Keep legacy source refreshes in their verified joint editions

Reviewed-on: #17

.gitea/workflows/check.yml

@@ -49,12 +49,15 @@ jobs:
               subprocess.run([str(venv/'bin/paper-atlas'),'--help'],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-m','paper_atlas','collect','cvf','--help'],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-m','paper_atlas','maintain','postgres','--help'],cwd=outside,check=True)
+              subprocess.run([python,'-I','-B','-m','paper_atlas','maintain','joint-editions','--help'],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-m','paper_atlas','import','records','--help'],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-m','paper_atlas','import','arxiv','--help'],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-m','paper_atlas','maintain','backfill','--help'],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-m','paper_atlas','audit','public-openreview','--help'],cwd=outside,check=True)
+              subprocess.run([python,'-I','-B','-m','paper_atlas','audit','histories','--help'],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-c','from paper_atlas.postgres.writer import PostgresStore, WriteConnection'],cwd=outside,check=True)
               smoke = "from paper_atlas.db.store import Store; from paper_atlas.config import DEFAULT_REGISTRY; import json; assert {'COLM','MM','MLSys'} <= {v['acronym'] for v in json.loads(DEFAULT_REGISTRY.read_text())['venues']}; s=Store('installed.sqlite'); s.conn.close()"
               subprocess.run([python,'-I','-B','-c',smoke],cwd=outside,check=True)
               subprocess.run([python,'-I','-B','-m','paper_atlas','query','--db','installed.sqlite','--stats'],cwd=outside,check=True)
+              subprocess.run([python,'-I','-B','-m','paper_atlas','audit','histories','--db','installed.sqlite','--examples','0'],cwd=outside,check=True)
           PY

README.md

@@ -86,3 +86,5 @@ paper-atlas collect colm --cache /data/paper-index/raw/http-cache \
 CI 在已授权的远程 runner 上运行测试、构建 wheel，并从源码目录外验证安装后的命令及随包资源。数据库全量去重和覆盖率是独立的数据验收步骤，不因代码测试通过而自动完成。
 
 开发通过工作分支和 PR 交付，由用户手动合并。
+
+历史联合会议的既有届次归属可通过 [`maintain joint-editions`](docs/joint-editions.md) 先只读规划，再按计划哈希执行；保留论文与投稿决定来源，不重导入。

docs/joint-editions.md

@@ -0,0 +1,67 @@
+# Repairing joint conference membership
+
+EURAI's [official history](https://www.eurai.org/ecai/history) identifies ECAI 2018
+and 2022 as joint IJCAI/ECAI conferences. The pinned DBLP volumes
+`conf/ijcai/2018` and `conf/ijcai/2022` use `IJCAI` as their booktitle and title.
+Existing records can therefore already be present under IJCAI while an ECAI query
+shows a missing year. Adding ECAI as a global alias to the ordinary IJCAI venue
+would incorrectly include all other IJCAI years.
+
+The existing canonical `ECAI+IJCAI` venue has both member aliases. This maintenance
+command changes only the venue reference of the two existing `main` edition rows.
+Edition IDs, submission IDs, decisions, source text, authors, identifiers, tags,
+source links and coverage records stay intact. It does not merge or create papers
+or submissions, resolve per-paper tracks, or turn reviews into negative decisions.
+The DBLP collector applies the joint mapping only to these two exact main volume
+keys; original booktitle/title remain in source metadata with the membership evidence.
+The shared ingestion entry point also resolves these exact pinned source volumes before
+creating an edition, so refreshing an older normalized file cannot recreate a separate
+IJCAI edition. Other sources, years, workshop volumes and additional tracks retain their existing rules.
+
+## Review a read-only plan
+
+Use a runtime containing this repair command. The configured PostgreSQL writer lock
+is used only for the apply operation; do not replace a newer ingestion runtime with
+an older main-based feature branch.
+
+```sh
+PGSERVICEFILE=/etc/paper-atlas/pg_service.conf paper-atlas maintain joint-editions \
+  --pg-service foundry-research --pg-schema research --out joint-plan.json
+```
+
+The preflight requires the existing joint venue and exactly its two member aliases,
+one nonempty unambiguous edition per year, and matching pinned DBLP volume evidence
+for every existing submission. A colliding target edition, missing provenance or
+unexpected source scope fails closed. The plan binds current database/schema, IDs,
+counts and full fingerprints of affected papers, identifiers, source records, tags,
+submissions, decisions and their provenance, and coverage rows. Observation time is
+recorded separately from conference year. These are scoped checks, not a final global
+identity or conference completeness audit.
+
+## Apply the exact reviewed plan
+
+Compute the file's SHA256 after review and pass it explicitly:
+
+```sh
+PGSERVICEFILE=/etc/paper-atlas/pg_service.conf paper-atlas maintain joint-editions \
+  --pg-service foundry-research --pg-schema research --plan joint-plan.json \
+  --plan-sha256 "$PLAN_SHA256" --out joint-applied.json
+```
+
+The plan hash is checked before opening a writer. Current evidence is checked again
+under the dataset writer lock; both edition updates and an audit marker commit in one
+transaction. Protected row hashes are checked again before commit. Changed evidence
+requires a fresh reviewed plan. Existing output reports are preserved; choose a new
+path for another run. SQLite samples use `--db sample.sqlite`; the frozen production
+backup remains protected.
+
+If a response is lost after commit, rerun with the same plan and a new output path.
+When protected evidence is unchanged and both editions already point to the joint
+venue, the result is `already_joint` with zero updates. It does not replay imports or
+regenerate source records. Keep the plan, apply report and independent postcheck
+alongside collection evidence. The audit marker is `joint_ijcai_ecai_2018_2022_v1`.
+
+Publication counts can differ between the DBLP volume and the current publisher
+page. This membership repair preserves all existing rows rather than deleting entries
+to force an aggregate match; section-level main/invited/other classification and
+publication completeness require separate per-paper evidence.

docs/usage.md

@@ -79,10 +79,10 @@ paper-atlas maintain merge --db /data/paper-index/samples/example.sqlite \
 ## 4. 查询与分析前检查
 
 ```sh
-paper-atlas query --db /data/paper-index/papers.sqlite --query '"language model"' --limit 20
-paper-atlas query --db /data/paper-index/papers.sqlite --tag arxiv:category=cs.AI
-paper-atlas query --db /data/paper-index/papers.sqlite --venue ICLR --year 2025 --status rejected
-paper-atlas query --db /data/paper-index/papers.sqlite --paper 123
+paper-atlas query --pg-service foundry-research --query '"language model"' --limit 20
+paper-atlas query --pg-service foundry-research --tag arxiv:category=cs.AI
+paper-atlas query --pg-service foundry-research --venue ICLR --year 2025 --status rejected
+paper-atlas query --pg-service foundry-research --paper 123
 paper-atlas coverage --db /data/paper-index/papers.sqlite --out /data/paper-index/collected/coverage.json
 ```
 
