Probabl's open-source skore library makes ML evaluation and experiment tracking a default workflow
GaelVaroquaux · x · 2026-09-16
Probabl promotes skore, an open-source library for data scientists using scikit-learn and other ML frameworks, turning methodological best practices into workflow defaults.
Its getting-started guide walks through a full binary classification workflow (toxicity dataset): proper train/test setup, cross-validated development and comparison of multiple models, final validation on held-out data, and experiment tracking with smart diagnostics. Reports can be pushed to Skore Hub for storing, sharing and exploring.
More from coding & agent
- Grafana dashboards are becoming executable context for AI agents — WirelessLife · 2026-09-16
- Rohan Paul: With MCP Behind Every Model, Picking One Becomes Optional — kevinkern · 2026-09-16
- Same Prompt, Four Models Behind One MCP: Only One Got It Right — rohanpaul_ai · 2026-09-16
- Shumer: Skip Complex Setups, One Manager Agent Session Is Enough — mattshumer_ · 2026-09-16
- Google Cloud API Gateway now acts as a remote MCP server for existing REST APIs — rseroter · 2026-09-16
- Dev ports Blender 5.1 MCP add-on to Blender 3.6, AI builds a full owl scene from one prompt — SpinachOk9137 · 2026-09-16