{"record": {"aliases": [], "artifacts": [{"id": "gh:hemachandra666/silent-misresolution-benchmark", "kind": "repo", "url": "https://github.com/hemachandra666/silent-misresolution-benchmark"}], "categories": ["Biology & Drug Discovery", "Language & Knowledge", "Software & AI Compute", "cs.AI"], "description": {"en": "A benchmark for silent misresolution in dictation cleanup, where a system deletes spoken content without leaving a trace in the output; it includes a corpus with revision sites and a scorer for detecting such failures."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/hemachandra666/silent-misresolution-benchmark", "source": "claire_radar", "source_url": "https://github.com/hemachandra666/silent-misresolution-benchmark", "title": "Silent Misresolution"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:hemachandra666/silent-misresolution-benchmark", "modality": null, "name": "Silent Misresolution", "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_silent-misresolution-benchmark_79846646", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "51fb1b95c80209f57c9a49ee2bdc9507b60f582b58cbc2a8567bd747c7091674", "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/hemachandra666/silent-misresolution-benchmark"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:hemachandra666/silent-misresolution-benchmark", "source_url": "https://github.com/hemachandra666/silent-misresolution-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-hemachandra666-silent-misresolution-benchmark", "source": "claire_radar", "source_benchmark_id": "github:hemachandra666/silent-misresolution-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute", "Biology & Drug Discovery"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/hemachandra666/silent-misresolution-benchmark", "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": "Low", "horizon": "7d", "reason": "The benchmark addresses a niche dictation issue and lacks independent validation or a formal release context, limiting its likely early attention.", "score": 0}, "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": "ae4e92e6a40c2113b13a092257571182445fd88d93d7ddf85f0909fe56455986", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The repository is newly created and serves primarily as a single paper's viewpoint probe rather than an established ongoing benchmark; there is no independent paper or official benchmark site referenced, and the corpus is small and narrowly scoped.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:15:55.708965Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "A benchmark for silent misresolution in dictation cleanup, where a system deletes spoken content without leaving a trace in the output; it includes a corpus with revision sites and a scorer for detecting such failures.", "discoverySources": [{"id": "github:hemachandra666/silent-misresolution-benchmark", "type": "github", "url": "https://github.com/hemachandra666/silent-misresolution-benchmark"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "no explicit benchmark release evidence"], "snippet": "silent-misresolution-benchmark A benchmark for silent misresolution in dictation cleanup: when a system deletes what you said and the output still reads perfectly."}, "familyId": "bmf_39f93253928c", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_silent-misresolution-benchmark_79846646", "indexedAt": "2026-08-23T06:55:51.988821Z", "industrySectors": ["Software & Cloud", "Pharma & Biotech"], "links": {"code": "https://github.com/hemachandra666/silent-misresolution-benchmark"}, "metrics": [], "motivation": "silent-misresolution-benchmark A benchmark for silent misresolution in dictation cleanup: when a system deletes what you said and the output still reads perfectly.", "name": "Silent Misresolution", "oneLine": "A benchmark for silent misresolution in dictation cleanup, where a system deletes spoken content without leaving a trace in the output; it includes a corpus with revision sites and a scorer for detecting such failures.", "paperTitle": "silent-misresolution-benchmark", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/hemachandra666/silent-misresolution-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:51.988821Z"}, "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": 517, "score": 23}, "method": "attention-ranking-v13", "rank": 517, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-20", "source": {"authors": ["hemachandra666"], "categories": [], "id": "github:hemachandra666/silent-misresolution-benchmark", "title": "silent-misresolution-benchmark", "type": "github", "url": "https://github.com/hemachandra666/silent-misresolution-benchmark"}, "sourceUpdatedAt": "2026-08-20T02:37:00Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing metrics like edit rate and WER are blind to silent misresolution because correct-looking outputs score well even when information is lost; this benchmark provides a targeted evaluation for a failure mode that is invisible to current quality processes."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