@@ -91,10 +91,26 @@ paper-atlas coverage --db /data/paper-index/papers.sqlite --out /data/paper-inde
 例如，查找在 ICLR 有拒稿记录、但在其他已知投稿中已有录用的论文：
 
 ```sh
-paper-atlas query --db /data/paper-index/papers.sqlite \\
+paper-atlas query --pg-service foundry-research \
   --venue ICLR --status rejected --outcome accepted
 ```
 
 `known_acceptances` 列出目前仍为录用状态的各次投稿及会议、年份、track 和决定证据，`publication_outcome` 汇总为 accepted 或 no_known_acceptance。汇总会检查所有会议和 track，不把某次拒稿覆盖到整篇论文；同一次投稿的后续撤稿也会更新该次状态并保留原决定。no_known_acceptance 只表示现有来源中没有查到录用，不能称为“从未录用”。
 
 `--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。
+
+## 5. 投稿历史关系审计
+
+```sh
+PGSERVICEFILE=/etc/paper-atlas/pg_service.conf paper-atlas audit histories \
+  --pg-service foundry-research --pg-schema research --examples 20 \
+  --out /data/paper-index/collected/history-audit.json
+```
+
+使用一个只读一致性快照，区分论文实体、投稿和决定观察；分别统计同次投稿曾出现负面与录用观察、不同投稿共存负面与当前已知录用、不同会议之间的共存。workshop/main 是不同 track，属于同一会议时不算跨会议；会议别名也不会增加一个会议。当前已知录用使用与 `query --outcome` 相同的“每次投稿最新观察”规则，后续撤稿的该次投稿不再算当前录用，但旧录用决定仍保留。
+
+报告不凭观察时间、届次年份或行顺序断言“拒稿发生在录用之前”。样例保留真实 `decision_date`、`observed_at`、原始标签、证据 URL 和决定来源，供进一步核查；日期缺失仍保持未知。`negative` 统计包含 rejected、desk_rejected 和 withdrawn，其原始状态不互相替换。
+
+总数覆盖快照内全部投稿，样例由 `--examples` 限定为 0–100 篇；每篇最多展示 20 次投稿、每次最多 50 条决定、每条决定最多 100 个来源，并明确标记截断。样例优先保留负面/录用的不同投稿对。四项来源关系检查报告缺失关联和来源论文归属不一致，不自动修复。
+
+这些统计依赖现有论文身份关联，不证明实体合并正确，也不证明原始决定签名、公开拒稿全集、标签类型或最终全库去重已完成。SQLite 独立样本可使用 `--db`；冻结备份不能代表当前 PostgreSQL 的历史情况。

