config.yaml

# For physics topics, use the specific subtopics, e.g. "Astrophysics"
topic: "Computer Science"
# An empty list here will include all categories in a topic
# Use the natural language names of the topics, found here: https://arxiv.org
# Including more categories will result in more calls to the large language model
categories: ["Artificial Intelligence", "Computation and Language"]

# The email address that the digest will be sent from. must be the address matching
# your sendgrid api key.
# Leaving this empty will cause the script to use the
# FROM_EMAIL environment variable instead
from_email: ""

# The email address you are going to send the digest to
# Leaving this empty will cause the script to use the
# TO_EMAIL environment variable instead
to_email: ""

# Relevance score threshold. abstracts that receive a score less than this from the large language model
# will have their papers filtered out.
#
# Must be within 1-10
threshold: 7

# A natural language statement that the large language model will use to judge which papers are relevant 
#
# For example:
#     "I am interested in complexity theory papers that establish upper bounds"
#     "gas chromatography, mass spectrometry"
#     "making lots of money"
#
# This can be empty, which just return a full list of papers with no judgement or filtering,
# in whatever order arXiv responds with.
interest: |
  1. Large language model pretraining and finetunings
  2. Multimodal machine learning
  3. Do not care about specific application, for example, information extraction, summarization, etc.
  4. Not interested in paper focus on specific languages, e.g., Arabic, Chinese, etc.