Add ICML 2026 public rejected-submission archive with platform evidence

docs/data-sources.md

@@ -77,6 +77,17 @@ paper-atlas audit public-openreview --db /data/paper-index/papers.sqlite \
 
 入库前审计核验文件哈希、数量、轨道和来源声明，并用真实 forum ID 对比同届同轨道已有投稿。存在不同决定时阻止整批导入，交由来源和时序核查；另一会议的后续录用属于独立投稿历史，不构成该次拒稿的冲突。同一 forum 的镜像不新增投稿事件，但论文实体的跨平台去重仍须在全量结束后核验。审计通过的报告包含带 SHA-256 的导入队列；应在单写入维护锁下及时串行导入，主库变化后重新审计。
 
+ICML 2026 另有[公开原始投稿快照](https://github.com/HemantKumar01/ICML-2026-data/blob/1a1b9d973a8dfbf254f740fb8100a2fcf36757ea/data/rejected.json)，包含 214 条投稿根记录。`collect icml-public-archive` 固定该 commit、文件长度及 Git blob 哈希，逐条要求 `readers` 包含 everyone、forum 等于自身 ID、域及投稿邀请属于主会、平台 `venueid` 明确为 `ICML.cc/2026/Conference/Rejected_Submission`。不能仅根据显示文案 Submitted to ICML 2026 推断拒稿。
+
+```sh
+paper-atlas collect icml-public-archive --out /data/paper-index/collected/icml-2026-public-archive
+paper-atlas audit public-openreview --db /data/paper-index/papers.sqlite \
+  --inventory /data/paper-index/collected/icml-2026-public-archive/public-openreview-inventory.json \
+  --out /data/paper-index/collected/icml-2026-public-preimport.json
+```
+
+这批证据标记为 `public_submission_venueid`，保留逐投稿许可及快照出处；它与整理者的 Reject 标签、原始签名决定分别表述。记录修改时间不当作决定日期，观察时间采用快照上界，不采用今天的导入时间。214 是这个公开 opt-in 子集的投稿数，不能当作会议全部拒稿数，也不能直接当作去重论文实体数。该采集器同样只提取元数据与标题摘要，丢弃 authorids、个人资料、评审和 PDF 字段。
+
 ```sh
 python3 -B -m paper_atlas collect peerread --cache /data/paper-index/raw/http-cache \
   --out /data/paper-index/collected

docs/usage.md

@@ -15,6 +15,7 @@ paper-atlas collect ecva --cache /data/paper-index/raw/http-cache --out /data/pa
 paper-atlas catalogue dblp --help
 paper-atlas audit iclr --help
 paper-atlas collect public-openreview --help
+paper-atlas collect icml-public-archive --help
 paper-atlas audit public-openreview --help
 ```
 

paper_atlas/audits/public_openreview.py

@@ -7,14 +7,19 @@ from pathlib import Path
 import sqlite3
 
 from paper_atlas.collectors.public_openreview import SOURCE, REVISION
+from paper_atlas.collectors.icml_public_archive import SOURCE as ARCHIVE_SOURCE, REVISION as ARCHIVE_REVISION
 from paper_atlas.db.submissions import timestamp
 
 
 def audit(db, inventory, out):
     inventory = Path(inventory).resolve()
     result = json.loads(inventory.read_text())
-    if result.get('source') != SOURCE or result.get('revision') != REVISION:
-        raise ValueError('Unsupported curated source inventory')
+    specs = {SOURCE: (REVISION, 'curated_public_status_assertion'),
+             ARCHIVE_SOURCE: (ARCHIVE_REVISION, 'public_submission_venueid')}
+    source = result.get('source')
+    if source not in specs or result.get('revision') != specs[source][0]:
+        raise ValueError('Unsupported public source inventory')
+    revision, evidence_kind = specs[source]
     db = Path(db).resolve()
     if not db.is_file():
         raise ValueError('Existing database required for identity and status audit')
@@ -38,8 +43,8 @@ def audit(db, inventory, out):
                 if any(row[key] != manifest[key] for key in ('source', 'venue', 'year', 'track')):
                     raise ValueError('Record edition differs from inventory')
                 meta = row['metadata']
-                if meta.get('evidence_kind') != 'curated_public_status_assertion' or meta.get('source_revision') != REVISION:
-                    raise ValueError('Missing explicit curated provenance')
+                if meta.get('evidence_kind') != evidence_kind or meta.get('source_revision') != revision:
+                    raise ValueError('Missing explicit public source provenance')
                 if meta.get('original_decision_signature_verified') is not False:
                     raise ValueError('Curated metadata must not claim original signatures')
                 if row['status'] not in ('rejected', 'desk_rejected', 'withdrawn'):
@@ -71,7 +76,7 @@ def audit(db, inventory, out):
             checksums[str(path)] = manifest['file_sha256']
     if checked != result['normalized_records']:
         raise ValueError('Normalized inventory total differs from checked records')
-    report = {'source': SOURCE, 'revision': REVISION, 'database': str(db),
+    report = {'source': source, 'revision': revision, 'database': str(db),
               'inventory': str(inventory), 'checked_at': timestamp(), 'records_checked': checked,
               'existing_same_edition_attempts': existing_attempts, 'conflicts': conflicts,
               'status': 'blocked' if conflicts else 'ready_for_serial_import',

