mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 03:49:26 +00:00
bench(pairs): real fix-commit pairs for the short families
97 advisory-fix pairs, one repository each (309 advisories examined, 212 rejected with reasons in research-2026-10-01.md): a public fix commit distinct from its parent, the advisory-named function declared on both sides with a changed body. Pointer pairs: materialize.py reads one file per side from a shallow blobless fetch into the pair cache and verifies them with the label builder's matcher (verification.json, bytes read). learn/sources.toml lists the catalog as the advisory-fixes source. Label snapshot: negative repository groups untrusted_destination 8->25, path 3->21, output_encoding 1->22, deserialization 0->21, access_control 0->20; all five reach the per-family floor. Five pairs on reserved repositories were dropped after the reserved-population guard flagged them. Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo
This commit is contained in:
co-authored by
Claude Opus 5.5
parent
658f2d5e39
commit
53c9a7cc65
@@ -56,6 +56,20 @@ recorded = "2026-09-30"
|
||||
status = "development"
|
||||
exclude_tiers = ["title"] # labels read from advisory titles; a sensitivity arm only (`--include-title`)
|
||||
|
||||
# Real fix-commit pairs for the families the pair corpus left without negatives (untrusted_destination, path,
|
||||
# output_encoding, deserialization, access_control). Each pair is a public advisory fix commit distinct from its parent;
|
||||
# the advisory-named function is declared on both sides and its body changes. Pointer pairs: both sides are
|
||||
# materialised into the pair cache by benchmarks/pairs/advisory-fixes/materialize.py (shallow blobless fetch, one
|
||||
# file per side); `evaluation` is the committed per-pair verification record (bytes read, declared both sides).
|
||||
[[source]]
|
||||
id = "advisory-fixes"
|
||||
kind = "pairs"
|
||||
file = "benchmarks/pairs/advisory-fixes/catalog.toml"
|
||||
evaluation = ["benchmarks/pairs/advisory-fixes/verification.json"]
|
||||
recorded = "2026-10-01"
|
||||
status = "development"
|
||||
exclude_tiers = ["title"]
|
||||
|
||||
[[source]]
|
||||
id = "adjudications"
|
||||
kind = "adjudications"
|
||||
|
||||
Reference in New Issue
Block a user