Keep day-only withdrawal evidence through native ingestion
Metadata integrity checks / metadata (push) Failing after 2m6s

This commit is contained in:
2026-11-10 01:02:54 +08:00
parent 930df2a4d5
commit bf05d3cdc8
3 changed files with 25 additions and 4 deletions
+1 -1
View File
@@ -9,7 +9,7 @@
排除 3 个 keynote;research 的 p238 明确标注 `Retracted June 8, 2026`,完整题名、作者、栏目、日期、原文和来源回执保存在采集报告 `held_publications` 中,**不会输出 accepted 或 withdrawn 投稿记录**。当前决定模型没有独立 retracted 状态,后续须单独建模和核验;原始证据不能删除。任何新增或改变的撤稿标记都会停止采集,等待人工核查。
另一个 extended abstract p3178 明确标注 `Withdrawn June 8, 2026`,输出 `withdrawn` 和日期 `2026-06-08`,不补造其此前的接受决定或 PDF 链接。因此 639 个输出条目是 **638 accepted、1 withdrawn**,按六个 track 分组:`proceedings_unspecified` 522、`aaai_transfer` 19、`blue_sky` 17、`doctoral` 34、`demo` 44、`jaamas` 3。全文/扩展摘要是发表形式,不是研究类型;research 栏目不能证明每篇原始 main/special 投稿轨道。JAAMAS 保留期刊展示语义,不制造另一次独立审稿录用。
另一个 extended abstract p3178 明确标注 `Withdrawn June 8, 2026`,输出 `withdrawn`,在 metadata 保留日期 `2026-06-08` 和日精度;原网页没有时区/时刻,不能伪造决定 timestamp,不补造其此前的接受决定或 PDF 链接。因此 639 个输出条目是 **638 accepted、1 withdrawn**,按六个 track 分组:`proceedings_unspecified` 522、`aaai_transfer` 19、`blue_sky` 17、`doctoral` 34、`demo` 44、`jaamas` 3。全文/扩展摘要是发表形式,不是研究类型;research 栏目不能证明每篇原始 main/special 投稿轨道。JAAMAS 保留期刊展示语义,不制造另一次独立审稿录用。
[AAAI 转投详细政策](https://cyprusconferences.org/aamas2026/call-for-papers-aaai-track/) 要求基于 AAAI-26 rejected 稿件;[总览](https://cyprusconferences.org/aamas2026/calls/) 却写 AAAI-25,须保留冲突。采集器保留 AAAI 栏目归属,不据此生成原 AAAI 投稿 ID、年份或逐篇拒稿决定。目录不是原始决定 note,未来关联仍需逐篇证据。
-2
View File
@@ -143,8 +143,6 @@ def parse_contents(html, evidence):
'raw_decision': retractions[0] if withdrawn else 'listed in official AAMAS 2026 published proceedings '+heading,
'metadata': metadata,
'tags': [{'namespace': 'aamas_proceedings:publication_format', 'value': publication_format}]})
if withdrawn:
records[-1]['decision_date'] = '2026-06-08'
if headers != list(SECTIONS) or dict(counts) != {k: v[3] for k, v in SECTIONS.items()}:
raise ValueError('Publisher section inventory differs from reviewed 2026 layout')
if (len(records), len(excluded), len(held)) != (639, 3, 1):
+24 -1
View File
@@ -3,10 +3,12 @@ import hashlib
import json
from pathlib import Path
import tempfile
import sqlite3
import unittest
from unittest.mock import patch
from paper_atlas.collectors import aamas, aamas2026
from paper_atlas.ingestion.records import ingest_file
FIXTURE = json.loads(gzip.decompress((Path(__file__).parent/'fixtures/aamas2026-fixture.json.gz').read_bytes()))
@@ -47,12 +49,33 @@ class Aamas2026Tests(unittest.TestCase):
rows, _, _ = self.parse()
row, = [r for r in rows if r['external_id'] == '2026/p3178']
self.assertEqual(row['status'], 'withdrawn')
self.assertEqual(row['decision_date'], '2026-06-08')
self.assertEqual(row['metadata']['withdrawal_date'], '2026-06-08')
self.assertNotIn('decision_date', row)
self.assertEqual(row['raw_decision'], 'Withdrawn June 8, 2026')
self.assertNotIn('paper_url', row['metadata'])
self.assertEqual(row['metadata']['publication_state'], 'withdrawn')
self.assertEqual(sum(r['status'] == 'accepted' for r in rows), 638)
def test_withdrawal_ingestion_retains_date_precision_without_invented_acceptance(self):
rows, _, _ = self.parse()
row, = [r for r in rows if r['external_id'] == '2026/p3178']
with tempfile.TemporaryDirectory() as tmp:
root = Path(tmp); path = root/'withdrawn.jsonl'; db = root/'sample.sqlite'
path.write_text(json.dumps(row, ensure_ascii=False)+'\n')
path.with_suffix('.manifest.json').write_text(json.dumps({
'source': 'aamas_proceedings', 'list_url': aamas2026.URL,
'venue': 'AAMAS', 'year': 2026, 'track': row['track'],
'count': 1, 'status': 'partial', 'missing_abstract_count': 1,
'file_sha256': hashlib.sha256(path.read_bytes()).hexdigest()}))
ingest_file(db, path)
with sqlite3.connect(db) as c:
self.assertEqual(c.execute('SELECT status,raw_value,decision_date FROM decisions').fetchall(),
[('withdrawn', 'Withdrawn June 8, 2026', None)])
metadata = json.loads(c.execute('SELECT metadata_json FROM source_records').fetchone()[0])
self.assertEqual(metadata['withdrawal_date'], '2026-06-08')
self.assertEqual(metadata['decision_date_precision'], 'day')
self.assertEqual(c.execute('PRAGMA foreign_key_check').fetchall(), [])
def test_retraction_is_not_accepted_or_withdrawn_and_retains_date(self):
rows, _, held = self.parse()
self.assertNotIn('2026/p238', {r['external_id'] for r in rows})