Pinned Loading

1. flowad-baseline flowad-baseline Public

   End-to-end Python baseline for intrusion/anomaly detection on network flows: LogReg/RF + OCSVM/IsolationForest, ROC-PR, thresholds.

   Python

2. textkd-p1-clean-prep textkd-p1-clean-prep Public

   A very simple baseline for text preprocessing + linear classification with Python and scikit-learn. It compares raw vs cleaned (lemmatized) text using TF-IDF + Logistic Regression, then saves metri…

   Python

3. textkd-p2-topics textkd-p2-topics Public

   Small baseline for topic modeling that compares a classic approach (LDA) with a contextual one (BERTopic). It runs on 20 Newsgroups, computes topic coherence (c_v) and topic diversity, and saves me…

   Python

4. textkd-p3-semantic-search textkd-p3-semantic-search Public

   A baseline for semantic search that compares a sparse approach (BM25) with a dense one (SBERT embeddings).

   Python

5. textkd-p4-fewshot-distilbert textkd-p4-fewshot-distilbert Public

   Few-shot text classification baseline: DistilBERT fine-tuning vs TF-IDF+SVM on IMDB. Includes metrics.json, learning curves, and qualitative error examples

   Python

6. amr-ner-baseline amr-ner-baseline Public

   Diagnostic baseline for AMR NER on PubMed abstracts using AIObioEnts in inference-only mode.

   Python