paper_atlas/cli.py

@@ -14,6 +14,7 @@ COMMANDS = {
     ('collect','iclr-program'): ('paper_atlas.collectors.iclr', {}, 'ICLR 官方公开程序'),
     ('collect','iclr-snapshot'): ('paper_atlas.collectors.openreview', {}, 'ICLR 公开投稿与决定快照'),
     ('collect','public-openreview'): ('paper_atlas.collectors.public_openreview', {}, '核验其他会议的公开拒稿及撤稿标签'),
+    ('collect','icml-public-archive'): ('paper_atlas.collectors.icml_public_archive', {}, 'ICML 2026 公开拒稿原始投稿快照'),
     ('collect','peerread'): ('paper_atlas.collectors.peerread', {}, 'PeerRead 历史决定补充'),
     ('collect','colm'): ('paper_atlas.collectors.proceedings', {'source':'colm'}, 'COLM 官方论文集'),
     ('collect','neurips'): ('paper_atlas.collectors.proceedings', {'source':'neurips'}, 'NeurIPS 官方论文集'),

paper_atlas/collectors/icml_public_archive.py

@@ -0,0 +1,125 @@
+"""ICML 2026 public submission roots with explicit Rejected_Submission IDs."""
+import argparse
+import fcntl
+import hashlib
+import json
+from pathlib import Path
+import re
+import shutil
+import tempfile
+
+from paper_atlas.collectors.openreview import date_ms, invitations, public, value
+from paper_atlas.collectors.public_openreview import download
+from paper_atlas.db.submissions import timestamp
+
+
+SOURCE = 'openreview_public_archive'
+REVISION = '1a1b9d973a8dfbf254f740fb8100a2fcf36757ea'
+AS_OF = '2026-08-08T12:03:26.000Z'
+URL = 'https://raw.githubusercontent.com/HemantKumar01/ICML-2026-data/' + REVISION + '/data/rejected.json'
+BLOB_SHA1 = 'cebdcddffe3eb2145d32d328db89a1626e3f85eb'
+BYTES = 1600856
+EXPECTED = 214
+DOMAIN = 'ICML.cc/2026/Conference'
+VENUEID = DOMAIN + '/Rejected_Submission'
+
+
+def normalize(note):
+    forum = note.get('id')
+    if not isinstance(forum, str) or not re.fullmatch(r'[A-Za-z0-9_-]{8,32}', forum) or note.get('forum') != forum:
+        raise ValueError('Not a public submission root with a real forum identity')
+    if not public(note) or note.get('ddate'):
+        raise ValueError('Submission is not explicitly public and live in the archive')
+    if note.get('domain') != DOMAIN or DOMAIN + '/-/Submission' not in invitations(note):
+        raise ValueError('Submission is outside the ICML 2026 conference track')
+    content = note.get('content') or {}
+    if value(content, 'venueid') != VENUEID:
+        raise ValueError('Missing explicit platform Rejected_Submission classification')
+    title, abstract = value(content, 'title'), value(content, 'abstract')
+    if not isinstance(title, str) or not title.strip():
+        raise ValueError('Submission lacks a title')
+    if abstract is not None and not isinstance(abstract, str):
+        raise ValueError('Submission abstract must be text')
+    authors = value(content, 'authors', []) or []
+    if not isinstance(authors, list):
+        raise ValueError('Unexpected public author format')
+    authors = [a.strip() for a in authors if isinstance(a, str) and a.strip() and '@' not in a
+               and not re.fullmatch(r'anonymous(?: authors?)?', a.strip(), re.I)]
+    tags = []
+    for field in ('keywords', 'primary_area'):
+        raw = value(content, field)
+        terms = raw if isinstance(raw, list) else re.split(r'[,;]', raw) if field == 'keywords' and isinstance(raw, str) else [raw]
+        tags.extend({'namespace': SOURCE + ':' + field, 'value': term.strip()}
+                    for term in terms if isinstance(term, str) and term.strip())
+    url = 'https://openreview.net/forum?id=' + forum
+    return {'source': SOURCE, 'external_id': 'icml/2026/' + forum, 'url': url,
+            'title': ' '.join(title.split()), 'abstract': abstract.strip() if abstract else None,
+            'authors': authors, 'identifiers': {'openreview': forum},
+            'submission_identifiers': [{'scheme': 'openreview', 'value': forum}],
+            'venue': 'ICML', 'year': 2026, 'track': 'main', 'status': 'rejected',
+            'raw_decision': VENUEID, 'evidence_url': url, 'observed_at': AS_OF,
+            'submitted_at': date_ms(note.get('cdate') or note.get('tcdate')), 'tags': tags,
