academic-refchecker 1.2.44__py3-none-any.whl → 1.2.46__py3-none-any.whl

__version__.py

@@ -1,3 +1,3 @@
 """Version information for RefChecker."""
 
-__version__ = "1.2.44"
+__version__ = "1.2.46"

{academic_refchecker-1.2.44.dist-info → academic_refchecker-1.2.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academic-refchecker
-Version: 1.2.44
+Version: 1.2.46
 Summary: A comprehensive tool for validating reference accuracy in academic papers
 Author-email: Mark Russinovich <markrussinovich@hotmail.com>
 License-Expression: MIT
@@ -78,7 +78,9 @@ A comprehensive tool for validating reference accuracy in academic papers, usefu
        Verified URL: https://www.semanticscholar.org/paper/5f4ac1ac7ca4b17d3db1b52d9aafd9e8b26c0d7
        ArXiv URL: https://arxiv.org/abs/1610.10099
        DOI URL: https://doi.org/10.48550/arxiv.1610.10099
-      ⚠️  Warning: Year mismatch: cited as 2017 but actually 2016
+      ⚠️  Warning: Year mismatch:
+               cited:  '2017'
+               actual: '2016'
 
 [2/45] Effective approaches to attention-based neural machine translation
        Minh-Thang Luong, Hieu Pham, Christopher D. Manning
@@ -87,7 +89,9 @@ A comprehensive tool for validating reference accuracy in academic papers, usefu
        Verified URL: https://www.semanticscholar.org/paper/93499a7c7f699b6630a86fad964536f9423bb6d0
        ArXiv URL: https://arxiv.org/abs/1508.04025
        DOI URL: https://doi.org/10.18653/v1/d15-1166
-      ❌ Error: First author mismatch: 'Minh-Thang Luong' vs 'Thang Luong'
+      ❌ Error: First author mismatch:
+               cited:  'Minh-Thang Luong'
+               actual: 'Thang Luong'
 
 [3/45] Deep Residual Learning for Image Recognition
        Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
@@ -98,7 +102,9 @@ A comprehensive tool for validating reference accuracy in academic papers, usefu
        Verified URL: https://www.semanticscholar.org/paper/2c03df8b48bf3fa39054345bafabfeff15bfd11d
        ArXiv URL: https://arxiv.org/abs/1512.03385
        DOI URL: https://doi.org/10.1109/CVPR.2016.90
-      ❌ Error: DOI mismatch: cited as '10.1109/CVPR.2016.91' but actually '10.1109/CVPR.2016.90'
+      ❌ Error: DOI mismatch:
+               cited:  '10.1109/CVPR.2016.91'
+               actual: '10.1109/CVPR.2016.90'
 
 ============================================================
 📋 SUMMARY
@@ -382,7 +388,9 @@ This enhanced URL display helps users access multiple authoritative sources for
            Verified URL: https://www.semanticscholar.org/paper/a1b2c3d4e5f6789012345678901234567890abcd
            ArXiv URL: https://arxiv.org/abs/2312.02119
            DOI URL: https://doi.org/10.48550/arxiv.2312.02119
-          ❌ Error: First author mismatch: 'T. Xie' vs 'Zhao Xu'
+          ❌ Error: First author mismatch:
+                   cited:  'T. Xie'
+                   actual: 'Zhao Xu'
     ```
   - `title`: Title discrepancies
     ```
@@ -392,7 +400,9 @@ This enhanced URL display helps users access multiple authoritative sources for
            Verified URL: https://www.semanticscholar.org/paper/df2b0e26d0599ce3e70df8a9da02e51594e0e992
            ArXiv URL: https://arxiv.org/abs/1810.04805
            DOI URL: https://doi.org/10.18653/v1/n19-1423
-          ❌ Error: Title mismatch: cited as 'BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding' but actually 'BERT: Pre-training of Deep Bidirectional Transformers for Language Comprehension'
+          ❌ Error: Title mismatch:
+                   cited:  'BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding'
+                   actual: 'BERT: Pre-training of Deep Bidirectional Transformers for Language Comprehension'
     ```
   - `arxiv_id`: Incorrect URLs or arXiv IDs
     ```
@@ -415,7 +425,9 @@ This enhanced URL display helps users access multiple authoritative sources for
            Verified URL: https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776
            ArXiv URL: https://arxiv.org/abs/1706.03762
            DOI URL: https://doi.org/10.48550/arXiv.1706.03762
-          ❌ Error: DOI mismatch: cited as '10.5555/3295222.3295349' but actually '10.48550/arXiv.1706.03762'
+          ❌ Error: DOI mismatch:
+                   cited:  '10.5555/3295222.3295349'
+                   actual: '10.48550/arXiv.1706.03762'
     ```
 
 - **⚠️ Warnings**: Minor issues that may need attention
@@ -428,7 +440,9 @@ This enhanced URL display helps users access multiple authoritative sources for
            Verified URL: https://www.semanticscholar.org/paper/f1a2b3c4d5e6f7890123456789012345678901ab
            ArXiv URL: https://arxiv.org/abs/2310.03684
            DOI URL: https://doi.org/10.48550/arxiv.2310.03684
-          ⚠️  Warning: Year mismatch: cited as 2024 but actually 2023
+          ⚠️  Warning: Year mismatch:
+                   cited:  '2024'
+                   actual: '2023'
     ```
   - `venue`: Venue format variations
     ```
@@ -439,7 +453,9 @@ This enhanced URL display helps users access multiple authoritative sources for
            Verified URL: https://www.semanticscholar.org/paper/c1d2e3f4a5b6c7d8e9f0123456789012345678ab
            ArXiv URL: https://arxiv.org/abs/2403.02151
            DOI URL: https://doi.org/10.48550/arxiv.2403.02151
-          ⚠️  Warning: Venue mismatch: cited as 'arXiv, 2024' but actually 'Neural Information Processing Systems'
+          ⚠️  Warning: Venue mismatch:
+                   cited:  'arXiv, 2024'
+                   actual: 'Neural Information Processing Systems'
     ```
 
