Commit History

13 days ago

  1. Update READMEs for Vite, Python 3.13 and new UI

    82c93a0
  2. UX: example articles, collapsible input, Ctrl+Enter and analysis timer

    29ce6c0
  3. New app icon; CPU-only torch in Docker for HF Spaces free tier

    82e0f1c
  4. Fix path traversal in SPA catch-all route

    72b05a3
  5. Fix highlight alignment: use backend sentence spans instead of client-side split

    2387007
  6. Redesign UI: sidebar layout, light/dark themes, lazy-loaded tabs

    9566847
  7. Pin Python dependencies, replace PyPDF2 with pypdf, Docker on Python 3.13

    f5317c9
  8. Upgrade frontend dependencies to latest

    cb66a71
  9. Migrate frontend from Create React App to Vite

    86e66c8
  10. Fix

    ad95ccd
  11. Made some changes

    8f2164d

  1. Cleanup

    09ff969
  2. Cleanup

    3652887

  1. Cleanup

    03b780d
  2. Add presentation

    6062f94

  1. RSS/parameter configuration UI, feedparser migration, effective-params logging

    914024f

  1. Fix readme

    6d71f60

  1. fix: copy tsconfig.json into Node build stage (required for CRA TypeScript resolution)

    046a308
  2. fix: npm ci --legacy-peer-deps for Node 20 peer dep conflicts

    c808b45
  3. Fix multi-stage Docker build for HF Spaces

    6523364
  4. Include frontend build for HF Spaces

    2fb0a8f
  5. Fix readme

    97e2882
  6. HuggingFace Spaces deploy + Neo4j Aura support

    a987836
  7. Refactor + fixes

    b886f85

  1. Fix readme

    4ed202a
  2. Set FAKE_THRESHOLD=0.75, benchmark results P=0.909 R=0.227 F1=0.364 Acc=0.650 FP=1 FN=34

    f734793
  3. integrate coverage_factor into TCS formula (0.85+0.15*cov), unify severity labels, upload.py error handling, dead code cleanup, TextHighlight regex fix, InconsistencyList TYPE_LABELS complete, Swagger description updated

    6432950
  4. Reports

    833a4ee
  5. threshold sweep + TF-IDF/RF/SVM baselines, event-date KG +64 canonical events (1169->1233 facts), V8 action-before-office check, _check_event_date() in external.py

    8702811
  6. Fix

    039be26

  1. DATE_TOLERANCE 400->200, cross-entity overlap check with same_role_category filter, Reference KG +22 manual facts (Nixon/Ford/LBJ/JFK/Truman/Blair/Thatcher/Starmer/Macron/Tusk + legislation) — F1 0.345->0.393, Recall 0.227->0.273, Sep +0.129->+0.151

    4024770

  1. RSS verification panel, benchmark split (100/150), remove Ollama/REBEL from frontend, sync Qwen3 labels

    8728df8
  2. Some fix

    1c00875

  1. Replace Ollama/llama3 with spacy-llm + Qwen3-1.7B (Pipeline B + Explainer), archive REBEL (F1=0.038), fix TCS n_claims=0 score, add ISOT/RAGuard eval scripts, update start.sh and requirements

    4a6ebd0

  1. RSS feeds updated + Reference KG 517->1161 facts + entity_label fix + Neo4j reconnect

    0232c1f
  2. RSS Stream C3b + HITL endpoint + frontend toggles

    2ff93ce

  1. Refactor

    f026e7a
  2. Pipeline C REBEL-large extractor + orchestrator integration

    fc08c44
  3. Testes + refactor

    c4c6759

  1. Testes + refactor

    f22b61b

  1. New translation

    3e5f65e
  2. Wikidata inverse, Neo4j cache decoupled, auto-title, cross-article button, batch checkboxes, threshold 0.55

    d638717

  1. New Readme

    f91939a
  2. Add new articles and script for liar dataset

    054da92
  3. Entity subject matching threshold + V5 HOLDS_POSITION only + KG tolerance 400d

    8ec175f
  4. Extended benchmark 25 articles + run_evaluation.py with LIAR/FakeNewsNet/boxplot

    af33f82

  1. Persist article title, source and analyzed_at in Article node

    fcbc9fa
  2. Translate all comments, logs and docstrings to English across 22 backend files

    31b3ba4
  3. Refactor and eliminate non-relevant files

    945f8be
  4. Manual benchmark 5 articles + run_benchmark.py with Precision/Recall/F1

    44ec294