{"slug":"openlair-nemo-curator","source_name":"openlair/nemo-curator","name":"Openlair/Nemo Curator","description":"GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.","version":1,"lift":{"pass_rate_delta_pts":69.57,"pass_rate_pct":91.3,"total_cases":23,"passed_cases":21,"tokens_delta_pct":79.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-06T16:40:45.197769+00:00"},"skill_score":0.913,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":69.57,"with_pass_pct":91.3,"without_pass_pct":21.7,"tokens_delta_pct":79.6,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-06T16:40:45.197769+00:00","run_id":"8d75a7ec-659d-49e8-84f1-2e21710ef69c","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"e00f02db052ff2e2a6e9d5b59d00e54cf7cd90b4867bc166f437f6e9e56dc235","raw_url":"https://app.decimal.ai/s/openlair-nemo-curator/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/openlair-nemo-curator"}