Keep stable paper identities separate from ambiguous title matches

docs/data-sources.md

@@ -178,10 +178,6 @@ paper-atlas collect dblp \
 
 输出按会议/年份/track 分文件，附 manifest、`dblp-normalization.json` 范围审查统计和带哈希的 `dblp-import-queue.json`。不能识别的书目、年份或归属会逐类登记，不默认算作主会。DBLP 不含摘要，因此输出摘要为空、清单为 partial；需要通过有证据的跨来源关联补齐论文实体摘要。书目发表证据与原始审稿决定分别保留，不依据书目缺席推断拒稿。已存在其他出版来源的届次，还须先回填其权威身份并核验镜像记录，不能直接累加投稿数。
 
-早期 AISTATS 1995/1997/1999/2001/2003/2005 和 COLT 1988–1991 的主系列名称本身含 Workshop，不能当作附属 workshop 漏掉。识别要求已核对的完整 proceedings key、会议书目名、原始标题前缀、届数和事件年一致；轨道名为 `main` 表示主系列，保留原始 Workshop 名称及官方目录证据，不改造其历史名称或出版形式。参见 [AISTATS 官方历史目录](https://aistats.org/other.html)、[COLT 协会目录](https://www.learningtheory.org/)。1995 AISTATS 的会议年与1996图书出版年分开；[PMLR R0](https://proceedings.mlr.press/r0/) 是后来重发的 pre-proceedings，不与 DBLP 图书条目盲目逐篇等同。
-
-真正附属的 AISTATS 2010 Active Learning and Experimental Design workshop 仍单列。COLT 2003 与 Kernel Workshop 的 [混合论文集](https://doi.org/10.1007/b12006) 缺少逐篇章节信息，使用 `proceedings_unspecified`，不能整卷改成 main 或附属 workshop。输出保存 `track_scope_note` 与 `track_scope_evidence_url`，导入后仍可追查分类理由；这些出版证据不是真实拒稿或原始决定签名，也不自动修正既有主库记录。
-
 部分早期 SIGIR、CIKM、IJCAI 出版卷使用两位年份键；只有论文集标题明确给出唯一完整年份且与短键相符时才采用，不推测世纪。WWW 特殊兴趣、Alternate track 单列；同卷混合 Applied Data Science、Demo、Industrial 且不能逐篇区分时使用 `proceedings_unspecified`，不把整卷归为某一个具体 track。
 
 书目中的前后页、目录组合和明确会务标题不产生论文录用记录；缺作者的赞助、委员会、活动汇总等标题单独排除。WWW 2019 companion 的匿名合成活动条目归入待核查材料，原始快照仍保留。范围报告分别统计这些原因；单纯缺作者并不排除真实研究论文，也不补造作者。

docs/usage.md

@@ -99,6 +99,8 @@ paper-atlas query --pg-service foundry-research \
 
 `--stats` 中 papers 是当前规则下的论文实体数；source_records 是来源记录数；decisions 是决定观察数。一个投稿可能有多个来源和多条观察，不能相加当作论文数。
 
