From da424d4bf675dbd88e5d168b475e60cd0cd908a8 Mon Sep 17 00:00:00 2001 From: Broque Thomas <26755000+Nezreka@users.noreply.github.com> Date: Tue, 5 May 2026 10:42:05 -0700 Subject: [PATCH] Treat 'type beat' as a wrong-version keyword A "type beat" is an instrumental track produced in another artist's style, uploaded to SoundCloud and tagged with that artist's name to game search ranking. They show up as candidates for major-label tracks (e.g. "Eminem - Greatest (Kamikaze) Type Beat - Sit Down" for "Greatest" by Eminem) and have nothing to do with the real song. Add 'type beat' to the version-keyword list so the scorer applies the 0.4x penalty + flags the result as wrong_version. Currently the matcher rejects them via low text-similarity scores anyway, but the explicit keyword makes the rejection deterministic and gives a clear diagnostic in the logs / modal. --- core/downloads/validation.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/core/downloads/validation.py b/core/downloads/validation.py index 7ca346ec..17171535 100644 --- a/core/downloads/validation.py +++ b/core/downloads/validation.py @@ -89,7 +89,12 @@ def get_valid_candidates(results, spotify_track, query): # Detect if the expected track is a specific version (live, remix, acoustic, etc.) expected_title_lower = (expected_title or '').lower() _version_keywords = ['remix', 'live', 'acoustic', 'instrumental', 'radio edit', - 'extended', 'slowed', 'sped up', 'reverb', 'karaoke'] + 'extended', 'slowed', 'sped up', 'reverb', 'karaoke', + # Producer-tag noise common on SoundCloud — "type + # beat" is an instrumental track produced in + # someone's style, tagged with the artist name to + # game search. NEVER the real song. + 'type beat'] expected_is_version = any(kw in expected_title_lower for kw in _version_keywords) scored = []