Use model_key as the addressable identifier and wire comparison-index sidecar

Merge remote-tracking branch 'origin/main' into feat/use-new-backend-data

Tighten eval cards UI and clean up stale local data

Drop input_modalities/output_modalities from MODEL_CARD_COLUMNS

Integrate with test backend data

Add new component files and align app to EvalEval design system

Replace shadcn-styled UI elements with design system primitives

Remove unused public/peer-ranks.json

Add plain-language captions and mode-aware framing for policy readers

Align user-facing labels with paper terminology

Merge corpus dashboard into home as paper-aligned landing

Bake DuckDB envs into runner stage

Restore DuckDB-aware build cache logic

Point Dockerfile at production card_backend dataset

Fix Fibble Arena (and similar) suite link routing

Sort eval-detail filenames by codepoint for parity

Set LOCAL_PIPELINE_OUTPUT/HF_DATA_OFFLINE at Docker build time

Bake DuckDB build-time defaults into Dockerfile

Deploy DuckDB-backed frontend to

Add three-tier test infrastructure for migration safety

Add DuckDB shadow-read backend with source-metadata fix

Separate policy and researcher views

Add interpretive signals, corpus dashboard, and slice browser

Preserve evaluator_relationship when flattening model hierarchy

improve ux

Differentiate audience modes and tighten eval navigation

Aggregate setup aliases and clarify benchmark variants

Fix RewardBench2 key normalization for matrix leaderboard routing

Improve eval/model UX, lite data paths, and leaderboard clarity

Improve homepage loading and eval grouping

Use HF dataset's peer-ranks.json instead of local recomputation

Add per-benchmark comparison histograms on model detail

Add site favicon metadata

Improve eval score displays and summary fallbacks

Harden aggregate evals and cache refresh

Refine evaluation browsing UX

Ignore local cache and data artifacts

Refresh eval cards UI and backend data flow

Fix survey submit: use correct HF commit API JSON format with files array

Fix survey submit: use multipart form data for HF commit API

Add alert feedback on survey submit success/failure

Fix HF commit API field: summary not commit_message

Fix survey submission: use HF commit API instead of deprecated upload

Add survey submission and update survey text for public use

fix bugs

fix bugs

fix bugs

chore: sync EEE pipeline output [2026-04-07 05:13 UTC]

ux changes

Add survey