{"record": {"aliases": [], "artifacts": [{"id": "gh:gbbarra/llm-summarization-benchmark-ptbr", "kind": "repo", "url": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr"}, {"kind": "dataset", "url": "https://zenodo.org/badge/DOI/10.5281/zenodo.22042502.svg"}], "categories": ["Language & Knowledge", "Software & AI Compute", "cs.AI"], "description": {"en": "Evaluates reference-faithful summarization of a technical report in Brazilian Portuguese across 9 local LLMs, using a pre-registered rubric with six runs per model and reported scores, timing, and speed."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/gbbarra/llm-summarization-benchmark-ptbr", "source": "claire_radar", "source_url": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr", "title": "LLM Summarization Benchmark — Brazilian Portuguese"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:gbbarra/llm-summarization-benchmark-ptbr", "modality": null, "name": "LLM Summarization Benchmark — Brazilian Portuguese", "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-candidate", "display_eligible": "false", "origin_record_id": "bm_llm-summarization-benchmark-ptbr_c5bebc73", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "73910ec0604f194ad82772fed5c3ae619c24999cbdd139c29c4be5bd79428503", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-26T06:15:55.708965Z", "source_url": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr"}, "publisher": null, "released": "2026-08-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:gbbarra/llm-summarization-benchmark-ptbr", "source_url": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-gbbarra-llm-summarization-benchmark-ptbr", "source": "claire_radar", "source_benchmark_id": "github:gbbarra/llm-summarization-benchmark-ptbr", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "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": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses a niche but growing area of multilingual LLM evaluation with detailed artifacts, likely attracting moderate interest from researchers focused on non-English benchmarks.", "score": 52}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:15:55.708965Z", "inputHash": "af5dc59bf039ba03abedd2090646bbd9f3d58d84fe011d581b56368e2464457b", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The formal benchmark name is source-grounded, but the public release does not yet meet the independent evidence or adoption threshold.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:15:55.708965Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates reference-faithful summarization of a technical report in Brazilian Portuguese across 9 local LLMs, using a pre-registered rubric with six runs per model and reported scores, timing, and speed.", "discoverySources": [{"id": "github:gbbarra/llm-summarization-benchmark-ptbr", "type": "github", "url": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "llm-summarization-benchmark-ptbr # LLM Summarization Benchmark — Brazilian Portuguese [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22042502.svg)](https://doi.org/10.5281/zenodo.22042502) *Six runs per model, a pre-registered rubric, and a trap-laden source text: which local LLMs summarize a technical report with strict faithfulness to the reference — and how fast — on a mini PC with no discrete GPU?* A fully reproducible benchmark of **reference-faithful summarization** across 9 local LLM"}, "familyId": "bmf_d1dd765edb10", "firstSeenAt": "2026-08-22", "heat": null, "id": "bm_llm-summarization-benchmark-ptbr_c5bebc73", "indexedAt": "2026-08-22T19:19:35.289219Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr", "data": "https://zenodo.org/badge/DOI/10.5281/zenodo.22042502.svg", "project": "https://doi.org/10.5281/zenodo.22042502"}, "metrics": [], "motivation": "llm-summarization-benchmark-ptbr # LLM Summarization Benchmark — Brazilian Portuguese [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22042502.svg)](https://doi.org/10.5281/zenodo.22042502) *Six runs per model, a pre-registered rubric, and a trap-laden source text: which local LLMs summarize a technical report with strict faithfulness to the reference — and how fast — on a mini PC with no discrete GPU?* A fully…", "name": "LLM Summarization Benchmark — Brazilian Portuguese", "oneLine": "Evaluates reference-faithful summarization of a technical report in Brazilian Portuguese across 9 local LLMs, using a pre-registered rubric with six runs per model and reported scores, timing, and speed.", "paperTitle": "llm-summarization-benchmark-ptbr", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-22T19:19:35.289219Z"}, "publications": [], "ranking": {"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": 509, "score": 23}, "method": "attention-ranking-v13", "rank": 509, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-21", "source": {"authors": ["gbbarra"], "categories": [], "id": "github:gbbarra/llm-summarization-benchmark-ptbr", "title": "llm-summarization-benchmark-ptbr", "type": "github", "url": "https://github.com/gbbarra/llm-summarization-benchmark-ptbr"}, "sourceUpdatedAt": "2026-08-22T13:46:12Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides a scarce multilingual evaluation resource for Portuguese summarization with detailed protocol and raw outputs, enabling reproducibility and comparison of local model faithfulness and efficiency."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
