Merge pull request '让稳定论文身份优先并拒绝多候选标题自动合并' (#25) from codex/paper-identity-guards into main
Metadata integrity checks / metadata (push) Successful in 1m16s

Reviewed-on: #25
This commit was merged in pull request #25.
This commit is contained in:
2026-11-08 15:07:15 +00:00
4 changed files with 87 additions and 7 deletions
+44
View File
@@ -53,6 +53,50 @@ class StoreTests(unittest.TestCase):
self.assertNotEqual(other,paper)
self.assertEqual(self.store.conn.execute('SELECT count(*) FROM match_candidates').fetchone()[0],1)
def test_identifier_anchor_does_not_absorb_a_same_title_arxiv_version(self):
conference,first=self.record('arxiv','1408.1485')
extended,second=self.record('arxiv','cs/0307069')
self.store.decision(extended,second,'ICLR',2025,'main','separate','https://example.org/reject','rejected','Reject')
resolved,_=self.record('dblp','conf/uai/example',{'arxiv':'1408.1485'})
self.assertEqual(resolved,conference);self.assertNotEqual(conference,extended)
c=self.store.conn
self.assertEqual(c.execute('SELECT count(*) FROM papers').fetchone()[0],2)
self.assertEqual(c.execute('SELECT paper_id FROM submissions').fetchone()[0],extended)
self.assertEqual(c.execute('SELECT count(*) FROM paper_merges').fetchone()[0],0)
self.assertEqual(c.execute('SELECT count(*) FROM match_candidates').fetchone()[0],1)
# A refresh of the anchored original source is equally unambiguous.
self.assertEqual(self.record('arxiv','1408.1485')[0],conference)
self.assertEqual(c.execute('SELECT count(*) FROM papers').fetchone()[0],2)
def test_ambiguous_title_aborts_whole_file_without_merging_existing_entities(self):
self.record('arxiv','1408.1485');self.record('arxiv','cs/0307069')
self.store.conn.commit()
rows=[{'source':'dblp','external_id':'conf/uai/new','url':'https://example.org/new',
'title':'An unrelated earlier record in this file','abstract':None,'authors':[],
'venue':'UAI','year':2001,'track':'main','status':'accepted'},
{'source':'dblp','external_id':'conf/uai/ambiguous','url':'https://example.org/ambiguous',
'title':'A sufficiently long example research paper title','abstract':None,
'authors':['Jane Doe','John Smith'],'identifiers':{'doi':'10.0000/not-yet-known'},
'venue':'UAI','year':2001,'track':'main','status':'accepted'}]
path=Path(self.tmp.name)/'ambiguous.jsonl'
path.write_text(''.join(json.dumps(row)+'\n' for row in rows))
path.with_suffix('.manifest.json').write_text(json.dumps({'source':'dblp','list_url':'https://example.org/list','count':2}))
with self.assertRaisesRegex(ValueError,'Ambiguous paper identity'):ingest_file(self.db,path)
c=self.store.conn
for table,count in [('papers',2),('source_records',2),('submissions',0),('decisions',0),('paper_merges',0)]:
self.assertEqual(c.execute('SELECT count(*) FROM '+table).fetchone()[0],count,table)
self.assertEqual(c.execute('SELECT status FROM ingest_runs').fetchone()[0],'failed')
def test_explicit_bridge_merges_only_its_identifier_matches(self):
first,_=self.record('arxiv','2601.00001',authors=['First Author'])
second,_=self.record('arxiv','2601.00002',{'doi':'10.0000/bridge'},authors=['Second Author'])
unrelated,_=self.record('arxiv','2601.00003')
resolved,_=self.record('official','bridge',{'arxiv':'2601.00001','doi':'10.0000/bridge'})
self.assertEqual(resolved,min(first,second))
self.assertEqual(self.store.conn.execute('SELECT count(*) FROM papers').fetchone()[0],2)
self.assertIsNotNone(self.store.conn.execute('SELECT 1 FROM papers WHERE id=?',(unrelated,)).fetchone())
self.assertEqual(self.store.conn.execute('SELECT count(*) FROM paper_merges').fetchone()[0],1)
def test_manifest_count_mismatch_rolls_back_records(self):
path=Path(self.tmp.name)/'source.jsonl'
path.write_text(json.dumps({'source':'pmlr','external_id':'v1/paper','url':'https://example.org/paper','title':'Paper','abstract':'Abstract','authors':[],'venue':'ICML','year':2023,'track':'main','status':'accepted'})+'\n')
+28
View File
@@ -110,6 +110,34 @@ class PostgreSQLIngestionTests(unittest.TestCase):
finally:
reader.close()
def test_identity_anchor_keeps_other_arxiv_version_and_ambiguous_file_rolls_back(self):
title='An identical long research title shared by conference and extended versions'
authors=['Jane Doe','John Smith']
store=self.store()
try:
first,_=store.record('arxiv','1408.1485','https://arxiv.org/abs/1408.1485',title,'Conference abstract',authors)
second,_=store.record('arxiv','cs/0307069','https://arxiv.org/abs/cs/0307069',title,'Extended abstract',authors)
resolved,_=store.record('dblp','known','https://example.org/known',title,None,authors,{'arxiv':'1408.1485'})
self.assertEqual(resolved,first);self.assertNotEqual(first,second)
store.conn.commit()
self.assertEqual(store.conn.execute('SELECT count(*) FROM papers').fetchone()[0],3)
self.assertEqual(store.conn.execute('SELECT count(*) FROM paper_merges').fetchone()[0],1) # migration fixture only
self.assertEqual(store.conn.execute('SELECT count(*) FROM match_candidates').fetchone()[0],1)
finally:store.conn.close()
rows=[self.row('official','earlier',status='accepted',venue='UAI',year=2001),
dict(self.row('official','ambiguous',status='accepted',venue='UAI',year=2001),
title=title,abstract=None,authors=authors,identifiers={})]
with self.assertRaisesRegex(ValueError,'Ambiguous paper identity'):self.ingest(self.file('ambiguous-identity',rows))
store=self.store()
try:
self.assertEqual(store.conn.execute('SELECT count(*) FROM papers').fetchone()[0],3)
self.assertEqual(store.conn.execute('SELECT count(*) FROM source_records').fetchone()[0],4)
self.assertEqual(store.conn.execute('SELECT count(*) FROM submissions').fetchone()[0],1)
self.assertEqual(store.conn.execute('SELECT count(*) FROM paper_merges').fetchone()[0],1)
self.assertEqual(store.conn.execute('SELECT status FROM ingest_runs ORDER BY id DESC LIMIT 1').fetchone()[0],'failed')
self.assertEqual(store.conn.execute("SELECT count(*) FROM source_records WHERE external_id IN (?,?)",('earlier','ambiguous')).fetchone()[0],0)
finally:store.conn.close()
def test_file_import_is_idempotent_and_refreshes_only_own_tags(self):
row = self.row(); row['tags'] = [{'namespace': 'openreview_snapshot:area', 'value': 'theory'}]
path = self.file('reject', [row]); self.ingest(path)