- New Delhi, India
- birha.in
Popular repositories Loading
-
-
-
raweval-eval-core
raweval-eval-core PublicLLM evaluation infrastructure — IAA workbench, LLM-as-a-judge harness, output drift detection, multi-model cost routing. Powers chat.raweval.com.
Python
-
raweval-iaa-engine
raweval-iaa-engine PublicProduction IAA engine — Krippendorff's Alpha, SBERT semantic agreement, Fleiss' Kappa, Shannon entropy, 3-layer collusion detection. Ran behind RawEval's 9-annotator workbench.
Python
-
raweval-interview
raweval-interview PublicAI interview engine — resume parsing, context-aware question generation, deterministic rubric scoring, hire band recommendation. Live at work.raweval.com.
Python
-
raweval-qc-pipeline
raweval-qc-pipeline Public4-stage annotation QC pipeline — rubric generation, 3-judge LLM panel, fraud detection (5 attack vectors), verdict aggregation. Catches bad AI annotations before they reach training data.
Python
If the problem persists, check the GitHub status page or contact support.
