Spaces:
Running
Running
Commit History
-
H7: AI Booster (AP) section — 6-row ablation table
JangJaewonVerified signature681355e -
v1.41b: HalluCode section + H6 4-row ablation table + nav link
JangJaewonVerified signature4eb3fed
-
Fix AGGREGATE_STATS avg_hc values from analysis_final2.json
- Claude: 0.4→0.85, Maverick: 0.0→1.8, Qwen: 4.0→2.27 - GPT-4o-mini: 0.8→1.28, GPT-4o: 0.0→0.7, MiniMax: 0.1→0.07 - Update MEI/HRR/SR to precise values from final analysis91cd961
-
Upload index.html with huggingface_hub
JangJaewonVerified signaturee66da7c -
Upload index.html with huggingface_hub
JangJaewonVerified signature8f24f6b -
Upload index.html with huggingface_hub
JangJaewonVerified signature54ab7b4 -
Upload index.html with huggingface_hub
JangJaewonVerified signature1bc7cf7 -
Upload index.html with huggingface_hub
JangJaewonVerified signature558c840 -
Add 4 new models: Llama-4-Maverick, Qwen-2.5-72B, Claude-3.7-Sonnet, GPT-4o
JangJaewonVerified signaturec9f3185 -
Upload hallumaze_final.html with huggingface_hub
JangJaewonVerified signaturec768ac3 -
Upload index.html with huggingface_hub
JangJaewonVerified signature8284c6f -
Upload index.html with huggingface_hub
JangJaewonVerified signature62f231b -
Upload hallumaze_final.html with huggingface_hub
JangJaewonVerified signature3bfe43c -
Upload docs/hallumaze.bib with huggingface_hub
JangJaewonVerified signature537c066 -
Upload docs/hallumaze_arxiv.tex with huggingface_hub
JangJaewonVerified signature6374373 -
Upload docs/figures/fig3_cost_mei.png with huggingface_hub
JangJaewonVerified signature09d6b65 -
Upload docs/figures/fig2_hrr_sr_scatter.png with huggingface_hub
JangJaewonVerified signature99490e7 -
Upload docs/figures/fig1_mei_leaderboard.png with huggingface_hub
JangJaewonVerified signatured1c56cd -
Upload index.html with huggingface_hub
JangJaewonVerified signature2e56e26 -
v1.4.1: paper draft arXiv prep
JangJaewonVerified signature6ccdeb3 -
v1.4: update commit_tree.txt
JangJaewonVerified signature4c8f12f -
v1.4: update docs/research/20260323-hallumaze-paper-draft.md
JangJaewonVerified signaturef52c465 -
v1.4: update .claude/CLAUDE.md
JangJaewonVerified signature7d487f8 -
v1.4: update scripts/build_final_analysis.py
JangJaewonVerified signature6af8c8c -
v1.4: update experiment_results/or_phaseC.json
JangJaewonVerified signature2505fdc -
v1.4: update experiment_results/analysis_final2.json
JangJaewonVerified signaturede22af2 -
v1.4: update hallumaze_final.html
JangJaewonVerified signature04799af
-
v1.2.1 — fix n=60 label nowrap in MEI bar
JangJaewonVerified signatureba7ad14 -
v1.2 — radar standalone panel, comparison grid-tab only
JangJaewonVerified signature90ecc2d -
v1.1.6 — fix scroll: body height auto override
JangJaewonVerified signature91beb28 -
v1.1.5 — fix model card overflow, label cutoff, scroll enabled
JangJaewonVerified signaturef8f2e30 -
Upload index.html with huggingface_hub
JangJaewonVerified signature7a79be2 -
Upload index.html with huggingface_hub
JangJaewonVerified signature2b32db0 -
Upload index.html with huggingface_hub
JangJaewonVerified signature062d8a2 -
Upload index.html with huggingface_hub
JangJaewonVerified signaturee2e6369 -
Upload index.html with huggingface_hub
JangJaewonVerified signature60acff3 -
Upload folder using huggingface_hub
JangJaewonVerified signatured77ae53 -
initial commit
JangJaewonVerified signature77d987c