paper_atlas/audits/histories.py

@@ -0,0 +1,196 @@
+"""Audit linked submission histories without inferring event chronology."""
+import argparse
+from collections import Counter
+import json
+from pathlib import Path
+import sqlite3
+
+from paper_atlas.db.backend import database_arguments, open_read_connection
+from paper_atlas.db.submissions import timestamp
+from paper_atlas.querying import LATEST_DECISION
+
+
+ATTEMPTS = '''SELECT s.paper_id,s.id AS submission_id,e.venue_id,v.acronym AS venue,e.year,e.track,
+    count(d.id) AS decision_observations,
+    MAX(CASE WHEN d.status IN ('rejected','desk_rejected','withdrawn') THEN 1 ELSE 0 END)
+        AS historical_negative,
+    MAX(CASE WHEN d.status='accepted' THEN 1 ELSE 0 END) AS historical_acceptance,
+    COALESCE(MAX(CASE WHEN ''' + LATEST_DECISION + ''' THEN d.status END),'unknown')
+        AS latest_observed_status
+    FROM submissions s JOIN editions e ON e.id=s.edition_id JOIN venues v ON v.id=e.venue_id
+    LEFT JOIN decisions d ON d.submission_id=s.id
+    GROUP BY s.paper_id,s.id,e.venue_id,v.acronym,e.year,e.track
+    ORDER BY s.paper_id,e.venue_id,s.id'''
+
+
+def _paper_counts(attempts):
+    negative = sum(row['historical_negative'] for row in attempts)
+    accepted = sum(row['latest_observed_status'] == 'accepted' for row in attempts)
+    overlap = sum(row['historical_negative'] and row['latest_observed_status'] == 'accepted'
+                  for row in attempts)
+    venues = {}
+    for row in attempts:
+        counts = venues.setdefault(row['venue_id'], [0, 0])
+        counts[0] += row['historical_negative']
+        counts[1] += row['latest_observed_status'] == 'accepted'
+    return {
+        'papers_with_submissions': 1,
+        'papers_with_multiple_submissions': int(len(attempts) > 1),
+        'papers_with_historical_negative': int(negative > 0),
+        'papers_with_current_known_acceptance': int(accepted > 0),
+        'papers_with_negative_and_acceptance_in_distinct_attempts': int(negative * accepted > overlap),
+        'papers_with_negative_and_acceptance_in_distinct_venues':
+            int(negative * accepted > sum(n * a for n, a in venues.values())),
+    }
+
+
+def _example(connection, attempts):
+    # Keep a negative/accepted pair visible even when a paper has many attempts.
+    accepted = [row for row in attempts if row['latest_observed_status'] == 'accepted']
+    first = accepted[0] if accepted else None
+    other_venue = next((row for row in accepted if row['venue_id'] != first['venue_id']), None)
+    pair = None
+    for negative in attempts:
+        if negative['historical_negative'] and first:
+            candidate = first if first['venue_id'] != negative['venue_id'] else other_venue
+            if candidate:
+                pair = (negative, candidate)
+                break
+    if pair is None:
+        for negative in attempts:
+            if negative['historical_negative'] and first:
+                candidate = first if first['submission_id'] != negative['submission_id'] else (
+                    accepted[1] if len(accepted) > 1 else None)
+                if candidate:
+                    pair = (negative, candidate)
+                    break
+    selected = {}
+    for row in list(pair or ()) + attempts:
+        if len(selected) < 20:
+            selected.setdefault(row['submission_id'], dict(row))
+    for row in selected.values():
+        row['decisions'] = []
+        for decision in connection.execute('''SELECT id,status,raw_value,evidence_url,
+                decision_date,observed_at FROM decisions WHERE submission_id=?
+                ORDER BY observed_at DESC,COALESCE(decision_date,observed_at) DESC,id DESC LIMIT 50''',
+                (row['submission_id'],)):
+            entry = dict(decision)
+            sources = [dict(source) for source in connection.execute('''
+                SELECT so.name,r.external_id,ds.source_decision_id FROM decision_sources ds
+                JOIN source_records r ON r.id=ds.source_record_id JOIN sources so ON so.id=r.source_id
+                WHERE ds.decision_id=? ORDER BY so.name,r.external_id LIMIT 101''', (entry['id'],))]
+            entry['sources'] = sources[:100]
+            entry['sources_truncated'] = len(sources) > 100
+            row['decisions'].append(entry)
+        row['decisions_truncated'] = row['decision_observations'] > len(row['decisions'])
+    paper_id = attempts[0]['paper_id']
+    return {'paper_id': paper_id,
+            'title': connection.execute('SELECT title FROM papers WHERE id=?', (paper_id,)).fetchone()[0],
+            'counts': _paper_counts(attempts), 'attempt_count': len(attempts),
+            'attempts': list(selected.values()), 'attempts_truncated': len(attempts) > len(selected),
+            'chronology': 'Not inferred from observed_at, edition year, or row order.'}
+
+
+def report(db=None, *, pg_service=None, pg_schema=None, examples=20):
+    if not 0 <= examples <= 100:
+        raise ValueError('Examples must be between 0 and 100')
+    started_at = timestamp()
+    connection = open_read_connection(db, pg_service=pg_service, pg_schema=pg_schema)
+    if not pg_service:
+        connection.row_factory = sqlite3.Row
+    try:
+        if pg_service:
+            identity = connection.execute('SELECT current_database(),current_schema()').fetchone()
+            database, schema = identity[0], identity[1]
+        else:
+            database, schema = str(Path(db).resolve()), None
+        names = ['papers_with_submissions', 'papers_with_multiple_submissions',
+                 'papers_with_historical_negative', 'papers_with_current_known_acceptance',
+                 'papers_with_negative_and_acceptance_in_distinct_attempts',
+                 'papers_with_negative_and_acceptance_in_distinct_venues']
+        totals = Counter({key: 0 for key in names})
+        totals.update(submissions=0, decision_observations=0,
+                      attempts_with_historical_negative=0,
+                      attempts_with_historical_negative_and_acceptance=0)
+        latest = Counter()
+        sample_attempts = []
+
+        def consume(rows):
+            if not rows:
+                return
+            counts = _paper_counts(rows)
+            totals.update(counts)
+            if counts['papers_with_negative_and_acceptance_in_distinct_attempts'] and len(sample_attempts) < examples:
+                sample_attempts.append(rows)
+
+        current = []
+        for raw in connection.execute(ATTEMPTS):
+            row = dict(raw)
+            if current and row['paper_id'] != current[0]['paper_id']:
+                consume(current)
+                current = []
+            current.append(row)
+            totals['submissions'] += 1
+            totals['decision_observations'] += row['decision_observations']
+            totals['attempts_with_historical_negative'] += row['historical_negative']
+            totals['attempts_with_historical_negative_and_acceptance'] += int(
+                row['historical_negative'] and row['historical_acceptance'])
+            latest[row['latest_observed_status']] += 1
+        consume(current)
+        # These are relationship checks, not a substitute for the final entity/FK audit.
+        integrity = {}
+        checks = {
+            'submissions_without_source_links': '''SELECT count(*) FROM submissions s
+                WHERE NOT EXISTS(SELECT 1 FROM submission_sources ss WHERE ss.submission_id=s.id)''',
+            'decisions_without_source_links': '''SELECT count(*) FROM decisions d
+                WHERE NOT EXISTS(SELECT 1 FROM decision_sources ds WHERE ds.decision_id=d.id)''',
+            'submission_source_paper_mismatches': '''SELECT count(*) FROM submission_sources ss
+                JOIN submissions s ON s.id=ss.submission_id JOIN source_records r ON r.id=ss.source_record_id
+                WHERE s.paper_id<>r.paper_id''',
+            'decision_source_paper_mismatches': '''SELECT count(*) FROM decision_sources ds
+                JOIN decisions d ON d.id=ds.decision_id JOIN submissions s ON s.id=d.submission_id
+                JOIN source_records r ON r.id=ds.source_record_id WHERE s.paper_id<>r.paper_id''',
+        }
+        for name, query in checks.items():
+            integrity[name] = connection.execute(query).fetchone()[0]
+        return {'report_started_at': started_at, 'checked_at': timestamp(),
+                'engine': 'postgresql' if pg_service else 'sqlite', 'database': database,
+                'schema': schema, 'pg_service': pg_service,
+                'status': 'observed_history_audit_not_final_dedup', 'counts': dict(totals),
+                'latest_attempt_status_counts': dict(sorted(latest.items())),
+                'evidence_relationship_checks': integrity,
+                'examples': [_example(connection, rows) for rows in sample_attempts],
+                'example_limit': examples,
+                'interpretation': [
+                    'Counts use existing canonical paper links, not independently verified real-world identity.',
+                    'Negative includes rejected, desk_rejected and withdrawn observations; these remain distinct decisions.',
+                    'Known acceptance follows the latest observed decision per attempt, matching query --outcome.',
+                    'Distinct attempts/venues require separate submission/venue IDs; aliases do not create new venues.',
+                    'Coexisting evidence does not prove rejection happened before acceptance. observed_at is collection time.',
+                    'No known acceptance is not proof of never accepted. Source signatures and completeness are not established here.',
+                    'Examples are bounded; counts include all attempts and observations in one read-only snapshot.',
+                    'This does not perform entity merging, final deduplication, or label namespace/type validation.',
+                ]}
+    finally:
+        connection.close()
+
+
+def main(argv=None, *, prog=None):
+    parser = argparse.ArgumentParser(prog=prog)
+    database_arguments(parser)
+    parser.add_argument('--examples', type=int, default=20)
+    parser.add_argument('--out')
+    args = parser.parse_args(argv)
+    result = report(args.db, pg_service=args.pg_service, pg_schema=args.pg_schema, examples=args.examples)
+    text = json.dumps(result, ensure_ascii=False, indent=2)
+    if args.out:
+        path = Path(args.out)
+        stage = path.with_suffix('.part')
+        stage.write_text(text + '\n')
+        stage.replace(path)
+    else:
+        print(text)
+
+
+if __name__ == '__main__':
+    main()

