{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.22778", "kind": "paper", "url": "https://arxiv.org/abs/2606.22778"}, {"id": "gh:hakari-bench/hakari-bench", "kind": "repo", "url": "https://github.com/hakari-bench/hakari-bench"}], "authors": ["Yuichi Tateno"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.22778", "source_url": "https://arxiv.org/abs/2606.22778"}, "categories": ["General AI", "Information retrieval", "Language & Knowledge", "cs.IR"], "description": {"en": "Evaluates retrieval architectures and efficiency settings (dimensionality reduction, quantization, reranking) across 35 benchmarks and 551 tasks in 43 languages, with unified conditions and metrics for BM25, dense, sparse, late interaction, and reranker models."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.22778", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.22778", "title": "HAKARI-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.22778", "modality": null, "name": "HAKARI-Bench", "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_hakari-bench_2bd08ca4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3f930525c93495f8821149b64dc8e33c847e37ccdd7161f596abea31e0160a49", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.22778"}, "publisher": null, "released": "2026-06-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.22778", "source_url": "https://arxiv.org/abs/2606.22778"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-22778", "source": "claire_radar", "source_benchmark_id": "2606.22778", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/hakari-bench/hakari-bench", "githubScope": "benchmark_repo", "githubStars": 32, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 2, "hfPaperUrl": "https://huggingface.co/papers/2606.22778", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Information retrieval"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "1a479749837c506d9b8e8f26a60193dda51557e0f8f714b4c24bdf6473759177", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates retrieval architectures and efficiency settings (dimensionality reduction, quantization, reranking) across 35 benchmarks and 551 tasks in 43 languages, with unified conditions and metrics for BM25, dense, sparse, late interaction, and reranker models.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We present HAKARI-Bench, a lightweight benchmark that reconstructs existing retrieval suites into small datasets (Nano-sets): 35 benchmarks and 551 tasks across 43 languages in a unified format, enabling same-condition, model-agnostic comparison of five retrieval families (BM25, dense, sparse, late interaction, rerankers) and their efficiency variants."}, "familyId": "bmf_c03e69e4986c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/hakari-bench/hakari-bench", "url": "https://github.com/hakari-bench/hakari-bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/hakari-bench/hakari-bench", "url": "https://huggingface.co/papers/2606.22778"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/hakari-bench/hakari-bench", "url": "https://arxiv.org/abs/2606.22778"}], "scope": "benchmark_repo", "url": "https://github.com/hakari-bench/hakari-bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_hakari-bench_2bd08ca4", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/hakari-bench/hakari-bench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.22778", "paper": "https://arxiv.org/abs/2606.22778", "pdf": "https://arxiv.org/pdf/2606.22778", "project": null, "report": "https://arxiv.org/abs/2606.22778"}, "metrics": [], "motivation": "With the rapid spread of retrieval-augmented generation and semantic search, choosing the right embedding and retrieval configuration is increasingly hard.", "name": "HAKARI-Bench", "oneLine": "Evaluates retrieval architectures and efficiency settings (dimensionality reduction, quantization, reranking) across 35 benchmarks and 551 tasks in 43 languages, with unified conditions and metrics for BM25, dense, sparse, late interaction, and reranker models.", "paperTitle": "HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.22778", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-22", "source": {"authors": ["Yuichi Tateno"], "categories": ["cs.IR", "cs.CL"], "id": "2606.22778", "title": "HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions", "type": "arxiv", "url": "https://arxiv.org/abs/2606.22778"}, "sourceUpdatedAt": "2026-06-22T02:42:06Z", "topics": ["cs.IR"], "venueAttempts": [], "whyItMatters": "Fills the gap for a lightweight, high-fidelity proxy for full retrieval benchmarks, enabling rapid model selection, regression detection, and quality-efficiency trade-off analysis under consistent conditions, which is otherwise computationally prohibitive."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