 - **❓ Unverified**: References that couldn't be verified with any of the checker APIs

{academic_refchecker-1.2.44.dist-info → academic_refchecker-1.2.46.dist-info}/RECORD

@@ -1,21 +1,21 @@
-__version__.py,sha256=k3lYUlcZL-yL2e_2u3UPBtgwqMqZJ11x7KVMZOotlE8,65
-academic_refchecker-1.2.44.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
+__version__.py,sha256=PuEdWOtQEDRwfL2m1mk5h6WKAoScQu-kbHu9VkBS764,65
+academic_refchecker-1.2.46.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
 checkers/__init__.py,sha256=T0PAHTFt6UiGvn-WGoJU8CdhXNmf6zaHmcGVoWHhmJQ,533
-checkers/crossref.py,sha256=Hzq4dlf1CSn0aZWU8CMOnLxIvaSivTabLoepIOkgkmY,20585
+checkers/crossref.py,sha256=cLYmSzE8ehJ5sNko_R3fEiGBGiPH5_HxLhFM-pCfDRM,20378
 checkers/enhanced_hybrid_checker.py,sha256=6yf5tV4jLSVzjX1xR_kQq0NOgQIst-z_WmkiqqMc8hQ,23469
-checkers/github_checker.py,sha256=54K6_YJW5w2GtzodnSOLfK5d1ErFJxbTOIIV5P_kFX0,13543
+checkers/github_checker.py,sha256=GoepG4aRRUqAomkM4HgOSNf20BPxQgocZEpsk0ZTZZU,14003
 checkers/local_semantic_scholar.py,sha256=DgGMjmR_w_saz2UTMatEhfXbhUED9tUmDG3vlZAIzc4,20428
-checkers/openalex.py,sha256=GxYUH9GZ0AyF-WFKgXiFHqkalrSnySgFSkiM1PsK0VI,19757
-checkers/openreview_checker.py,sha256=FLh21F0Zr7Gj3BI0u-gE6IwGNOZiRcViirDBeNvUp94,20432
-checkers/semantic_scholar.py,sha256=BelhyIJ-W8navRdqEGpk12CIXYWmVL2Cq8HHZR7ynJs,34905
-checkers/webpage_checker.py,sha256=BvNwOqukTX9IeQUpUfIrI_5Gr2w9VLBt5x_PB-hKUIo,21616
+checkers/openalex.py,sha256=Fbc7iscZzmXjAZxH32PDX2r2Nwo9b5Ku-Sh1Ut9KpLA,19550
+checkers/openreview_checker.py,sha256=EYRcVu7sZzrFjqdOEKp72vd0S3sXSSjTgI9jsAVpdD0,20524
+checkers/semantic_scholar.py,sha256=99KOHLAiYs31nSdx-gcMR_TWIlV8G4juNL0bmV4AoUs,34768
+checkers/webpage_checker.py,sha256=Ivzhu0xcpeWZcCTlAt9C06Lfsz5gKEiSko9gJ7EyQEw,22324
 config/__init__.py,sha256=r7sONsX2-ITviUJRU1KEz76uAuTRqZlzU-TVkvFRGYY,15
 config/logging.conf,sha256=r1tP0ApLHtlz7rV-oKS1MVO7oXJOgahbZFTtYmKnf9U,687
 config/settings.py,sha256=-vODFoXbWbGPUElpmchE5zbCj_n4Vtxr8HU1hQDFp_c,6164
 core/__init__.py,sha256=1T2MSQyDk0u_PupbHvm4CvNNN--dxsw78fqKUrqoYrM,157
 core/db_connection_pool.py,sha256=XRiOdehikkSz3obH4WKgf8woa3694if50Q15rBT-4XQ,4697
-core/parallel_processor.py,sha256=5V2iJDBFwwryMCnCNU_oRt2u5he1wpy-_9qapC_6f00,17043
-core/refchecker.py,sha256=w3KNWyyaZZVL3ghFhEfro8SPs4xXEUjmCJERfZ7Du6A,273648
+core/parallel_processor.py,sha256=AOnjqhBHXlSb1c-PSunat9Eug5y04gOygwbHdPUqxgk,17202
+core/refchecker.py,sha256=lU6r9cKpB8Fc4Wd7vOqdqhxP9cwYEoB6D4PlYznglGY,274337
 database/__init__.py,sha256=mEuVHlEBuS44t_2ZT_JnvQQrlRCjo1SJq1NmaJ6r8OY,125
 database/download_semantic_scholar_db.py,sha256=waN4I97KC_36YMiPbiBDUUmgfzu1nub5yeKdAsIR2aw,75276
 llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -26,21 +26,21 @@ scripts/start_vllm_server.py,sha256=ZepWp2y2cKFW0Kgsoima2RbmF02fTU29UFcLLpsBhFU,
 services/__init__.py,sha256=jGi9S74Msak3YR-C4Qb68VU7HB4oLaX9o1rlVAFpOFI,187
 services/pdf_processor.py,sha256=vu_JnhFGZY6jFVbDbPvG-mlQojvB-3Dzc8_946KVV2E,9427
 utils/__init__.py,sha256=1RrGoIIn1_gVzxd56b6a7HeAS-wu7uDP-nxLbR3fJ-8,1199
-utils/arxiv_utils.py,sha256=Y8sDJgDwHxp1L33BkQoDumIl0Pkp-BuYZb1PwWYsmak,18251
+utils/arxiv_utils.py,sha256=MxyD3Q0EzrmE0xORMJw8wdVtZ4Fp-ux_cn6jLMQimV8,18168
 utils/author_utils.py,sha256=DLTo1xsxef2wxoe4s_MWrh36maj4fgnvFlsDLpDE-qQ,5507
 utils/biblatex_parser.py,sha256=OkHXQcjiBrEDuhBfEk0RtmAYxufu5lAxAjb8__DzMjI,25537
 utils/bibliography_utils.py,sha256=mpmdAklzAs1CT3gqrOcjujGhouL95OuliCx0LE9Pg90,11705
 utils/bibtex_parser.py,sha256=a89NLy_q2kwED4QFJgxWFgPQOJBV73bIUL3RS_Urmro,15231
 utils/config_validator.py,sha256=rxf7K3DYmJ-BNPsmtaCNipY2BTVT-pJZ7wN-M9Y3GC8,11167
 utils/db_utils.py,sha256=_wSupfBlm0ILFvntQTvoj7tLDCbrYPRQrp9NDvphF_E,6281
-utils/doi_utils.py,sha256=8f3iE4RdSNkzeqa9wJfoKcVEiBVse3_uf643biLudmw,4134
-utils/error_utils.py,sha256=JqnRg4z-O9GcJ1eJGeTMzmOQwPWbWo2Lf6Duwj-ymHQ,6258
+utils/doi_utils.py,sha256=qAf2slTLkgBwwnkYsWMkwMSDf6q8wNqd2YwNxhQudEc,3995
+utils/error_utils.py,sha256=wrLQhVJIIWUzcTSOLVvrvCAtMRNXt_1YYL5OXYnYf0A,11085
 utils/mock_objects.py,sha256=QxU-UXyHSY27IZYN8Sb8ei0JtNkpGSdMXoErrRLHXvE,6437
-utils/text_utils.py,sha256=uEwKasw3aTVgIDHbDJDSOcTUbPwfiivIdhKwmxQJy0U,206378
+utils/text_utils.py,sha256=gFI-qu6g-9Lo1s3w1OjgBZ9SvdPufL1mMg-05l0BwD0,210269
 utils/unicode_utils.py,sha256=-WBKarXO756p7fd7gCeNsMag4ztDNURwFX5IVniOtwY,10366
 utils/url_utils.py,sha256=HdxIO8QvciP6Jp8Wd4sTSrS8JQrOMwgM7pxdUC8RJb4,9176
-academic_refchecker-1.2.44.dist-info/METADATA,sha256=ueA0mwKqmiqhR9WBLyPy2W40wfJc4JRiWSTbrQHKU14,22298
-academic_refchecker-1.2.44.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-academic_refchecker-1.2.44.dist-info/entry_points.txt,sha256=WdI89tYkIfz-M628PiboOfOLzTBWZAqvlF29qCVCkek,61
-academic_refchecker-1.2.44.dist-info/top_level.txt,sha256=6RlcQEA0kHb7-ndbKMFMZnYnJQVohgsU6BBkbEvJvEs,69
-academic_refchecker-1.2.44.dist-info/RECORD,,
+academic_refchecker-1.2.46.dist-info/METADATA,sha256=lP_pMHS9uI4hhXEsox_yGlSnT6pSl1_6W58CtzZEbDM,22576
+academic_refchecker-1.2.46.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+academic_refchecker-1.2.46.dist-info/entry_points.txt,sha256=WdI89tYkIfz-M628PiboOfOLzTBWZAqvlF29qCVCkek,61
+academic_refchecker-1.2.46.dist-info/top_level.txt,sha256=6RlcQEA0kHb7-ndbKMFMZnYnJQVohgsU6BBkbEvJvEs,69
+academic_refchecker-1.2.46.dist-info/RECORD,,