paper_atlas/audits/public_openreview.py

@@ -39,7 +39,9 @@ def audit(db, inventory, out, *, pg_service=None, pg_schema=None):
             if json.loads(path.with_suffix('.manifest.json').read_text()) != manifest:
                 raise ValueError('Collected manifest differs from inventory')
             count = 0
-            for line in path.read_text().splitlines():
+            # Unicode paragraph/line separators are valid inside JSON strings;
+            # split physical byte lines, not Unicode text boundaries.
+            for line in path.read_bytes().splitlines():
                 row = json.loads(line)
                 if any(row[key] != manifest[key] for key in ('source', 'venue', 'year', 'track')):
                     raise ValueError('Record edition differs from inventory')

paper_atlas/cli.py

@@ -25,6 +25,7 @@ COMMANDS = {
     ('catalogue','dblp'): ('paper_atlas.collectors.dblp', {}, '盘点 DBLP 历史会议目录'),
     ('import','arxiv'): ('paper_atlas.ingestion.arxiv', {}, '导入 arXiv 元数据 ZIP'),
     ('import','records'): ('paper_atlas.ingestion.records', {}, '导入核验过的会议文件'),
+    ('maintain','joint-editions'): ('paper_atlas.ingestion.joint_editions', {}, '按已核验计划修正既有联合会议届次归属'),
     ('maintain','merge'): ('paper_atlas.ingestion.maintenance', {}, '协调单写入合并与恢复'),
     ('maintain','backfill'): ('paper_atlas.ingestion.backfill', {}, '回填既有投稿的来源身份'),
     ('maintain','arxiv-tags'): ('paper_atlas.ingestion.arxiv_tags', {}, '恢复逐来源记录的 arXiv 类别证据'),
@@ -35,6 +36,7 @@ COMMANDS = {
     ('audit','arxiv'): ('paper_atlas.audits.arxiv', {}, '核验 arXiv 原始编号、重复行与 ZIP 完整性'),
     ('audit','arxiv-tags'): ('paper_atlas.audits.arxiv_tags', {}, '逐记录核验 arXiv 类别及出处完整性'),
     ('audit','public-openreview'): ('paper_atlas.audits.public_openreview', {}, '核对公开负面决定与已有投稿历史'),
+    ('audit','histories'): ('paper_atlas.audits.histories', {}, '只读核对跨会议投稿历史及决定来源关系'),
 }
 
 

paper_atlas/collectors/dblp_records.py

@@ -88,6 +88,8 @@ def normalize_row(row,volumes,targets,include_workshops=False,through_year=2026)
               'scope_rule':edition['rule'],'author_names_raw':fields.get('author',[]),'publtype':row.get('publtype'),
               'bibliography':{key:value for key,value in fields.items() if key in ('booktitle','year','ee','url','pages','volume','number','publisher','series','isbn')},
               'ambiguous_identifiers':ambiguous,'publication_evidence':'inproceedings bibliography; not an original decision note'}
+    if edition.get('joint_edition_evidence'):
+        metadata['joint_edition_evidence'] = edition['joint_edition_evidence']
     if edition.get('track_scope_note'):
         metadata['track_scope_note']=edition['track_scope_note']
     flagged=bool(re.search(r'\b(?:withdrawn|retracted)\b',row.get('publtype') or '',re.I))

paper_atlas/collectors/dblp_scope.py

@@ -96,8 +96,15 @@ def scope(row,volume,through_year=2026):
     elif suffix.casefold() in ('poster','posters') and venue not in ('ICLR','ACL','EMNLP','NAACL','EACL','COLING','CoNLL'):track='poster'
     if venue=='AAAI+IAAI':track='proceedings_unspecified'
     if venue=='AAMAS' and year<2002:return None,'predecessor_not_aamas'
+    joint_evidence = None
+    if (family == 'ijcai' and base == 'IJCAI' and track == 'main'
+            and year in (2018, 2022) and volume['key'] == 'conf/ijcai/' + str(year)):
+        venue, aliases = 'ECAI+IJCAI', ['ECAI', 'IJCAI']
+        joint_evidence = 'https://www.eurai.org/ecai/history'
     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 joint_evidence:
+        result['joint_edition_evidence'] = joint_evidence
     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

@@ -144,6 +144,20 @@ class Store:
 
     def decision(self,paper,record,venue,year,track,external_id,url,status,raw_value,aliases=None,identities=None,observed_at=None,decision_date=None,source_decision_id='',submitted_at=None,guard_status=False):
         c = self.conn
+        # An already collected file may still call these exact pinned volumes
+        # IJCAI. Resolve membership before finding/creating an edition so a
+        # later refresh cannot split the repaired joint event again.
+        if venue == 'IJCAI' and year in (2018,2022) and track == 'main':
+            from paper_atlas.collectors.dblp import XML_SHA
+            evidence=c.execute('SELECT src.name,r.metadata_json FROM source_records r JOIN sources src ON src.id=r.source_id WHERE r.id=?',(record,)).fetchone()
+            if evidence and evidence[0] == 'dblp':
+                metadata=json.loads(evidence[1])
+                if (metadata.get('snapshot_sha256') == XML_SHA
+                        and metadata.get('proceedings_key') == 'conf/ijcai/'+str(year)
+                        and metadata.get('bibliographic_year') == year
+                        and (metadata.get('bibliography') or {}).get('booktitle') in (['IJCAI'],['IJCAI/ECAI'])):
+                    venue='ECAI+IJCAI'
+                    aliases=sorted(set(aliases or []) | {'ECAI','IJCAI'})
         existing=c.execute('SELECT id FROM venues WHERE lower(acronym)=lower(?)',(venue,)).fetchone()
         if existing:venue_id=existing[0]
         else:venue_id=inserted_id(c,"INSERT INTO venues(acronym,name,field,venue_type) VALUES(?,?,?,'conference')",(venue,venue,'unclassified'))

