-
Notifications
You must be signed in to change notification settings - Fork 0
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
- Status: Open.#133 In dariero/RagaliQ;
[FEAT] Real OpenAI transport for cross-provider meta-evaluation
featNew functionality or capabilityNew functionality or capabilityjudgeLLM judge implementationLLM judge implementationStatus: Open.#114 In dariero/RagaliQ;[FIX] K is recorded per run but never compared across runs
choreMaintenance tasks, tooling, and dependenciesMaintenance tasks, tooling, and dependenciestestingTesting infrastructureTesting infrastructureStatus: Open.#108 In dariero/RagaliQ;[FIX] mostly_faithful_one_drift sits 0.033 from the default threshold
bugUnexpected behavior or incorrect evaluation resultsUnexpected behavior or incorrect evaluation resultstestingTesting infrastructureTesting infrastructureStatus: Open.#103 In dariero/RagaliQ;[CHORE] Golden set is saturated — 14 claims gives ~0.07 resolution
choreMaintenance tasks, tooling, and dependenciesMaintenance tasks, tooling, and dependenciestestingTesting infrastructureTesting infrastructureStatus: Open.#90 In dariero/RagaliQ;