checkers/crossref.py

@@ -31,6 +31,7 @@ import re
 from typing import Dict, List, Tuple, Optional, Any, Union
 from urllib.parse import quote_plus
 from utils.text_utils import normalize_text, clean_title_basic, find_best_match, is_name_match, compare_authors, clean_title_for_search
+from utils.error_utils import format_year_mismatch, format_doi_mismatch
 from config.settings import get_config
 
 # Set up logging
@@ -478,21 +479,19 @@ class CrossRefReferenceChecker:
         if year and work_year and year != work_year:
             errors.append({
                 'warning_type': 'year',
-                'warning_details': f"Year mismatch: cited as {year} but actually {work_year}",
+                'warning_details': format_year_mismatch(year, work_year),
                 'ref_year_correct': work_year
             })
         
         # Verify DOI
         work_doi = work_data.get('DOI')
         if doi and work_doi:
-            # Normalize DOIs for comparison (remove URL prefix and trailing periods)
-            cited_doi_clean = doi.replace('https://doi.org/', '').replace('http://doi.org/', '').strip().rstrip('.')
-            work_doi_clean = work_doi.replace('https://doi.org/', '').replace('http://doi.org/', '').strip().rstrip('.')
-            
-            if cited_doi_clean.lower() != work_doi_clean.lower():
+            # Compare DOIs using the proper comparison function
+            from utils.doi_utils import compare_dois
+            if not compare_dois(doi, work_doi):
                 errors.append({
                     'error_type': 'doi',
-                    'error_details': f"DOI mismatch: cited as {doi} but actually {work_doi}",
+                    'error_details': format_doi_mismatch(doi, work_doi),
                     'ref_doi_correct': work_doi
                 })
         

checkers/github_checker.py

@@ -169,9 +169,14 @@ class GitHubChecker:
             if cited_title:
                 title_match = self._check_title_match(cited_title, actual_name, actual_description)
                 if not title_match:
+                    from utils.error_utils import format_title_mismatch
+                    details = format_title_mismatch(cited_title, actual_name)
+                    if actual_description:
+                        snippet = actual_description[:100] + ('...' if len(actual_description) > 100 else '')
+                        details += f" ({snippet})"
                     errors.append({
                         "warning_type": "title",
-                        "warning_details": f"Title mismatch: cited as '{cited_title}' but repository is '{actual_name}' ({actual_description[:100]}{'...' if len(actual_description) > 100 else ''})"
+                        "warning_details": details
                     })
             
             # Verify authors
@@ -180,9 +185,13 @@ class GitHubChecker:
                 author_str = ', '.join(cited_authors) if isinstance(cited_authors, list) else str(cited_authors)
                 author_match = self._check_author_match(author_str, actual_owner, actual_owner_name)
                 if not author_match:
+                    from utils.error_utils import format_three_line_mismatch
+                    left = author_str
+                    right = f"{actual_owner} ({actual_owner_name})" if actual_owner_name else actual_owner
+                    details = format_three_line_mismatch("Author mismatch", left, right)
                     errors.append({
                         "warning_type": "author",
-                        "warning_details": f"Author mismatch: cited as '{author_str}' but repository owner is '{actual_owner}' ({actual_owner_name})"
+                        "warning_details": details
                     })
             
             # Verify year
@@ -191,9 +200,10 @@ class GitHubChecker:
                 try:
                     cited_year_int = int(cited_year)
                     if cited_year_int < creation_year:
+                        from utils.error_utils import format_year_mismatch
                         errors.append({
                             "warning_type": "year",
-                            "warning_details": f"Year mismatch: cited as {cited_year} but repository created in {creation_year}",
+                            "warning_details": format_year_mismatch(cited_year, creation_year),
                             "ref_year_correct": str(creation_year)
                         })
                 except (ValueError, TypeError):

checkers/openalex.py

@@ -33,6 +33,7 @@ import re
 from typing import Dict, List, Tuple, Optional, Any, Union
 from urllib.parse import quote_plus
 from utils.text_utils import normalize_text, clean_title_basic, find_best_match, is_name_match, compare_authors, clean_title_for_search
+from utils.error_utils import format_year_mismatch, format_doi_mismatch
 from config.settings import get_config
 
 # Set up logging
@@ -448,7 +449,7 @@ class OpenAlexReferenceChecker:
         if year and work_year and year != work_year:
             errors.append({
                 'warning_type': 'year',
-                'warning_details': f"Year mismatch: cited as {year} but actually {work_year}",
+                'warning_details': format_year_mismatch(year, work_year),
                 'ref_year_correct': work_year
             })
         
@@ -458,14 +459,12 @@ class OpenAlexReferenceChecker:
             work_doi = work_data['ids']['doi']
         
         if doi and work_doi:
-            # Normalize DOIs for comparison (remove URL prefix and trailing periods)
-            cited_doi_clean = doi.replace('https://doi.org/', '').replace('http://doi.org/', '').strip().rstrip('.')
-            work_doi_clean = work_doi.replace('https://doi.org/', '').replace('http://doi.org/', '').strip().rstrip('.')
-            
-            if cited_doi_clean.lower() != work_doi_clean.lower():
+            # Compare DOIs using the proper comparison function
+            from utils.doi_utils import compare_dois
+            if not compare_dois(doi, work_doi):
                 errors.append({
                     'error_type': 'doi',
-                    'error_details': f"DOI mismatch: cited as {doi} but actually {work_doi}",
+                    'error_details': format_doi_mismatch(doi, work_doi),
                     'ref_doi_correct': work_doi
                 })
         

checkers/openreview_checker.py

@@ -425,9 +425,11 @@ class OpenReviewReferenceChecker:
         if cited_title and paper_title:
             similarity = calculate_title_similarity(cited_title, paper_title)
             if similarity < 0.7:  # Using a reasonable threshold
+                from utils.error_utils import format_title_mismatch
+                details = format_title_mismatch(cited_title, paper_title) + f" (similarity: {similarity:.2f})"
                 errors.append({
                     "warning_type": "title",
-                    "warning_details": f"Title mismatch: cited as '{cited_title}' but OpenReview shows '{paper_title}' (similarity: {similarity:.2f})"
+                    "warning_details": details
                 })
         