paper_atlas/ingestion/joint_editions.py

@@ -0,0 +1,204 @@
+"""Evidence-bound repair of two existing IJCAI/ECAI edition memberships."""
+import argparse
+from contextlib import closing
+import hashlib
+import json
+from pathlib import Path
+
+from paper_atlas.db.backend import database_arguments, open_read_connection, open_store
+from paper_atlas.db.submissions import timestamp
+from paper_atlas.collectors.dblp import XML_SHA
+
+YEARS = (2018, 2022)
+TARGET = 'ECAI+IJCAI'
+MEMBERS = {'ECAI', 'IJCAI'}
+EVIDENCE = 'https://www.eurai.org/ecai/history'
+MARKER = 'joint_ijcai_ecai_2018_2022_v1'
+
+
+def _digest(c, sql, params=()):
+    sha = hashlib.sha256(); count = 0
+    for row in c.execute(sql, params):
+        sha.update((json.dumps([row[i] for i in range(len(row))], ensure_ascii=False,
+                              separators=(',', ':')) + '\n').encode())
+        count += 1
+        if count > 100000:
+            raise ValueError('Joint repair evidence scope exceeded bounded row limit')
+    return {'rows': count, 'sha256': sha.hexdigest()}
+
+
+def fingerprints(c, ids):
+    marks = ','.join('?' for _ in ids)
+    submissions = 'SELECT id FROM submissions WHERE edition_id IN (' + marks + ')'
+    papers = 'SELECT paper_id FROM submissions WHERE edition_id IN (' + marks + ')'
+    decisions = 'SELECT id FROM decisions WHERE submission_id IN (' + submissions + ')'
+    checks = {
+        'papers': ('id IN (' + papers + ')', 'id'),
+        'identifiers': ('paper_id IN (' + papers + ')', 'scheme,value'),
+        'source_records': ('paper_id IN (' + papers + ')', 'id'),
+        'paper_tags': ('paper_id IN (' + papers + ')', 'paper_id,tag_id,evidence_key'),
+        'submissions': ('edition_id IN (' + marks + ')', 'id'),
+        'decisions': ('submission_id IN (' + submissions + ')', 'id'),
+        'submission_sources': ('submission_id IN (' + submissions + ')', 'submission_id,source_record_id,source_submission_id'),
+        'submission_identifiers': ('edition_id IN (' + marks + ')', 'edition_id,scheme,value'),
+        'decision_sources': ('decision_id IN (' + decisions + ')', 'decision_id,source_record_id,source_decision_id'),
+        'edition_sources': ('edition_id IN (' + marks + ')', 'edition_id,source_id,list_url'),
+    }
+    return {table: _digest(c, 'SELECT * FROM ' + table + ' WHERE ' + where + ' ORDER BY ' + order, ids)
+            for table, (where, order) in checks.items()}
+
+
+def inspect(c):
+    target = c.execute('SELECT id FROM venues WHERE acronym=?', (TARGET,)).fetchall()
+    if len(target) != 1:
+        raise ValueError('Exactly one existing canonical joint venue required')
+    target = target[0][0]
+    aliases = {r[0] for r in c.execute('SELECT alias FROM venue_aliases WHERE venue_id=?', (target,))}
+    if aliases != MEMBERS:
+        raise ValueError('Joint target must already have exactly ECAI and IJCAI aliases')
+    editions = []
+    for year in YEARS:
+        rows = c.execute('''SELECT e.id,e.venue_id,v.acronym FROM editions e JOIN venues v ON v.id=e.venue_id
+            WHERE v.acronym IN ('IJCAI','ECAI+IJCAI') AND e.year=? AND e.track='main' ''', (year,)).fetchall()
+        if len(rows) != 1:
+            raise ValueError('Expected one existing edition per year; missing or colliding editions require separate review')
+        edition, venue, acronym = (rows[0][i] for i in range(3))
+        count = c.execute('SELECT count(*) FROM submissions WHERE edition_id=?', (edition,)).fetchone()[0]
+        if not 0 < count <= 5000:
+            raise ValueError('Existing edition must have a nonempty bounded submission scope')
+        # Every existing submission must be supported by its own pinned DBLP
+        # volume record. No title/author matching, new attempts or text writes.
+        evidence = c.execute('''SELECT s.id,r.external_id,r.metadata_json FROM submissions s
+            JOIN submission_sources ss ON ss.submission_id=s.id
+            JOIN source_records r ON r.id=ss.source_record_id JOIN sources src ON src.id=r.source_id
+            WHERE s.edition_id=? AND src.name='dblp' ORDER BY s.id,r.id''', (edition,)).fetchall()
+        seen = set()
+        for row in evidence:
+            sid, external, metadata = (row[i] for i in range(3))
+            meta = json.loads(metadata)
+            bibliography = meta.get('bibliography') or {}
+            if (meta.get('snapshot_sha256') != XML_SHA
+                    or meta.get('proceedings_key') != 'conf/ijcai/' + str(year)
+                    or meta.get('bibliographic_year') != year
+                    or bibliography.get('booktitle') not in (['IJCAI'], ['IJCAI/ECAI'])
+                    or not external.startswith('conf/ijcai/')):
+                raise ValueError('Source evidence outside the exact verified IJCAI/ECAI volume')
+            seen.add(sid)
+        if len(seen) != count:
+            raise ValueError('Every submission must have matching original volume evidence')
+        editions.append({'id': edition, 'year': year, 'track': 'main', 'from_venue_id': venue,
+                         'from_venue': acronym, 'target_venue_id': target, 'submissions': count,
+                         'evidence_url': EVIDENCE, 'proceedings_key': 'conf/ijcai/' + str(year)})
+    ids = tuple(e['id'] for e in editions)
+    return {'format_version': 1, 'kind': MARKER, 'checked_at': timestamp(), 'editions': editions,
+            'content_fingerprints': fingerprints(c, ids), 'target_aliases': sorted(aliases),
+            'status': 'already_joint' if all(e['from_venue_id'] == target for e in editions) else 'ready',
+            'scope': 'Only these two existing edition venue references; no source text, paper, submission, decision, track, identifier or tag change.'}
+
+
+def validate_plan(expected):
+    if not isinstance(expected, dict):
+        raise ValueError('Repair plan must be a JSON object')
+    if set(expected) != {'format_version','kind','checked_at','editions','content_fingerprints','target_aliases','status','scope','database'}:
+        raise ValueError('Unexpected repair plan fields')
+    if (type(expected['format_version']) is not int or expected['format_version'] != 1
+            or expected['kind'] != MARKER or expected['status'] not in ('ready','already_joint')):
+        raise ValueError('Unsupported repair plan')
+    if (not isinstance(expected['database'],dict) or not isinstance(expected['content_fingerprints'],dict)
+            or not isinstance(expected['editions'],list) or len(expected['editions']) != 2
+            or expected['target_aliases'] != sorted(MEMBERS)):
+        raise ValueError('Invalid repair plan structure')
+    for edition, year in zip(expected['editions'], YEARS):
+        if not isinstance(edition,dict) or edition.get('year') != year:
+            raise ValueError('Repair plan must name the two exact ordered years')
+        for key in ('id','year','from_venue_id','target_venue_id','submissions'):
+            if type(edition.get(key)) is not int or edition[key] <= 0:
+                raise ValueError('Repair plan IDs/counts must be positive integers')
+
+
+def apply_plan(c, expected):
+    validate_plan(expected)
+    actual = inspect(c)
+    if actual['content_fingerprints'] != expected['content_fingerprints'] or actual['target_aliases'] != expected['target_aliases']:
+        raise ValueError('Stale repair plan: protected content or aliases changed')
+    if len(expected['editions']) != 2:
+        raise ValueError('Exactly two editions required')
+    for old, now in zip(expected['editions'], actual['editions']):
+        if set(old) != set(now):
+            raise ValueError('Unexpected edition fields')
+        for key in ('id','year','track','target_venue_id','submissions','evidence_url','proceedings_key'):
+            if old[key] != now[key]:
+                raise ValueError('Stale repair plan: edition differs')
+        if now['from_venue_id'] != old['from_venue_id'] and now['from_venue_id'] != now['target_venue_id']:
+            raise ValueError('Edition membership differs from plan')
+    if actual['status'] == 'already_joint':
+        return {**actual, 'status':'already_joint', 'updated_editions':0}
+    for edition in actual['editions']:
+        if edition['from_venue_id'] == edition['target_venue_id']:
+            continue
+        changed = c.execute('''UPDATE editions SET venue_id=? WHERE id=? AND venue_id=? AND year=? AND track=?''',
+                            (edition['target_venue_id'],edition['id'],edition['from_venue_id'],edition['year'],edition['track']))
+        if changed.rowcount != 1:
+            raise ValueError('Concurrent edition change; entire repair must roll back')
+    after = inspect(c)
+    if after['status'] != 'already_joint' or after['content_fingerprints'] != actual['content_fingerprints']:
+        raise ValueError('Postcheck changed protected content; entire repair must roll back')
+    c.execute('INSERT INTO schema_migrations(name) VALUES(?) ON CONFLICT DO NOTHING', (MARKER,))
+    return {**after, 'status':'applied', 'updated_editions':sum(e['from_venue_id'] != e['target_venue_id'] for e in actual['editions'])}
+
+
+def database_identity(c, db):
+    if getattr(c, 'postgres', False):
+        row = c.execute('SELECT current_database(),current_schema()').fetchone()
+        return {'engine':'postgresql','database':row[0],'schema':row[1]}
+    return {'engine':'sqlite','path':str(Path(db).resolve())}
+
+
+def run(db, out, *, pg_service=None, pg_schema=None, plan=None, plan_sha256=None):
+    out = Path(out).resolve()
+    if not out.parent.is_dir():
+        raise ValueError('Report parent directory must already exist')
+    if out.exists():
+        raise ValueError('Preserve existing evidence report; choose a new output path')
+    expected = None
+    if plan:
+        raw = Path(plan).read_bytes()
+        if hashlib.sha256(raw).hexdigest() != plan_sha256:
+            raise ValueError('Repair plan hash differs before opening database')
+        expected = json.loads(raw)
+        validate_plan(expected)
+    elif plan_sha256:
+        raise ValueError('Plan hash requires an existing plan')
+    if db and out == Path(db).resolve():
+        raise ValueError('Report must not overwrite database')
+    writer = open_store(db, pg_service=pg_service, pg_schema=pg_schema) if expected is not None else None
+    c = writer.conn if writer else open_read_connection(db, pg_service=pg_service, pg_schema=pg_schema)
+    with closing(c):
+        try:
+            if expected is not None and not getattr(c, 'postgres', False):
+                c.commit(); c.execute('BEGIN IMMEDIATE')
+            identity = database_identity(c, db)
+            if expected is not None and expected['database'] != identity:
+                raise ValueError('Plan belongs to another database/schema')
+            report = apply_plan(c, expected) if expected is not None else inspect(c)
+            report['database'] = identity
+            if expected is not None:
+                report['plan_sha256'] = plan_sha256
+            if expected is not None:
+                c.commit()
+        except BaseException:
+            if expected is not None: c.rollback()
+            raise
+    out.write_text(json.dumps(report,ensure_ascii=False,indent=2)+'\n')
+    print(json.dumps({'status':report['status'],'editions':len(report['editions']),
+                      'updated_editions':report.get('updated_editions',0),'report':str(out)}))
+    return report
+
+
+def main(argv=None, *, prog=None):
+    parser = argparse.ArgumentParser(prog=prog); database_arguments(parser)
+    parser.add_argument('--out', required=True)
+    parser.add_argument('--plan', help='Apply an already reviewed plan; omitted means read-only preflight')
+    parser.add_argument('--plan-sha256', help='Required exact plan SHA256 when applying')
+    args = parser.parse_args(argv)
+    run(args.db,args.out,pg_service=args.pg_service,pg_schema=args.pg_schema,plan=args.plan,plan_sha256=args.plan_sha256)

