connor
c89a723603
Ground-up replacement for news_triage, whose signal quality failed because it had no representation of what its user likes -- three keywords fed to BM25 plus a two-term substring blocklist. profile/ holds the taste model as prose and TOML: 11 interest blocks, 3 veto blocks, 5 importance blocks, each a set of probe sentences to be embedded. The [scoring] constants are fitted, not guessed. CALIBRATION.md records the measurements against all 3,885 items in the v0.2 database and 40 real feedback labels, including two findings that changed the design: - compare blocks by z-score within block, never raw cosine; raw cosine let geopolitics win 78% of items and buried known-liked items at median rank 1246 of 3885 (293 after normalizing) - veto needs a margin over the interest signal, not a threshold; a plain 0.55 cutoff falsely killed "Belgian mayor blocks club from hosting Israeli opponent in Europa League", which the old substring blocklist also killed
33 lines
487 B
Plaintext
33 lines
487 B
Plaintext
# Allowlist ignore file, per the house convention: ignore everything, then
|
|
# explicitly re-admit tracked paths.
|
|
**/*
|
|
|
|
!.gitignore
|
|
!README.md
|
|
!pyproject.toml
|
|
!uv.lock
|
|
|
|
!profile/
|
|
!profile/**
|
|
|
|
!news/
|
|
!news/**
|
|
|
|
!tests/
|
|
!tests/**
|
|
|
|
!deploy/
|
|
!deploy/**
|
|
|
|
# Re-exclude generated and local artifacts that would otherwise slip through
|
|
# the directory re-admissions above.
|
|
news/**/__pycache__/**
|
|
news/**/*.pyc
|
|
tests/**/__pycache__/**
|
|
tests/**/*.pyc
|
|
**/*.db
|
|
**/*.db-wal
|
|
**/*.db-shm
|
|
**/*.npy
|
|
.venv/**
|