Files
paper-atlas/tests/test_histories.py
codex-bot 5a925457b0
Metadata integrity checks / metadata (push) Successful in 3m0s
Audit cross-venue submission histories without inferring chronology
2026-11-08 04:30:19 +08:00

115 lines
6.5 KiB
Python

from pathlib import Path
import tempfile
import unittest
from paper_atlas.audits.histories import report
from paper_atlas.db.store import Store
def add_history_fixture(store):
def event(work, forum, venue, year, track, status, observed):
paper, record = store.record('history_fixture', work + '/' + forum,
'https://example.org/' + forum, work + ' title\x00 preserved', 'Abstract', ['Jane Doe'],
{'arxiv': work})
store.decision(paper, record, venue, year, track, forum,
'https://example.org/' + forum + '/' + str(status), status, status or '',
identities=[('openreview', forum)], observed_at=observed)
return paper
# The negative observation was collected later: observation order is not chronology.
event('2501.00001', 'HistoryA01', 'ICLR', 2024, 'main', 'rejected', '2026-02-01T00:00:00Z')
event('2501.00001', 'HistoryA02', 'ICML', 2025, 'main', 'accepted', '2026-01-01T00:00:00Z')
event('2501.00002', 'HistoryB01', 'ICLR', 2024, 'main', 'rejected', '2026-01-01T00:00:00Z')
event('2501.00002', 'HistoryB01', 'ICLR', 2024, 'main', 'accepted', '2026-02-01T00:00:00Z')
event('2501.00003', 'HistoryC01', 'ICLR', 2024, 'main', 'desk_rejected', '2026-01-01T00:00:00Z')
event('2501.00003', 'HistoryC02', 'ICLR', 2024, 'workshop_example', 'accepted', '2026-02-01T00:00:00Z')
event('2501.00004', 'HistoryD01', 'ICML', 2025, 'main', 'accepted', '2026-01-01T00:00:00Z')
event('2501.00004', 'HistoryD01', 'ICML', 2025, 'main', 'withdrawn', '2026-02-01T00:00:00Z')
event('2501.00004', 'HistoryD02', 'ICLR', 2024, 'main', 'rejected', '2026-01-01T00:00:00Z')
event('2501.00005', 'HistoryE01', 'COLM', 2026, 'main', None, '2026-01-01T00:00:00Z')
store.conn.commit()
class HistoryTests(unittest.TestCase):
def setUp(self):
self.tmp = tempfile.TemporaryDirectory()
self.addCleanup(self.tmp.cleanup)
self.db = Path(self.tmp.name) / 'sample.sqlite'
self.store = Store(self.db)
self.addCleanup(self.store.conn.close)
def test_distinct_attempts_venues_and_latest_acceptances_are_not_observation_counts(self):
add_history_fixture(self.store)
result = report(self.db)
self.assertEqual(result['counts'], {
'papers_with_submissions': 5, 'papers_with_multiple_submissions': 3,
'papers_with_historical_negative': 4, 'papers_with_current_known_acceptance': 3,
'papers_with_negative_and_acceptance_in_distinct_attempts': 2,
'papers_with_negative_and_acceptance_in_distinct_venues': 1,
'submissions': 8, 'decision_observations': 9,
'attempts_with_historical_negative': 5,
'attempts_with_historical_negative_and_acceptance': 2,
})
self.assertEqual(result['latest_attempt_status_counts'],
{'accepted': 3, 'desk_rejected': 1, 'rejected': 2, 'unknown': 1, 'withdrawn': 1})
self.assertEqual(len(result['examples']), 2)
first = result['examples'][0]
self.assertIn('\x00', first['title'])
self.assertEqual({r['venue'] for r in first['attempts']}, {'ICLR', 'ICML'})
self.assertTrue(all(r['decisions'][0]['sources'] for r in first['attempts']))
self.assertTrue(all(r['decisions'][0]['decision_date'] is None for r in first['attempts']))
self.assertIn('Not inferred', first['chronology'])
self.assertEqual(result['status'], 'observed_history_audit_not_final_dedup')
self.assertTrue(all(v == 0 for v in result['evidence_relationship_checks'].values()))
def test_missing_and_mislinked_source_evidence_is_reported_without_repair(self):
add_history_fixture(self.store)
self.store.conn.execute('DELETE FROM decision_sources WHERE decision_id=1')
self.store.conn.execute('DELETE FROM submission_sources WHERE submission_id=1')
# Record3 belongs to paper2; move it to paper1 to create a real mismatch.
self.store.conn.execute('UPDATE source_records SET paper_id=1 WHERE id=3')
self.store.conn.commit()
result = report(self.db, examples=0)
checks = result['evidence_relationship_checks']
self.assertEqual(checks['decisions_without_source_links'], 1)
self.assertEqual(checks['submissions_without_source_links'], 1)
self.assertEqual(checks['submission_source_paper_mismatches'], 1)
self.assertEqual(checks['decision_source_paper_mismatches'], 2)
self.assertEqual(self.store.conn.execute('SELECT paper_id FROM source_records WHERE id=3').fetchone()[0], 1)
def test_example_limit_does_not_change_global_counts(self):
add_history_fixture(self.store)
none, one = report(self.db, examples=0), report(self.db, examples=1)
self.assertEqual(none['counts'], one['counts'])
self.assertEqual(none['examples'], [])
self.assertEqual(len(one['examples']), 1)
def test_empty_snapshot_and_invalid_limit_do_not_create_missing_database(self):
empty = report(self.db)
self.assertTrue(all(v == 0 for v in empty['counts'].values()))
self.assertEqual(empty['latest_attempt_status_counts'], {})
absent = self.db.parent / 'absent.sqlite'
with self.assertRaisesRegex(ValueError, 'Examples'):
report(absent, examples=-1)
with self.assertRaisesRegex(ValueError, 'Existing database'):
report(absent)
self.assertFalse(absent.exists())
def test_truncated_example_keeps_the_cross_venue_acceptance_visible(self):
paper, record = self.store.record('fixture', 'many', 'https://example.org/many',
'Many attempts', 'Abstract', [])
for index in range(26):
accepted = index == 25
forum = f'BoundedForum{index}'
self.store.decision(paper, record, 'ICML' if accepted else 'ICLR', 2025, 'main', forum,
'https://example.org/' + forum, 'accepted' if accepted else 'rejected',
'Accept' if accepted else 'Reject', identities=[('openreview', forum)])
self.store.conn.commit()
result = report(self.db)
example, = result['examples']
self.assertEqual((example['attempt_count'], len(example['attempts'])), (26, 20))
self.assertTrue(example['attempts_truncated'])
self.assertEqual({row['latest_observed_status'] for row in example['attempts']},
{'accepted', 'rejected'})
self.assertEqual(result['counts']['submissions'], 26)