+已有稳定标识或原来源记录匹配时，该身份优先；同标题、同作者的另一 arXiv 存档或扩展稿不会仅因相似标题被并入。没有身份锚点时，作者佐证的精确标题只有一个候选才可匹配；多个候选会报 `Ambiguous paper identity`，整个采集文件回滚并记录失败运行。应补有证据的标识或先核查版本关系，不删除重复候选或任取第一个。一个新来源明确同时携带两个既有稳定标识时，仍可按既有规则归并并保留投稿、标签和合并日志；未归并的同标题关系继续保留为待核查候选。这些规则不证明全库去重完成。
+
 ## 5. 投稿历史关系审计
 
 ```sh

paper_atlas/collectors/dblp_records.py

@@ -90,8 +90,6 @@ def normalize_row(row,volumes,targets,include_workshops=False,through_year=2026)
               'ambiguous_identifiers':ambiguous,'publication_evidence':'inproceedings bibliography; not an original decision note'}
     if edition.get('track_scope_note'):
         metadata['track_scope_note']=edition['track_scope_note']
-    if edition.get('track_scope_evidence_url'):
-        metadata['track_scope_evidence_url']=edition['track_scope_evidence_url']
     flagged=bool(re.search(r'\b(?:withdrawn|retracted)\b',row.get('publtype') or '',re.I))
     result={'source':'dblp','external_id':row['key'],'url':'https://dblp.org/rec/'+row['key']+'.html',
             'title':title,'abstract':None,'authors':authors,'identifiers':own,

paper_atlas/collectors/dblp_scope.py

@@ -38,39 +38,6 @@ BOOKS = {
 }
 
 
-# These are the historical primary series themselves, not co-located workshops.
-# Exact proceedings keys, original names, ordinals and event years must agree.
-HISTORICAL_WORKSHOP_TITLES = {
-    **{('aistats', year): prefix + ordinal + ' International Workshop on Artificial Intelligence and Statistics'
-       for year, ordinal, prefix in [
-           (1995, 'Fifth', 'Learning from Data - '),
-           (1997, 'Sixth', 'Proceedings of the '),
-           (1999, 'Seventh', 'Proceedings of the '),
-           (2001, 'Eighth', 'Proceedings of the '),
-           (2003, 'Ninth', 'Proceedings of the '),
-           (2005, 'Tenth', 'Proceedings of the ')]},
-    **{('colt', year): 'Proceedings of the ' + ordinal + ' Annual Workshop on Computational Learning Theory'
-       for year, ordinal in [(1988, 'First'), (1989, 'Second'), (1990, 'Third'), (1991, 'Fourth')]},
-}
-
-
-def historical_track(family, base, suffix, volume_key, year, title):
-    if suffix or base.casefold() != family or volume_key != f'conf/{family}/{year}':
-        return None
-    prefix = HISTORICAL_WORKSHOP_TITLES.get((family, year))
-    if (prefix and title.casefold().startswith(prefix.casefold() + ',')
-            and re.search(r'\b' + str(year) + r'\b', title)):
-        url = 'https://aistats.org/other.html' if family == 'aistats' else 'https://www.learningtheory.org/'
-        return ('main', 'Historical primary series named Workshop; exact proceedings key, ordinal, title and event year verified.', url)
-    if (family == 'colt' and year == 2003
-            and title.startswith('Computational Learning Theory and Kernel Machines, 16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003,')
-            and title.endswith('Proceedings')):
-        return ('proceedings_unspecified',
-                'Combined COLT 2003 and Kernel Workshop volume; per-paper section absent from DBLP XML. Do not infer a main or workshop track.',
-                'https://doi.org/10.1007/b12006')
-    return None
-
-
 def scope(row,volume,through_year=2026):
     fields=row['fields'];books=fields.get('booktitle',[])
     if len(books)!=1:return None,'ambiguous_booktitle'
@@ -108,9 +75,7 @@ def scope(row,volume,through_year=2026):
     if len(bibliographic)!=1 or not re.fullmatch(r'\d{4}',bibliographic[0]):return None,'ambiguous_bibliographic_year'
     if int(bibliographic[0])!=year and not re.search(r'\b'+str(year)+r'\b',title):return None,'unverified_year_difference'
     text=(suffix+' '+title).casefold();track='main'
-    historical = historical_track(family, base, suffix, volume['key'], year, title)
-    if historical:track=historical[0]
-    elif 'findings' in text:track='findings'
+    if 'findings' in text:track='findings'
     elif 'shared task' in text:track='shared_task'
     elif 'student research' in text or 'workshop' in text or 'wokshop' in text or base in ('ICCVW','EWSL'):track='workshop'
     elif ('demo track' in text and ('industrial track' in text or 'applied data science track' in text)):track='proceedings_unspecified'
@@ -133,9 +98,6 @@ def scope(row,volume,through_year=2026):
