chore: snapshot in-progress question-gen work before preflight fixes

This commit is contained in:
2026-07-16 04:12:21 -04:00
parent 11a5545f57
commit a4c429b247
39 changed files with 738 additions and 283 deletions
+12 -23
View File
@@ -81,18 +81,11 @@ RETRIEVAL_FAMILY = QuestionFamilySpec(
),
legal_task_types=frozenset(
[
"Action Recognition",
"Action Reasoning",
"Action Prediction",
"Action Sequence",
"Object Recognition",
"Object Reasoning",
"Object Interaction",
"Scene Understanding",
"Event Reasoning",
"Causal Reasoning",
"Temporal Reasoning",
"Spatial Reasoning",
"Action Recognition",
"Attribute Perception",
"OCR Problems",
]
),
leak_profile=LeakTestProfile(
@@ -116,10 +109,7 @@ REASONING_FAMILY = QuestionFamilySpec(
[
"Action Reasoning",
"Object Reasoning",
"Event Reasoning",
"Causal Reasoning",
"Temporal Reasoning",
"Spatial Reasoning",
"Information Synopsis",
]
),
leak_profile=LeakTestProfile(
@@ -141,10 +131,10 @@ ENUMERATION_FAMILY = QuestionFamilySpec(
),
legal_task_types=frozenset(
[
"Action Sequence",
"Object Recognition",
"Object Interaction",
"Scene Understanding",
"Counting Problem",
"Temporal Reasoning",
"Temporal Perception",
"Information Synopsis",
]
),
leak_profile=LeakTestProfile(
@@ -166,10 +156,10 @@ VISUAL_FAMILY = QuestionFamilySpec(
),
legal_task_types=frozenset(
[
"Object Recognition",
"Scene Understanding",
"Attribute Perception",
"Counting Problem",
"OCR Problems",
"Action Recognition",
"Spatial Reasoning",
]
),
leak_profile=LeakTestProfile(
@@ -191,9 +181,8 @@ SPATIAL_FAMILY = QuestionFamilySpec(
),
legal_task_types=frozenset(
[
"Spatial Perception",
"Spatial Reasoning",
"Object Interaction",
"Scene Understanding",
]
),
leak_profile=LeakTestProfile(