Time every modality and ask which memory came back first

One stride over file order, truncated to the probe count, dropped the
tail of the suite: a 300-probe sample held 128 code, 86 pdf, 36
screenshot, 26 image and 24 video queries and no conversation query at
all, so every report built from it measured five of six modalities.
The budget is now split by suite weight with a floor of one probe per
modality, and a test pins that the frozen sample covers all six.

The set's question type rides along on each query, and a second metric
asks the question recall@10 cannot: when the answer lives in several
dated memories, did the newest come back first? A knowledge-update
question scores 1.000 on recall while the ranking still leads with the
value the speaker has since replaced, and that is the failure the next
task is meant to fix.
This commit is contained in:
ZacharyZhang-NY committed 2026-10-09 06:14:04 -04:00
1 parent 246dae949c
commit a6a1ef05f0
6 files changed
+265 -15

No files matched your search

+9
View File
@@ -32,6 +32,11 @@ def test_the_report_prints_every_arm_with_its_numbers(tmp_path: Path) -> None:
"median_distinct_sources": 4,
"by_modality": {"code": 0.953, "pdf": 0.849},
"modality_counts": {"code": 128, "pdf": 86},
"by_category": {"knowledge-update": 1.0, "temporal-reasoning": 0.947, "unlabelled": 0.84},
"category_counts": {"knowledge-update": 25, "temporal-reasoning": 19, "unlabelled": 256},
"newest_gold_first": 0.44,
"newest_gold_first_by_category": {"knowledge-update": 0.4, "temporal-reasoning": 0.526},
"newest_gold_first_counts": {"knowledge-update": 25, "temporal-reasoning": 19},
}
report: dict[str, Any] = {
"commit": "abcdef123456",
@@ -63,4 +68,8 @@ def test_the_report_prints_every_arm_with_its_numbers(tmp_path: Path) -> None:
assert (
"53,668 atoms at 512 dimensions" in text and "44.7" in text
), "the picture index needs its shape in the report, and its build cost derived from a measured rate"
assert (
"knowledge-update" in text and "1.000" in text and "0.40 (25)" in text
), "the two question types the contract names need their own recall and their own n"
assert "unlabelled" not in text, "an unlabelled bucket would hide which set a number came from"
assert "abcdef123456" in text and "load_average" not in text