         # Check authors
@@ -460,9 +462,10 @@ class OpenReviewReferenceChecker:
                 
                 is_different, year_message = is_year_substantially_different(cited_year_int, paper_year_int)
                 if is_different and year_message:
+                    from utils.error_utils import format_year_mismatch
                     errors.append({
                         "warning_type": "year",
-                        "warning_details": year_message
+                        "warning_details": format_year_mismatch(cited_year_int, paper_year_int)
                     })
             except (ValueError, TypeError):
                 pass  # Skip year validation if conversion fails
@@ -473,10 +476,10 @@ class OpenReviewReferenceChecker:
         
         if cited_venue and paper_venue:
             if are_venues_substantially_different(cited_venue, paper_venue):
-                from utils.error_utils import clean_venue_for_comparison
+                from utils.error_utils import format_venue_mismatch
                 errors.append({
                     "warning_type": "venue",
-                    "warning_details": f"Venue mismatch: cited as '{clean_venue_for_comparison(cited_venue)}' but OpenReview shows '{clean_venue_for_comparison(paper_venue)}'"
+                    "warning_details": format_venue_mismatch(cited_venue, paper_venue)
                 })
         
         # Create verified data structure

checkers/semantic_scholar.py

@@ -29,6 +29,7 @@ import logging
 import re
 from typing import Dict, List, Tuple, Optional, Any, Union
 from utils.text_utils import normalize_text, clean_title_basic, find_best_match, is_name_match, are_venues_substantially_different, calculate_title_similarity, compare_authors, clean_title_for_search
+from utils.error_utils import format_title_mismatch
 from config.settings import get_config
 
 # Set up logging
@@ -471,7 +472,7 @@ class NonArxivReferenceChecker:
         if found_title and title_similarity < SIMILARITY_THRESHOLD:
             errors.append({
                 'error_type': 'title',
-                'error_details': f"Title mismatch: cited as '{title}' but actually '{found_title}'",
+                'error_details': format_title_mismatch(title, found_title),
                 'ref_title_correct': paper_data.get('title', '')
             })
         
@@ -525,9 +526,10 @@ class NonArxivReferenceChecker:
             is_different, warning_message = is_year_substantially_different(year, paper_year, context)
             
             if is_different and warning_message:
+                from utils.error_utils import format_year_mismatch
                 errors.append({
                     'warning_type': 'year',
-                    'warning_details': warning_message,
+                    'warning_details': format_year_mismatch(year, paper_year),
                     'ref_year_correct': paper_year
                 })
         
@@ -541,49 +543,50 @@ class NonArxivReferenceChecker:
         elif paper_venue and not isinstance(paper_venue, str):
             paper_venue = str(paper_venue)
         
+        # Check venue mismatches
         if cited_venue and paper_venue:
             # Use the utility function to check if venues are substantially different
             if are_venues_substantially_different(cited_venue, paper_venue):
                 from utils.error_utils import create_venue_warning
                 errors.append(create_venue_warning(cited_venue, paper_venue))
         elif not cited_venue and paper_venue:
-            # Check if this is an arXiv paper first
-            external_ids = paper_data.get('externalIds', {})
-            arxiv_id = external_ids.get('ArXiv') if external_ids else None
-            
-            if arxiv_id:
-                # For arXiv papers, suggest including the arXiv URL instead of venue
-                arxiv_url = f"https://arxiv.org/abs/{arxiv_id}"
-                
-                # Check if the reference already includes this ArXiv URL or equivalent DOI
-                reference_url = reference.get('url', '')
-                
-                # Check for direct arXiv URL match
-                has_arxiv_url = arxiv_url in reference_url
-                
-                # Also check for arXiv DOI URL (e.g., https://doi.org/10.48550/arxiv.2505.11595)
-                arxiv_doi_url = f"https://doi.org/10.48550/arxiv.{arxiv_id}"
-                has_arxiv_doi = arxiv_doi_url.lower() in reference_url.lower()
-                
-                if not (has_arxiv_url or has_arxiv_doi):
+            # Original reference has the venue in raw text but not parsed correctly
+            raw_text = reference.get('raw_text', '')
+            if raw_text and '#' in raw_text:
+                # Check if venue might be in the raw text format (author#title#venue#year#url)
+                parts = raw_text.split('#')
+                if len(parts) >= 3 and parts[2].strip():
+                    # Venue is present in raw text but missing from parsed reference
                     errors.append({
                         'warning_type': 'venue',
-                        'warning_details': f"Reference should include arXiv URL: {arxiv_url}",
-                        'ref_url_correct': arxiv_url
+                        'warning_details': f"Venue missing: should include '{paper_venue}'",
+                        'ref_venue_correct': paper_venue
                     })
-            else:
-                # Original reference has the venue in raw text but not parsed correctly
-                raw_text = reference.get('raw_text', '')
-                if raw_text and '#' in raw_text:
-                    # Check if venue might be in the raw text format (author#title#venue#year#url)
-                    parts = raw_text.split('#')
-                    if len(parts) >= 3 and parts[2].strip():
-                        # Venue is present in raw text but missing from parsed reference
-                        errors.append({
-                            'warning_type': 'venue',
-                            'warning_details': f"Venue missing: should include '{paper_venue}'",
-                            'ref_venue_correct': paper_venue
-                        })
+
+        # Always check for missing arXiv URLs when paper has arXiv ID
+        external_ids = paper_data.get('externalIds', {})
+        arxiv_id = external_ids.get('ArXiv') if external_ids else None
+        
+        if arxiv_id:
+            # For arXiv papers, check if reference includes the arXiv URL
+            arxiv_url = f"https://arxiv.org/abs/{arxiv_id}"
+            
+            # Check if the reference already includes this ArXiv URL or equivalent DOI
+            reference_url = reference.get('url', '')
+            
+            # Check for direct arXiv URL match
+            has_arxiv_url = arxiv_url in reference_url
+            
+            # Also check for arXiv DOI URL (e.g., https://doi.org/10.48550/arxiv.2505.11595)
+            arxiv_doi_url = f"https://doi.org/10.48550/arxiv.{arxiv_id}"
+            has_arxiv_doi = arxiv_doi_url.lower() in reference_url.lower()
+            
+            if not (has_arxiv_url or has_arxiv_doi):
+                errors.append({
+                    'warning_type': 'url',
+                    'warning_details': f"Reference could include arXiv URL: {arxiv_url}",
+                    'ref_url_correct': arxiv_url
+                })
 
