fix: address reviewer feedback — qualify claims, fix AGENTS.md, add quantization caveat

fix: use num_labels=1 instead of num_classes=1

docs: restore OpenSight community validation and preview sections

docs: mention AGENTS.md for LLM tools, add benchmark Space section

docs: final README overhaul + CHANGELOG for July 2026 fix

fix: remove id2label/label2id — not meaningful for num_classes=1 sigmoid output

chore: rename onnx_v1.1→onnx_legacy; update LICENSE

docs: remove test_app references, update ONNX count to 5 variants

chore: exclude test_app from repo (deploy as separate HF Space)

chore: require transformers >= 5.4.0 for shortest_edge resize support

feat: update test_app for corrected ONNX v1.1, single-class output

feat: re-export ONNX from corrected ViT-Small weights

chore: archive legacy weights, rename ONNX to v1.1

test: add 8 evaluation images (real, fake, and adversarial)

docs: update README for num_classes=1 sigmoid output, correct verification

fix: regenerate model.safetensors from correct .pt checkpoint

fix: resolve old checkpoint path relative to repo root

feat: add Old vs New comparison tab

chore: stash UI improvements before test images

docs: update AGENTS.md — ONNX directory, test app, corrected config specs

feat: test app v2 — compare tab, benchmark tab, help tab

docs: overhaul README — fix notice, ONNX variant guide, test app, deprecate old ONNX repo

feat: add ONNX quantized variants (8 models, 21MB–138MB)

chore: move custom wrapper to scripts/, mark as deprecated

fix: correct ViT-Small config — num_classes(1→2), num_attention_heads(12→6), preprocessor(resize 440→384 crop)

Update README.md

Update preprocessor_config.json

Update preprocessor_config.json

Update preprocessor_config.json

Update preprocessor_config.json

Update preprocessor_config.json

Update README.md

Add project page and link to paper (#2)

Update preprocessor_config.json

Rename preprocessor.json to preprocessor_config.json

chore: final config (hopefully)

Update README.md

Update README.md

Upload ViTForImageClassification (#1)

Create 03-analysis.txt

Create 02-restructure.txt

Create quick_analysis.py

chore: restructure new evalset

add: eval dataset resampling round 1

Create logs/.gitkeep

chore: resample-prep

Create scripts/convert_to_pytorch.py

Update README.md

Update config.json

Update README.md