+            'metadata': {'source_revision': REVISION, 'source_blob_sha1': BLOB_SHA1,
+                         'source_file': URL, 'original_forum': forum, 'license': note.get('license'),
+                         'venue': value(content, 'venue'), 'venueid': VENUEID,
+                         'public_readers_verified': True, 'original_invitations': invitations(note),
+                         'source_note_modified_at': date_ms(note.get('mdate')),
+                         'evidence_kind': 'public_submission_venueid',
+                         'original_decision_signature_verified': False,
+                         'source_snapshot_upper_bound': AS_OF}}
+
+
+def collect(out, fetcher=None):
+    fetcher = fetcher or download
+    out = Path(out)
+    out.mkdir(parents=True, exist_ok=True)
+    with (out / 'collect.lock').open('a') as lock:
+        fcntl.flock(lock, fcntl.LOCK_EX | fcntl.LOCK_NB)
+        if (out / 'public-openreview-inventory.json').exists():
+            raise ValueError('Completed inventory exists; select a new output directory')
+        if shutil.disk_usage(out).free < 8 * 1024**3:
+            raise RuntimeError('Less than 8 GiB free before collection')
+        data = fetcher(URL, BYTES)
+        blob = hashlib.sha1(b'blob ' + str(len(data)).encode() + b'\0' + data).hexdigest()
+        if len(data) != BYTES or blob != BLOB_SHA1:
+            raise ValueError('Public archive checksum mismatch')
+        archive = json.loads(data)
+        notes = archive['notes']
+        if archive.get('count') != EXPECTED or not isinstance(notes, list) or len(notes) != EXPECTED:
+            raise ValueError('Public archive inventory count mismatch')
+        records = [normalize(note) for note in notes]
+        if len({row['identifiers']['openreview'] for row in records}) != EXPECTED:
+            raise ValueError('Repeated submission forum in public archive')
+        records.sort(key=lambda row: row['external_id'])
+        with tempfile.TemporaryDirectory(prefix='.icml-public-', dir=out) as temporary:
+            stage = Path(temporary)
+            path = stage / 'public-openreview-icml-2026-main.jsonl'
+            path.write_text(''.join(json.dumps(row, ensure_ascii=False) + '\n' for row in records))
+            manifest = {'source': SOURCE, 'parser_version': 1, 'venue': 'ICML', 'year': 2026,
+                        'track': 'main', 'count': EXPECTED, 'status': 'partial', 'list_url': URL,
+                        'file': str(out / path.name), 'file_sha256': hashlib.sha256(path.read_bytes()).hexdigest(),
+                        'source_revision': REVISION, 'missing_abstract_count': sum(not row['abstract'] for row in records),
+                        'evidence_kind': 'public_submission_venueid',
+                        'note': 'Public opt-in subset; explicit platform venueid, not original signed PC notes.'}
+            path.with_suffix('.manifest.json').write_text(json.dumps(manifest, indent=2) + '\n')
+            result = {'source': SOURCE, 'revision': REVISION, 'finished_at': timestamp(),
+                      'input_rows': EXPECTED, 'normalized_records': EXPECTED, 'files': [manifest],
+                      'source_files': [{'url': URL, 'git_blob_sha1': blob, 'input_bytes': len(data)}],
+                      'note': 'Snapshot preserves per-note public visibility and licenses; no reviews, authorids or PDFs retained.'}
+            inventory = stage / 'public-openreview-inventory.json'
+            inventory.write_text(json.dumps(result, indent=2) + '\n')
+            for child in sorted(stage.iterdir(), key=lambda child: child == inventory):
+                child.replace(out / child.name)
+            print(json.dumps(result), flush=True)
+            return result
+
+
+def main(argv=None, *, prog=None):
+    parser = argparse.ArgumentParser(prog=prog)
+    parser.add_argument('--out', required=True)
+    args = parser.parse_args(argv)
+    collect(args.out)
+
+
+if __name__ == '__main__':
+    main()