     if venue=='AAMAS' and year<2002:return None,'predecessor_not_aamas'
     result = {'venue':venue,'venue_aliases':aliases,'year':year,'track':track,'bibliographic_year':int(bibliographic[0]),
               'rule':family+':'+base,'proceedings_title':title,'edition_year_basis':year_basis}
-    if historical:
-        result['track_scope_note'] = historical[1]
-        result['track_scope_evidence_url'] = historical[2]
     if venue=='MM' and track=='main':
         # A main MM volume also includes doctoral, tutorials, companion papers
         # and other sections. DBLP XML omits the per-paper TOC section.

paper_atlas/db/store.py

@@ -95,13 +95,19 @@ class Store:
             matches.add(old[0])
         key = normalized(title)
         title_matches = c.execute('SELECT id,authors_json,abstract FROM papers WHERE title_key=?',(key,)).fetchall()
-        authors_set = author_keys(authors)
-        for paper,old_authors,old_abstract in title_matches:
-            overlap = authors_set & author_keys(json.loads(old_authors))
-            # Cross-platform title matching needs independent author corroboration.
-            same_source = c.execute('SELECT 1 FROM source_records WHERE paper_id=? AND source_id=? LIMIT 1',(paper,source_id)).fetchone()
-            if not same_source and len(key)>=25 and (len(overlap)>=2 or (overlap and abstract and abstract.strip()==(old_abstract or '').strip())):
-                matches.add(paper)
+        # An existing identifier/source record anchors the entity. Title
+        # similarity must not pull in another deposit or an extended version.
+        if not matches:
+            title_only_matches = set()
+            authors_set = author_keys(authors)
+            for paper,old_authors,old_abstract in title_matches:
+                overlap = authors_set & author_keys(json.loads(old_authors))
+                same_source = c.execute('SELECT 1 FROM source_records WHERE paper_id=? AND source_id=? LIMIT 1',(paper,source_id)).fetchone()
+                if not same_source and len(key)>=25 and (len(overlap)>=2 or (overlap and abstract and abstract.strip()==(old_abstract or '').strip())):
+                    title_only_matches.add(paper)
+            if len(title_only_matches)>1:
+                raise ValueError('Ambiguous paper identity: multiple author-corroborated title matches; provide verified identifiers')
+            matches = title_only_matches
         if matches:
             paper = min(matches)
             for other in sorted(matches-{paper}):

tests/test_dblp_records.py

@@ -10,7 +10,7 @@ from unittest.mock import patch
 
 from paper_atlas.collectors.dblp import XML_SHA
 from paper_atlas.collectors.dblp_records import collect,identifiers,normalize_row,material_reason
-from paper_atlas.collectors.dblp_scope import scope, HISTORICAL_WORKSHOP_TITLES
+from paper_atlas.collectors.dblp_scope import scope
 from paper_atlas.db.store import Store
 from paper_atlas.ingestion.records import ingest_file
 
@@ -70,69 +70,6 @@ class DblpRecordTests(unittest.TestCase):
         self.assertEqual(scope(self.row(),self.volume('kdd',2024))[1],'crossref_venue_conflict')
         self.assertEqual(scope(self.row(year=2027),self.volume('aaai',2027))[1],'future_edition')
 
-    def test_historical_primary_series_workshop_names_require_exact_editions(self):
-        self.assertEqual(set(HISTORICAL_WORKSHOP_TITLES),
-                         {('aistats',year) for year in [1995,1997,1999,2001,2003,2005]} |
-                         {('colt',year) for year in [1988,1989,1990,1991]})
-        for (family,year),prefix in HISTORICAL_WORKSHOP_TITLES.items():
-            with self.subTest(family=family,year=year):
-                title=prefix+f', {family.upper()} {year}, Proceedings.'
-                volume=self.volume(family,year,title)
-                row=self.row(family,family.upper(),year)
-                if year==1995:
-                    row['fields']['year']=['1996'];volume['fields']['year']=['1996']
-                edition,reason=scope(row,volume)
-                self.assertIsNone(reason);self.assertEqual(edition['track'],'main')
-                self.assertEqual(edition['year'],year)
