fix: mobile layout zoomed out bug during animations and splash screen

fix: correct vertical stretch on input box and fix hero section centering

fix: layout clipping on smaller screens and humanize UI text

fix: correct layout blowout and revert wording

fix: resolve shrinking layout bug and add mobile responsiveness

fix: CORS allow_origins typo and frontend badge classes

fix: resolve Bi-LSTM model loading error and adjust frontend input UI to fit single page

remove deberta model completely

add Bi-LSTM model weights and vocab

update frontend to use Bi-LSTM, point to HF Space, remove AI text, and add scan history

update backend to Bi-LSTM model and fix paths

fix: correct inverted label mapping

fix: resolve softmax crash in AI detection by accessing .logits attribute

fix: resolve AI detection failure by loading model directly and keep DeBERTa veracity engine

feat: revert core engine to DeBERTa-v3 and fix accuracy by matching training input (content only)

feat: switch to Bi-LSTM for maximum accuracy and fix training-inference mismatch

docs: add planning.txt for future true MTL transition

feat: implement dual-input system and dedicated AI detection for maximum accuracy

fix: add missing os import in backend utils

fix: bundle deberta tokenizer files to bypass Hub parsing errors

fix: apply DeBERTa tokenizer stability fix (use_fast=False) and protobuf

fix: add tiktoken dependency for DeBERTa tokenizer

fix: sanitize API URL and improve response validation to prevent blank screen

debug: add logs and safer scroll logic to handlePredict

fix: prevent blank screen on interaction by improving error handling and adding error UI

fix: add missing build configuration files and fix typescript errors

feat: initial clean project setup (root-level)