tests/test_histories.py

@@ -0,0 +1,114 @@
+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)

tests/test_joint_editions.py

@@ -0,0 +1,187 @@
+from contextlib import closing, redirect_stdout
+import hashlib
+import io
+import json
+import os
+from pathlib import Path
+import tempfile
+import unittest
+from unittest.mock import patch
+import uuid
+
+from paper_atlas.collectors.dblp import XML_SHA
+from paper_atlas.collectors.dblp_scope import scope
+from paper_atlas.collectors.dblp_records import normalize_row
+from paper_atlas.db.store import Store
+from paper_atlas.db.backend import open_store
+from paper_atlas.ingestion.joint_editions import (TARGET, MARKER, inspect, apply_plan, run)
+from paper_atlas.postgres.client import connect
+from paper_atlas.postgres.migration import migrate
+from paper_atlas.postgres.schema import quote
+from paper_atlas import querying
+
+
+def seed(store):
+    c = store.conn
+    c.execute("INSERT INTO venues(acronym,name,field,venue_type) VALUES(?,?,'reasoning','conference')", (TARGET,TARGET))
+    target = c.execute('SELECT id FROM venues WHERE acronym=?',(TARGET,)).fetchone()[0]
+    for alias in ['ECAI','IJCAI']:
+        c.execute('INSERT INTO venue_aliases VALUES(?,?)',(target,alias))
+    for year in [2018,2019,2022]:
+        metadata = {'snapshot_sha256':XML_SHA,'proceedings_key':'conf/ijcai/'+str(year),
+                    'bibliographic_year':year,'bibliography':{'booktitle':['IJCAI']}}
+        p,r=store.record('dblp','conf/ijcai/fixture'+str(year),'https://dblp.org/rec/fixture',
+                         'Original publication '+str(year),'Abstract\x00with\x01data',[],
+                         {'doi':'10.24963/ijcai.'+str(year)+'/1'}, {})
+        store.record_tags(p,r,'dblp',[{'namespace':'dblp:booktitle','value':'IJCAI'}])
+        store.decision(p,r,'IJCAI',year,'main','fixture'+str(year),'https://example.org/decision','accepted','listed')
+        stored=json.loads(c.execute('SELECT metadata_json FROM source_records WHERE id=?',(r,)).fetchone()[0]);stored.update(metadata)
+        c.execute('UPDATE source_records SET metadata_json=? WHERE id=?',(json.dumps(stored),r))
+    c.commit()
+
+
+def plan(c):
+    return {**inspect(c),'database':{'engine':'sqlite','path':'fixture'}}
+
+
+class JointEditionTests(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)
+        seed(self.store); self.c=self.store.conn
+
+    def test_apply_preserves_every_protected_row_and_edition_id(self):
+        before=plan(self.c); ids=[r['id']for r in before['editions']]
+        result=apply_plan(self.c,before);self.c.commit()
+        self.assertEqual(result['updated_editions'],2)
+        self.assertEqual(result['content_fingerprints'],before['content_fingerprints'])
+        self.assertEqual([r['id']for r in result['editions']],ids)
+        untouched=self.c.execute('SELECT v.acronym FROM editions e JOIN venues v ON v.id=e.venue_id WHERE e.year=2019').fetchone()[0]
+        self.assertEqual(untouched,'IJCAI')
+        self.assertEqual(self.c.execute('PRAGMA foreign_key_check').fetchall(),[])
+        self.assertEqual(self.c.execute('SELECT count(*) FROM schema_migrations WHERE name=?',(MARKER,)).fetchone()[0],1)
+        with redirect_stdout(io.StringIO())as out:
+            querying.main(['--db',str(self.db),'--venue','ECAI'])
+        self.assertEqual(len(json.loads(out.getvalue())),2)
+        self.assertEqual(apply_plan(self.c,before)['updated_editions'],0)
+
+    def test_refresh_of_old_normalized_source_does_not_recreate_ordinary_edition(self):
+        before=plan(self.c);apply_plan(self.c,before)
+        for year in [2018,2022]:
+            row=self.c.execute('''SELECT r.paper_id,r.id,d.observed_at FROM source_records r
+                JOIN submissions s ON s.source_record_id=r.id JOIN decisions d ON d.submission_id=s.id
+                WHERE r.external_id=?''',('conf/ijcai/fixture'+str(year),)).fetchone()
+            self.store.decision(row[0],row[1],'IJCAI',year,'main','fixture'+str(year),
+                                'https://example.org/decision','accepted','listed',observed_at=row[2])
+        self.assertEqual(inspect(self.c)['content_fingerprints'],before['content_fingerprints'])
+        self.assertEqual(self.c.execute('SELECT count(*) FROM editions').fetchone()[0],3)
+
+    def test_any_changed_source_text_rejects_stale_plan_before_membership_updates(self):
+        before=plan(self.c)
+        self.c.execute("UPDATE source_records SET title='New evidence' WHERE external_id='conf/ijcai/fixture2018'")
+        with self.assertRaisesRegex(ValueError,'Stale repair plan'):
+            apply_plan(self.c,before)
+        self.assertEqual(inspect(self.c)['status'],'ready')
+
+    def test_conflicting_target_edition_is_never_merged_or_deleted(self):
+        target=self.c.execute('SELECT id FROM venues WHERE acronym=?',(TARGET,)).fetchone()[0]
+        self.c.execute("INSERT INTO editions(venue_id,year,track) VALUES(?,2018,'main')",(target,))
+        with self.assertRaisesRegex(ValueError,'colliding'):
+            inspect(self.c)
+        self.assertEqual(self.c.execute('SELECT count(*) FROM editions WHERE year=2018').fetchone()[0],2)
+
+    def test_wrong_source_volume_and_snapshot_fail_closed(self):
+        original=self.c.execute("SELECT metadata_json FROM source_records WHERE external_id='conf/ijcai/fixture2018'").fetchone()[0]
+        for key,value in [('proceedings_key','conf/ijcai/2018w'),('snapshot_sha256','wrong'),('bibliographic_year',2017),('bibliography',{'booktitle':['Other']})]:
+            m=json.loads(original);m[key]=value
+            self.c.execute("UPDATE source_records SET metadata_json=? WHERE external_id='conf/ijcai/fixture2018'",(json.dumps(m),))
+            with self.subTest(key=key),self.assertRaisesRegex(ValueError,'Source evidence'):
+                inspect(self.c)