         # Verify DOI
         paper_doi = None
@@ -591,14 +594,13 @@ class NonArxivReferenceChecker:
         if external_ids and 'DOI' in external_ids:
             paper_doi = external_ids['DOI']
             
-            # Compare DOIs, but strip hash fragments and trailing periods for comparison
-            cited_doi_clean = doi.split('#')[0].rstrip('.') if doi else ''
-            paper_doi_clean = paper_doi.split('#')[0].rstrip('.') if paper_doi else ''
-            
-            if cited_doi_clean and paper_doi_clean and cited_doi_clean.lower() != paper_doi_clean.lower():
+            # Compare DOIs using the proper comparison function
+            from utils.doi_utils import compare_dois
+            if doi and paper_doi and not compare_dois(doi, paper_doi):
+                from utils.error_utils import format_doi_mismatch
                 errors.append({
                     'error_type': 'doi',
-                    'error_details': f"DOI mismatch: cited as {doi} but actually {paper_doi}",
+                    'error_details': format_doi_mismatch(doi, paper_doi),
                     'ref_doi_correct': paper_doi
                 })
         

checkers/webpage_checker.py

@@ -71,7 +71,8 @@ class WebPageChecker:
         doc_indicators = [
             'docs', 'documentation', 'readthedocs.io', 'help', 'guide', 'tutorial',
             'reference', 'manual', 'wiki', 'blog', 'api', 'developer', 'platform',
-            'index', 'research', 'news', 'insights', 'whitepaper', 'brief', 'develop'
+            'index', 'research', 'news', 'insights', 'whitepaper', 'brief', 'develop',
+            'posts'  # For blog posts and forum posts like LessWrong
         ]
         
         return any(indicator in url.lower() for indicator in doc_indicators) or self._is_likely_webpage(url)
@@ -84,7 +85,8 @@ class WebPageChecker:
         doc_domains = [
             'pytorch.org', 'tensorflow.org', 'readthedocs.io', 'onnxruntime.ai',
             'deepspeed.ai', 'huggingface.co', 'openai.com', 'microsoft.com',
-            'google.com', 'nvidia.com', 'intel.com', 'langchain.com'
+            'google.com', 'nvidia.com', 'intel.com', 'langchain.com',
+            'lesswrong.com'  # LessWrong rationality and AI safety blog platform
         ]
         
         return any(domain in parsed.netloc for domain in doc_domains)
@@ -182,9 +184,10 @@ class WebPageChecker:
             # Check title match
             if cited_title and page_title:
                 if not self._check_title_match(cited_title, page_title, page_description):
+                    from utils.error_utils import format_title_mismatch
                     errors.append({
                         "warning_type": "title",
-                        "warning_details": f"Title mismatch: cited as '{cited_title}' but page title is '{page_title}'"
+                        "warning_details": format_title_mismatch(cited_title, page_title)
                     })
             
             # Check if this is a documentation page for the cited topic
@@ -201,9 +204,13 @@ class WebPageChecker:
             if cited_authors:
                 author_str = ', '.join(cited_authors) if isinstance(cited_authors, list) else str(cited_authors)
                 if not self._check_author_match(author_str, site_info, web_url):
+                    from utils.error_utils import format_three_line_mismatch
+                    left = author_str
+                    right = site_info.get('organization', 'unknown')
+                    details = format_three_line_mismatch("Author/organization mismatch", left, right)
                     errors.append({
                         "warning_type": "author",
-                        "warning_details": f"Author/organization mismatch: cited as '{author_str}' but page is from '{site_info.get('organization', 'unknown')}'"
+                        "warning_details": details
                     })
             
             logger.debug(f"Web page verification completed for: {web_url}")
@@ -390,6 +397,14 @@ class WebPageChecker:
         organization = site_info.get('organization', '').lower()
         domain = site_info.get('domain', '').lower()
         
+        # Accept generic web resource terms - these are valid for any web URL
+        generic_web_terms = [
+            'web resource', 'web site', 'website', 'online resource', 
+            'online', 'web', 'internet resource', 'web page', 'webpage'
+        ]
+        if cited_lower in generic_web_terms:
+            return True
+        
         # Direct matches
         if cited_lower in organization or organization in cited_lower:
             return True

core/parallel_processor.py

@@ -352,12 +352,15 @@ class ParallelReferenceProcessor:
                     error_type = error.get('error_type') or error.get('warning_type')
                     error_details = error.get('error_details') or error.get('warning_details', 'Unknown error')
                     
