yummyyl/EC2Seq2Sql: v1.0.0 (PLOS ONE revision)
Abstract
This release is the revision snapshot for our PLOS ONE manuscript: "EC2Seq2Sql: Patient-Trial Matching with LLM Agents" (Manuscript ID: PONE-D-25-32421R1) It includes: Stage-1 baselines (eligibility text → snippet) under baselines/, producing outputs/ /metrics.json (ROUGE-1/2/L, BLEU) A Stage-1 summary script: scripts/run_stage1_baselines_summary.py → outputs/stage1/table_stage1.{csv,md,tex} Stage-2 schema-grounded SQL generation code under sql_agent/ and evaluation/ A public demo schema (no patient-level data): data/schemas/demo_schema.json For reproducibility, third-party datasets are not redistributed. Use: scripts/download_seq2seq_data.py (pinned upstream commit) and scripts/prepare_splits.py (deterministic splits) See README.md and data/README.md for exact commands. Full Changelog: https://github.com/yummyyl/EC2Seq2Sql/commits/v1.0.0
Fields of Study & Subjects
Artificial Intelligence in Healthcare and Education
Machine Learning in Healthcare
Topic Modeling
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 10 January 2026