tests/test_icml_public_archive.py

@@ -0,0 +1,86 @@
+import hashlib
+import json
+from pathlib import Path
+import tempfile
+import unittest
+from unittest.mock import patch
+
+from paper_atlas.collectors import icml_public_archive as archive
+from paper_atlas.audits.public_openreview import audit
+from paper_atlas.db.store import Store
+from paper_atlas.ingestion.records import ingest_file
+
+
+class ICMLPublicArchiveTests(unittest.TestCase):
+    def note(self, **changes):
+        return {'id': 'PublicRoot1', 'forum': 'PublicRoot1', 'readers': ['everyone'],
+                'domain': archive.DOMAIN, 'invitations': [archive.DOMAIN + '/-/Submission'],
+                'license': 'CC BY 4.0', 'cdate': 1769251630136,
+                'content': {'title': {'value': 'A public rejected submission'},
+                            'abstract': {'value': 'Public abstract'},
+                            'authors': {'value': ['Anonymous', 'Jane Doe']},
+                            'authorids': {'value': ['private@example.org']},
+                            'venue': {'value': 'Submitted to ICML 2026'},
+                            'venueid': {'value': archive.VENUEID},
+                            'primary_area': {'value': 'learning'},
+                            'pdf': {'value': '/private.pdf'}},
+                'details': {'reviews': ['not retained']}, **changes}
+
+    def test_explicit_platform_classification_requires_public_root_and_correct_scope(self):
+        original = self.note()
+        normalized = archive.normalize(original)
+        self.assertEqual(normalized['status'], 'rejected')
+        self.assertEqual(normalized['raw_decision'], archive.VENUEID)
+        self.assertEqual(normalized['metadata']['license'], 'CC BY 4.0')
+        self.assertEqual(normalized['metadata']['evidence_kind'], 'public_submission_venueid')
+        self.assertFalse(normalized['metadata']['original_decision_signature_verified'])
+        self.assertNotIn('private@example.org', json.dumps(normalized))
+        self.assertNotIn('not retained', json.dumps(normalized))
+        for changes in ({'readers': ['authors']}, {'forum': 'AnotherRoot'}, {'ddate': 1000},
+                        {'domain': 'ICML.cc/2026/Position_Papers'}, {'invitations': []}):
+            with self.subTest(changes=changes), self.assertRaises(ValueError):
+                archive.normalize(self.note(**changes))
+        for venueid in (None, 'ICML.cc/2026/Conference/Submission', 'ICML.cc/2026/Conference/Accepted_Submission'):
+            candidate = self.note()
+            candidate['content']['venueid'] = {'value': venueid}
+            with self.assertRaisesRegex(ValueError, 'classification'):
+                archive.normalize(candidate)
+
+    def collect_fixture(self, out, notes, count=None, corrupt=False):
+        data = json.dumps({'count': len(notes) if count is None else count, 'notes': notes}).encode()
+        blob = hashlib.sha1(b'blob ' + str(len(data)).encode() + b'\0' + data).hexdigest()
+        with patch.multiple(archive, BYTES=len(data), BLOB_SHA1=blob, EXPECTED=len(notes)), \
+             patch.object(archive.shutil, 'disk_usage', return_value=type('Space', (), {'free': 20 * 1024**3})()):
+            return archive.collect(out, fetcher=lambda url, limit: data + b'x' if corrupt else data)
+
+    def test_verified_archive_roundtrips_through_preflight_and_idempotent_import(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            result = self.collect_fixture(root / 'source', [self.note()])
+            db = root / 'db.sqlite'
+            Store(db).conn.close()
+            report = audit(db, root / 'source/public-openreview-inventory.json', root / 'audit.json')
+            self.assertEqual(report['status'], 'ready_for_serial_import')
+            self.assertEqual(report['source'], archive.SOURCE)
+            self.assertEqual(result['files'][0]['status'], 'partial')
+            for _ in range(2):
+                ingest_file(db, report['files'][0])
+            store = Store(db)
+            try:
+                self.assertEqual(store.conn.execute('SELECT count(*) FROM submissions').fetchone()[0], 1)
+                self.assertEqual(store.conn.execute('SELECT status FROM decisions').fetchall(), [('rejected',)])
+            finally:
+                store.conn.close()
+
+    def test_bad_hash_count_or_duplicate_identity_publishes_nothing(self):
+        for kwargs in ({'corrupt': True}, {'count': 99}, {}):
+            notes = [self.note(), self.note()] if not kwargs else [self.note()]
+            with self.subTest(kwargs=kwargs), tempfile.TemporaryDirectory() as tmp:
+                with self.assertRaises(ValueError):
+                    self.collect_fixture(tmp, notes, **kwargs)
+                self.assertEqual(list(Path(tmp).glob('*.jsonl')), [])
+                self.assertFalse((Path(tmp) / 'public-openreview-inventory.json').exists())
+
+
+if __name__ == '__main__':
+    unittest.main()