+                    from utils.error_utils import print_labeled_multiline
+
                     if error_type == 'arxiv_id':
+                        # Keep existing style for arXiv ID errors
                         print(f"      ❌ {error_details}")
                     elif 'error_type' in error:
-                        print(f"      ❌ Error: {error_details}")
+                        print_labeled_multiline("❌ Error", error_details)
                     else:
-                        print(f"      ⚠️  Warning: {error_details}")
+                        print_labeled_multiline("⚠️  Warning", error_details)
         
         # Show timing info for slow references
         if result.processing_time > 5.0:

core/refchecker.py

@@ -1900,10 +1900,11 @@ class ArxivReferenceChecker:
             db_title = self.non_arxiv_checker.normalize_paper_title(paper_data.get('title'))
             
             if normalized_title != db_title:
+                from utils.error_utils import format_title_mismatch
                 logger.debug(f"DB Verification: Title mismatch - cited: '{title}', actual: '{paper_data.get('title')}'")
                 errors.append({
                     'error_type': 'title',
-                    'error_details': f"Title mismatch: cited as '{title}' but actually '{paper_data.get('title')}'",
+                    'error_details': format_title_mismatch(title, paper_data.get('title')),
                     'ref_title_correct': paper_data.get('title')
                 })
         
@@ -1925,30 +1926,36 @@ class ArxivReferenceChecker:
         paper_year = paper_data.get('year')
         if year and paper_year and year != paper_year:
             logger.debug(f"DB Verification: Year mismatch - cited: {year}, actual: {paper_year}")
+            from utils.error_utils import format_year_mismatch
             errors.append({
                 'warning_type': 'year',
-                'warning_details': f"Year mismatch: cited as {year} but actually {paper_year}",
+                'warning_details': format_year_mismatch(year, paper_year),
                 'ref_year_correct': paper_year
             })
         
         # Verify DOI
-        if doi and external_ids.get('DOI') and doi.lower() != external_ids['DOI'].lower():
-            # Check if the cited DOI is a partial match of the actual DOI
-            # This handles cases like "10.1111/j.2044-8260." vs "10.1111/J.2044-8260.1997.TB01237.X"
-            cited_doi_clean = doi.lower().rstrip('.')
-            actual_doi_clean = external_ids['DOI'].lower().rstrip('.')
-            
-            # If the cited DOI is a prefix of the actual DOI, it's likely a partial citation
-            # Only flag as error if it's not a reasonable partial match
-            if not actual_doi_clean.startswith(cited_doi_clean):
-                logger.debug(f"DB Verification: DOI mismatch - cited: {doi}, actual: {external_ids['DOI']}")
-                errors.append({
-                    'error_type': 'doi',
-                    'error_details': f"DOI mismatch: cited as {doi} but actually {external_ids['DOI']}",
-                    'ref_doi_correct': external_ids['DOI']
-                })
-            else:
-                logger.debug(f"DB Verification: DOI partial match - cited: {doi}, actual: {external_ids['DOI']} (acceptable)")
+        if doi and external_ids.get('DOI'):
+            from utils.doi_utils import compare_dois, normalize_doi
+            
+            # Use proper DOI comparison first
+            if not compare_dois(doi, external_ids['DOI']):
+                # Check if the cited DOI is a partial match of the actual DOI
+                # This handles cases like "10.1111/j.2044-8260." vs "10.1111/J.2044-8260.1997.TB01237.X"
+                cited_doi_normalized = normalize_doi(doi)
+                actual_doi_normalized = normalize_doi(external_ids['DOI'])
+                
+                # If the cited DOI is a prefix of the actual DOI, it's likely a partial citation
+                # Only flag as error if it's not a reasonable partial match
+                if not actual_doi_normalized.startswith(cited_doi_normalized.rstrip('.')):
+                    logger.debug(f"DB Verification: DOI mismatch - cited: {doi}, actual: {external_ids['DOI']}")
+                    from utils.error_utils import format_doi_mismatch
+                    errors.append({
+                        'error_type': 'doi',
+                        'error_details': format_doi_mismatch(doi, external_ids['DOI']),
+                        'ref_doi_correct': external_ids['DOI']
+                    })
+                else:
+                    logger.debug(f"DB Verification: DOI partial match - cited: {doi}, actual: {external_ids['DOI']} (acceptable)")
 
         # Verify ArXiv ID
         if reference.get('type') == 'arxiv':
@@ -3489,8 +3496,9 @@ class ArxivReferenceChecker:
         author_field_match = re.search(r'\\bibfield\{author\}\{(.*?)\}(?:\s*\\bibinfo\{year\}|\s*\\newblock|$)', content, re.DOTALL)
         if author_field_match:
             author_content = author_field_match.group(1)
-            # Find all \bibinfo{person}{Name} entries
-            person_matches = re.findall(r'\\bibinfo\{person\}\{([^}]+)\}', author_content)
+            # Find all \bibinfo{person}{Name} entries using balanced brace extraction
+            from utils.text_utils import extract_bibinfo_person_content
+            person_matches = extract_bibinfo_person_content(author_content)
             if person_matches:
                 authors = []
                 for person in person_matches:
@@ -3502,33 +3510,31 @@ class ArxivReferenceChecker:
                         authors.append(clean_name)
                 ref['authors'] = authors
         
-        # Extract title from \bibinfo{title}{Title}
-        title_match = re.search(r'\\bibinfo\{title\}\{([^}]+)\}', content)
-        if title_match:
-            title = strip_latex_commands(title_match.group(1)).strip()
+        # Import balanced brace extraction function
+        from utils.text_utils import extract_bibinfo_field_content
+        
+        # Extract title from \bibinfo{title}{Title} using balanced brace extraction
+        title_content = extract_bibinfo_field_content(content, 'title')
+        if title_content:
+            title = strip_latex_commands(title_content).strip()
             ref['title'] = title
         
