@diamond2nv

experiment-lifecycle-governance enforces safety and auditability across ml experiment workflows via pin-protected destructive operations, standardized metric definitions with competition thresholds, and multi-model ranking with gating rules.

hfpclawer-paper-search aggregates academic papers from arxiv, huggingface papers, and openreview via multi-source search, deduplication, pdf download, and markdown conversion. designed for daily paper monitoring workflows with optional wiki sync.

clearml-metrics-logging-pattern standardizes metric naming and logging across pdebench training scripts using group/metric pairs compatible with expflow compare-scores. covers loss, validation, competition scores, pde residuals, and system monitoring.

PDEBench competition workflow orchestration with expflow — three pipeline modes (full/fast/skip), distributed HPO, pruner integration, and ClearML HyperParam...

Build and maintain a structured PDE equation registry, analyze competition tasks (difficulty, bottlenecks, score projections), generate strategic recommendat...

Verify academic paper citations using a three-tier fallback pipeline: local FTS5 database → Semantic Scholar API → OpenAlex API. Supports single citation che...