id": "bm_how-correct-is-your-answer-a-semantic-corr_98ea61f9", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "cbbc1964fed9ecccf91fc39969af963738268cc3492c621b48d6da6a253fcbab", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-03T00:59:34.317835Z", "source_url": "https://arxiv.org/abs/2609.01369"}, "publisher": null, "released": "2026-09-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.01369", "source_url": "https://arxiv.org/abs/2609.01369"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-01369", "source": "claire_radar", "source_benchmark_id": "2609.01369", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T06:30:32.214812Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.01369", "observedAt": "2026-08-31T04:56:28.279469Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T06:30:32.214812Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses a common QA evaluation gap and is released with companion data, but the abstract lacks details on adoption or infrastructure.", "score": 55}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T00:59:34.317835Z", "inputHash": "25561f07cd0aba8a5d57631ea94a3cbef3e9975d9a5a77a096c49744dbcb19e2", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we release CAP-Correctness, an 8.8k-example benchmark spanning widely used QA datasets", "canonicalNameSource": "abstract", "decisionReason": "The abstract explicitly releases a named benchmark with a clear evaluation object and public reuse path, satisfying formal release criteria.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T00:59:34.317835Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates semantic correctness of open-domain QA answers using 8.8k examples derived from widely used QA datasets, with a framework for answer verification.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "Second, we release CAP-Correctness, an 8.8k-example benchmark spanning widely used QA datasets, and CAP-Statements, an 11k-example dataset for converting question-answer pairs into declarative statements for natural language inference (NLI) training and statement-based evaluation."}, "familyId": "bmf_69baba4f5ba3", "firstSeenAt": "2026-09-02", "heat": null, "id": "bm_how-correct-is-your-answer-a-semantic-corr_98ea61f9", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.01369", "pdf": "https://arxiv.org/pdf/2609.01369", "project": null, "report": "https://arxiv.org/abs/2609.01369"}, "metrics": [], "motivation": "Reliable evaluation of open-ended question answering remains a bottleneck for measuring answer correctness of modern LLMs.", "name": "CAP-Correctness", "oneLine": "Evaluates semantic correctness of open-domain QA answers using 8.8k examples derived from widely used QA datasets, with a framework for answer verification.", "paperTitle": "How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.01369", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "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}, "today": {"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": 2, "historyDate": "2026-08-31", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.58, "role": "bonus", "value": 58}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 15}, "method": "attention-ranking-v13", "rank": null, "score": 15}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-09-01", "source": {"authors": ["Elitsa Yotkova", "Violeta Kastreva", "Petar Velkov", "Hristo Boyanov", "Dimitar Dimitrov", "Ivan Koychev", "Preslav Nakov"], "categories": ["cs.CL"], "id": "2609.01369", "title": "How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation", "type": "arxiv", "url": "https://arxiv.org/abs/2609.01369"}, "sourceUpdatedAt": "2026-09-01T15:06:39Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Provides a standardized way to assess whether answers are semantically correct rather than exact-match, and includes a dataset for training NLI-based statement evaluation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