-                self.assertIn('Historical primary series',edition['track_scope_note'])
-                record,reason=normalize_row(row,{volume['key']:volume},{family.upper()})
-                self.assertIsNone(reason);self.assertEqual(record['metadata']['track_scope_evidence_url'],edition['track_scope_evidence_url'])
-                self.assertEqual(record['metadata']['proceedings_title'],title)
-                if year==1995:self.assertEqual(record['metadata']['bibliographic_year'],1996)
-
-    def test_historical_exception_does_not_promote_affiliated_or_wrong_scope_workshops(self):
-        title=HISTORICAL_WORKSHOP_TITLES[('aistats',1995)]+', AISTATS 1995, Proceedings.'
-        for book,key,changed in [
-            ('AISTATS','conf/aistats/1995w',title),
-            ('AISTATS (Workshops)','conf/aistats/1995',title),
-            ('AISTATS','conf/aistats/1995',title.replace('Fifth','Sixth')),
-            ('AISTATS','conf/aistats/1995',title.replace('1995','1997'))]:
-            volume=self.volume('aistats',1995,changed);volume['key']=key
-            row=self.row('aistats',book,1995);row['fields']['crossref']=[key]
-            self.assertEqual(scope(row,volume)[0]['track'],'workshop')
-        volume=self.volume('aistats',2010,'Active Learning and Experimental Design workshop, In conjunction with AISTATS 2010')
-        volume['key']='conf/aistats/2010w'
-        row=self.row('aistats','AISTATS',2011);row['fields']['crossref']=[volume['key']]
-        self.assertEqual(scope(row,volume)[0]['track'],'workshop')
-
-    def test_combined_colt_kernel_volume_keeps_unknown_per_paper_track(self):
-        title='Computational Learning Theory and Kernel Machines, 16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington, DC, USA, August 24-27, 2003, Proceedings'
-        volume=self.volume('colt',2003,title);row=self.row('colt','COLT',2003)
-        record,reason=normalize_row(row,{volume['key']:volume},{'COLT'})
-        self.assertIsNone(reason);self.assertEqual(record['track'],'proceedings_unspecified')
-        self.assertEqual(record['status'],'accepted')
-        self.assertIn('per-paper section absent',record['metadata']['track_scope_note'])
-        self.assertEqual(record['metadata']['track_scope_evidence_url'],'https://doi.org/10.1007/b12006')
-        volume['key']='conf/colt/2003w';row['fields']['crossref']=[volume['key']]
-        self.assertEqual(scope(row,volume)[0]['track'],'workshop')
-
-    def test_historical_scope_provenance_survives_file_ingestion(self):
-        title=HISTORICAL_WORKSHOP_TITLES[('colt',1988)]+', COLT 1988, Proceedings.'
-        row=self.row('colt','COLT',1988);volume=self.volume('colt',1988,title)
-        record,reason=normalize_row(row,{volume['key']:volume},{'COLT'})
-        self.assertIsNone(reason)
-        with tempfile.TemporaryDirectory() as tmp:
-            root=Path(tmp);path=root/'history.jsonl'
-            path.write_text(json.dumps(record)+'\n')
-            path.with_suffix('.manifest.json').write_text(json.dumps({'source':'dblp','count':1,'list_url':'https://doi.org/10.4230/dblp.xml.2026-11-01','file_sha256':hashlib.sha256(path.read_bytes()).hexdigest()}))
-            ingest_file(root/'sample.sqlite',path)
-            with closing(sqlite3.connect(root/'sample.sqlite')) as connection:
-                track=connection.execute('SELECT track FROM editions').fetchone()[0]
-                metadata=json.loads(connection.execute('SELECT metadata_json FROM source_records').fetchone()[0])
-            self.assertEqual(track,'main')
-            self.assertEqual(metadata['track_scope_evidence_url'],'https://www.learningtheory.org/')
-            self.assertEqual(metadata['proceedings_title'],title)
-
     def test_only_own_identifier_links_are_used_and_ambiguity_is_preserved(self):
         own,ambiguous=identifiers({'ee':['https://doi.org/10.1234/published','https://doi.org/10.48550/arXiv.2401.00001','https://openreview.net/forum?id=realForum'],
                                     'cite':['https://doi.org/10.9999/reference']})

tests/test_index_core.py

@@ -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')

tests/test_postgres_ingestion.py

@@ -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)