Fetching metadata from the HF Docker repository... - results Cleanup
- 125 kB Testes + refactor
- 220 kB RSS verification panel, benchmark split (100/150), remove Ollama/REBEL from frontend, sync Qwen3 labels
- 5.96 kB Add compare_pipelines.py - batch evaluation A vs B
- 6.07 kB 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
- 12.1 kB 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
- 21.7 kB Testes + refactor
- 15.1 kB 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
- 13.6 kB 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
- 18.2 kB Testes + refactor
- 16.8 kB 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
- 6.68 kB 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
- 6.14 kB Wikidata inverse, Neo4j cache decoupled, auto-title, cross-article button, batch checkboxes, threshold 0.55