+
+    def test_missing_source_support_and_wrong_aliases_are_not_guessed(self):
+        self.c.execute("DELETE FROM venue_aliases WHERE alias='ECAI'")
+        with self.assertRaisesRegex(ValueError,'aliases'):
+            inspect(self.c)
+        self.c.rollback()
+        self.c.execute('DELETE FROM submission_sources WHERE source_record_id=(SELECT id FROM source_records WHERE external_id=?)',('conf/ijcai/fixture2022',))
+        with self.assertRaisesRegex(ValueError,'Every submission'):
+            inspect(self.c)
+
+    def test_cli_plan_readonly_hash_binding_identity_and_repeat_apply(self):
+        out=Path(self.tmp.name)/'plan.json'
+        with redirect_stdout(io.StringIO()):run(self.db,out)
+        self.assertEqual(inspect(self.c)['status'],'ready')
+        raw=out.read_bytes();sha=hashlib.sha256(raw).hexdigest()
+        with patch('paper_atlas.ingestion.joint_editions.open_store')as writer:
+            with self.assertRaisesRegex(ValueError,'hash differs'):
+                run(self.db,Path(self.tmp.name)/'bad.json',plan=out,plan_sha256='0'*64)
+            writer.assert_not_called()
+        with redirect_stdout(io.StringIO()):
+            result=run(self.db,Path(self.tmp.name)/'applied.json',plan=out,plan_sha256=sha)
+            again=run(self.db,Path(self.tmp.name)/'retry.json',plan=out,plan_sha256=sha)
+        self.assertEqual(result['updated_editions'],2);self.assertEqual(again['updated_editions'],0)
+        self.assertEqual(result['plan_sha256'],sha);self.assertEqual(again['plan_sha256'],sha)
+        altered=json.loads(raw);altered['database']['path']='another.sqlite'
+        bad=Path(self.tmp.name)/'wrong-db.json';bad.write_text(json.dumps(altered))
+        with self.assertRaisesRegex(ValueError,'another database'):
+            run(self.db,Path(self.tmp.name)/'wrong-result.json',plan=bad,plan_sha256=hashlib.sha256(bad.read_bytes()).hexdigest())
+
+    def test_invalid_empty_plan_fails_before_opening_writer(self):
+        f=Path(self.tmp.name)/'empty.json';f.write_text('{}')
+        with patch('paper_atlas.ingestion.joint_editions.open_store')as writer:
+            with self.assertRaises(ValueError):
+                run(self.db,Path(self.tmp.name)/'empty-result.json',plan=f,plan_sha256=hashlib.sha256(f.read_bytes()).hexdigest())
+            writer.assert_not_called()
+
+    def test_collector_only_changes_the_two_exact_main_volume_keys(self):
+        for year in [2018,2019,2022]:
+            volume={'key':'conf/ijcai/'+str(year),'fields':{'title':['IJCAI '+str(year)],'year':[str(year)]}}
+            row={'record_type':'inproceedings','key':'conf/ijcai/One'+str(year),'fields':{'booktitle':['IJCAI'],
+                 'year':[str(year)],'crossref':[volume['key']],'title':['Original research title'],
+                 'author':['Jane Doe'],'ee':['https://doi.org/10.24963/ijcai.'+str(year)+'/1']}}
+            result,error=normalize_row(row,{volume['key']:volume},{'IJCAI','ECAI'})
+            self.assertIsNone(error)
+            self.assertEqual(result['venue'],TARGET if year in(2018,2022)else'IJCAI')
+            self.assertEqual(result['metadata']['bibliography']['booktitle'],['IJCAI'])
+            self.assertEqual(result['title'],'Original research title')
+            if year in(2018,2022):
+                self.assertIn('joint_edition_evidence',result['metadata'])
+                row['fields']['booktitle']=['IJCAI (Workshop)']
+                scoped,_=scope(row,volume)
+                self.assertEqual(scoped['venue'],'IJCAI')
+                self.assertEqual(scoped['track'],'workshop')
+
+
+@unittest.skipUnless(os.environ.get('PAPER_ATLAS_TEST_PG_SERVICE'),'Requires approved remote PostgreSQL service')
+class PostgreSQLJointTests(unittest.TestCase):
+    def setUp(self):
+        self.service=os.environ['PAPER_ATLAS_TEST_PG_SERVICE'];self.target='pa_joint_'+uuid.uuid4().hex[:12]
+        self.tmp=tempfile.TemporaryDirectory();self.addCleanup(self.tmp.cleanup)
+        self.db=Path(self.tmp.name)/'sample.sqlite';s=Store(self.db);seed(s);s.conn.close()
+        self.addCleanup(self.cleanup)
+        with redirect_stdout(io.StringIO()):migrate(self.db,self.service,Path(self.tmp.name)/'migration.json',schema=self.target,min_free_gib=0)
+
+    def cleanup(self):
+        with connect(self.service)as c:
+            for name, in c.execute('SELECT nspname FROM pg_namespace WHERE starts_with(nspname,%s)',(self.target,)).fetchall():
+                c.execute('DROP SCHEMA '+quote(name)+' CASCADE')
+
+    def test_native_repair_is_idempotent_keeps_codec_and_provenance(self):
+        p=Path(self.tmp.name)/'plan.json'
+        with redirect_stdout(io.StringIO()):
+            before=run(None,p,pg_service=self.service,pg_schema=self.target)
+            after=run(None,Path(self.tmp.name)/'applied.json',pg_service=self.service,pg_schema=self.target,plan=p,plan_sha256=hashlib.sha256(p.read_bytes()).hexdigest())
+        self.assertEqual(after['content_fingerprints'],before['content_fingerprints'])
+        with closing(open_store(pg_service=self.service,pg_schema=self.target).conn)as c:
+            self.assertEqual(apply_plan(c,before)['updated_editions'],0)
+            self.assertEqual(c.execute('SELECT abstract FROM papers ORDER BY id LIMIT 1').fetchone()[0],'Abstract\x00with\x01data')
+
+    def test_native_stale_source_plan_preserves_both_original_memberships(self):
+        with closing(open_store(pg_service=self.service,pg_schema=self.target).conn)as c:
+            before=plan(c)
+            c.execute("UPDATE source_records SET title='Changed' WHERE external_id=?",('conf/ijcai/fixture2022',));c.commit()
+            with self.assertRaisesRegex(ValueError,'Stale repair plan'):
+                apply_plan(c,before)
+            c.rollback()
+            self.assertEqual(inspect(c)['status'],'ready')

