diff --git a/.env.example b/.env.example index 389fbe1..11f7c11 100644 --- a/.env.example +++ b/.env.example @@ -131,9 +131,12 @@ IMPORT_PATH=/data/import # Maximum perceptual-hash distance (Hamming, out of 64 bits) for two files to be # treated as duplicate candidates. Lower = stricter (fewer, more confident # matches); higher = looser (catches more re-encodes/resizes but risks false -# positives). Used only by the dedup tool's pairs rebuild — see the dedup CLI / -# `docker compose run --rm dedup`. Default 10. -DUPLICATE_HASH_THRESHOLD=10 +# positives). On real libraries the distance histogram climbs steeply in the 8–10 +# band — coincidental "vaguely similar" pairs, not duplicates — so 4 keeps the +# genuine-duplicate signal without that noise (and far fewer pairs to cluster). +# Used only by the dedup tool's pairs rebuild — see the dedup CLI / +# `docker compose run --rm dedup`. Code default is 10. +DUPLICATE_HASH_THRESHOLD=4 # --------------------------------------------------------------------------- # Static SPA