examples/sample_paper_input.yml

# Example input for: researchlink ingest --config examples/sample_paper_input.yml
#
# Runs fully offline (RESEARCHLINK_OFFLINE=true) with no PDF, keys, or network:
# manual_metadata seeds the module; arxiv_id/github_url become strong identifiers
# used for provenance and (when online) live metadata resolution + discovery.

arxiv_id: "1706.03762"
github_url: "https://github.com/tensorflow/tensor2tensor"
target_output_dir: "examples/sample_outputs"

manual_metadata:
  title: "Attention Is All You Need"
  year: 2017
  venue: "NeurIPS"
  authors:
    - "Ashish Vaswani"
    - "Noam Shazeer"
    - "Niki Parmar"
  abstract: "Introduces the Transformer, a sequence model based solely on attention, dispensing with recurrence and convolutions."
  areas:
    - "deep learning"
    - "natural language processing"
  tags:
    - "transformer"
    - "attention"
    - "sequence modeling"

author_notes: |
  Seminal architecture paper. Metadata needs verification against the primary source.