tests/test_postgres.py

@@ -175,6 +175,22 @@ class PostgreSQLIntegrationTests(unittest.TestCase):
         finally:
             reader.close()
 
+    def test_history_audit_matches_sqlite_for_actual_postgresql_snapshot(self):
+        from paper_atlas.audits.histories import report
+        from tests.test_histories import add_history_fixture
+        store = Store(self.db)
+        try:
+            add_history_fixture(store)
+        finally:
+            store.conn.close()
+        expected = report(self.db)
+        self.assertEqual(self.migrate()['status'], 'complete')
+        actual = report(pg_service=self.service, pg_schema=self.target)
+        self.assertEqual(actual['engine'], 'postgresql')
+        self.assertEqual(actual['schema'], self.target)
+        for key in ('counts', 'latest_attempt_status_counts', 'evidence_relationship_checks', 'examples'):
+            self.assertEqual(actual[key], expected[key], key)
+
     def interrupt_after_first_table(self):
         calls = 0
         def interrupt(*args):

tests/test_public_openreview.py

@@ -152,6 +152,35 @@ class PublicOpenReviewTests(unittest.TestCase):
             finally:
                 store.conn.close()
 
+    def test_unicode_separators_in_abstract_survive_audit_and_import(self):
+        for separator in ('\u0085', '\u2028', '\u2029'):
+            with self.subTest(separator=repr(separator)), tempfile.TemporaryDirectory() as tmp:
+                root = Path(tmp)
+                abstract = 'First paragraph' + separator + 'Second paragraph'
+                result = self.collect(root / 'source', {
+                    'venues/icml/icml2025.jsonl': [self.row(abstract=abstract)]})
+                path = Path(result['files'][0]['file'])
+                data = path.read_bytes()
+                self.assertIn(separator.encode(), data)
+                self.assertEqual(data.count(b'\n'), 1)
+                db = root / 'db.sqlite'
+                store = Store(db)
+                store.conn.close()
+                inventory = root / 'source/public-openreview-inventory.json'
+                before = audit(db, inventory, root / 'before.json')
+                self.assertEqual(before['status'], 'ready_for_serial_import')
+                self.assertEqual(before['records_checked'], 1)
+                ingest_file(db, path)
+                after = audit(db, inventory, root / 'after.json')
+                self.assertEqual(after['status'], 'ready_for_serial_import')
+                self.assertEqual(after['existing_same_edition_attempts'], 1)
+                store = Store(db)
+                try:
+                    self.assertEqual(store.conn.execute(
+                        'SELECT abstract FROM source_records').fetchone()[0], abstract)
+                finally:
+                    store.conn.close()
+
 
 if __name__ == '__main__':
     unittest.main()