Files
logic-skeleton-bench/tests/test_skeletons.py
T

76 lines
3.1 KiB
Python

import unittest
from logicbench.skeletons import generate_skeletons, resolve_length
class SkeletonTests(unittest.TestCase):
def test_short_world_has_many_entities_and_realized_events(self):
skeleton = generate_skeletons(1, "short", seed=42)[0]
self.assertEqual(skeleton.entity_count, 128)
self.assertEqual(skeleton.simulation_steps, 1000)
self.assertGreater(len(skeleton.events), 300)
self.assertGreaterEqual(len(skeleton.proof_event_ids), 4)
self.assertLess(skeleton.generator_checks["proof_event_ratio"], 0.05)
def test_generation_is_deterministic(self):
first = [item.to_dict() for item in generate_skeletons(4, 4, seed=7)]
second = [item.to_dict() for item in generate_skeletons(4, 4, seed=7)]
self.assertEqual(first, second)
def test_renderer_receives_realized_history_but_no_program_or_answer(self):
skeleton = generate_skeletons(1, "short", seed=1)[0]
payload = skeleton.renderer_payload()
for secret in (
"id",
"hidden_program",
"hidden_state",
"final_state",
"gold_answer",
"proof_event_ids",
"proof_facts",
"generator_checks",
):
self.assertNotIn(secret, payload)
self.assertEqual(len(payload["events"]), len(skeleton.events))
self.assertEqual(len(payload["entity_types"]), 128)
def test_query_is_not_directly_stated_and_proof_events_exist(self):
for skeleton in generate_skeletons(5, "short", seed=20260922):
query_pair = skeleton.query.arguments
direct = [
event
for event in skeleton.events
if event.kind == "RELATE"
and event.arguments.get("predicate") == skeleton.query.predicate
and (event.arguments.get("subject"), event.arguments.get("object")) == query_pair
]
self.assertFalse(direct)
event_ids = {event.id for event in skeleton.events}
self.assertTrue(set(skeleton.proof_event_ids) <= event_ids)
self.assertGreaterEqual(len(skeleton.proof_event_ids), skeleton.complexity)
def test_world_contains_multiple_logic_domains(self):
skeleton = generate_skeletons(1, "short", seed=3)[0]
predicates = {
event.arguments.get("predicate")
for event in skeleton.events
if event.kind == "RELATE"
}
self.assertTrue({"ABOVE", "MEMBER", "SUBSET", "CONNECTED"} <= predicates)
kinds = {event.kind for event in skeleton.events}
self.assertTrue({"MOVE", "UPDATE_NUMBER", "SET_STATE"} <= kinds)
def test_length_and_scale_validation(self):
self.assertEqual(resolve_length("medium"), 6)
self.assertEqual(resolve_length("5"), 5)
with self.assertRaises(ValueError):
resolve_length("huge")
with self.assertRaises(ValueError):
resolve_length(2)
with self.assertRaises(ValueError):
generate_skeletons(1, "short", entity_count=20)
if __name__ == "__main__":
unittest.main()