-        # Extract venue/journal from various fields
-        venue_patterns = [
-            r'\\bibinfo\{booktitle\}\{([^}]+)\}',
-            r'\\bibinfo\{journal\}\{([^}]+)\}',
-            r'\\bibinfo\{series\}\{([^}]+)\}',
-            r'\\bibinfo\{note\}\{([^}]+)\}'
-        ]
+        # Extract venue/journal from various fields using balanced brace extraction
+        venue_field_types = ['booktitle', 'journal', 'series', 'note']
         
-        for pattern in venue_patterns:
-            venue_match = re.search(pattern, content)
-            if venue_match:
-                venue = strip_latex_commands(venue_match.group(1)).strip()
+        for field_type in venue_field_types:
+            venue_content = extract_bibinfo_field_content(content, field_type)
+            if venue_content:
+                venue = strip_latex_commands(venue_content).strip()
                 if venue:
                     ref['venue'] = venue
                     ref['journal'] = venue  # For compatibility
                     break
         
-        # Extract DOI
-        doi_match = re.search(r'\\bibinfo\{doi\}\{([^}]+)\}', content)
-        if doi_match:
-            ref['doi'] = doi_match.group(1).strip()
+        # Extract DOI using balanced brace extraction
+        doi_content = extract_bibinfo_field_content(content, 'doi')
+        if doi_content:
+            ref['doi'] = doi_content.strip()
         
         # Extract ArXiv ID from \showeprint[arxiv]{ID}
         arxiv_match = re.search(r'\\showeprint\[arxiv\]\{([^}]+)\}', content)
@@ -5048,7 +5054,8 @@ class ArxivReferenceChecker:
             correct_first = correct_authors[0]
             
             if not enhanced_name_match(cited_first, correct_first):
-                return False, f"First author mismatch: '{cited_first}' vs '{correct_first}'"
+                from utils.error_utils import format_first_author_mismatch
+                return False, format_first_author_mismatch(cited_first, correct_first)
         
         return True, "Authors match"
     
@@ -5454,12 +5461,14 @@ class ArxivReferenceChecker:
                     error_type = error.get('error_type') or error.get('warning_type')
                     error_details = error.get('error_details') or error.get('warning_details', 'Unknown error')
                     
+                    from utils.error_utils import print_labeled_multiline
+
                     if error_type == 'arxiv_id':
                         print(f"      ❌ {error_details}")
                     elif 'error_type' in error:
-                        print(f"      ❌ Error: {error_details}")
+                        print_labeled_multiline("❌ Error", error_details)
                     else:
-                        print(f"      ⚠️  Warning: {error_details}")
+                        print_labeled_multiline("⚠️  Warning", error_details)
 
     def _output_reference_errors(self, reference, errors, url):
         """

utils/arxiv_utils.py

@@ -392,32 +392,29 @@ def get_bibtex_content(paper):
         logger.debug(f"Detected ArXiv paper {arxiv_id}, checking for structured bibliography")
         tex_content, bib_content, bbl_content = download_arxiv_source(arxiv_id)
         
-        # Choose between .bib and .bbl files based on content richness
-        # Prioritize .bbl if it has more references than filtered .bib, otherwise prefer .bib
+        # Choose between .bib and .bbl files - .bbl files take priority when they contain entries
+        # .bbl files are processed biblatex output that reflects exactly what was cited
         if bib_content and bbl_content:
-            # Count entries in both
+            # Count entries in both for logging
             bib_entry_count = len(re.findall(r'@\w+\s*\{', bib_content))
             bbl_entry_count = len(re.findall(r'\\bibitem\[', bbl_content))
             
-            # If we have LaTeX content, get filtered BibTeX count
-            filtered_bib_count = bib_entry_count
-            filtered_content = bib_content
-            if tex_content:
-                cited_keys = extract_cited_keys_from_tex({}, tex_content)
-                if cited_keys:
-                    logger.debug(f"Found {len(cited_keys)} cited keys, filtering BibTeX")
-                    filtered_content = filter_bibtex_by_citations(bib_content, {}, tex_content)
-                    filtered_bib_count = len(re.findall(r'@\w+\s*\{', filtered_content))
-            
-            logger.debug(f"Bibliography comparison: .bbl has {bbl_entry_count} entries, filtered .bib has {filtered_bib_count} entries")
+            logger.debug(f"Bibliography comparison: .bbl has {bbl_entry_count} entries, .bib has {bib_entry_count} entries")
             
-            # Prioritize .bbl if it has significantly more entries
-            if bbl_entry_count > filtered_bib_count * 1.5:  # 50% more entries threshold
-                logger.info(f"Using .bbl files from ArXiv source")
+            # Only use .bbl if it actually contains bibliography entries
+            if bbl_entry_count > 0:
+                logger.info(f"Using .bbl files from ArXiv source (biblatex takes priority over bibtex)")
                 return bbl_content
             else:
-                logger.info(f"Using filtered .bib files")
-                return filtered_content
+                logger.info(f"Using .bib files from ArXiv source (.bbl file is empty)")
+                # If we have LaTeX content, filter BibTeX by cited keys
+                if tex_content:
+                    cited_keys = extract_cited_keys_from_tex({}, tex_content)
+                    if cited_keys:
+                        logger.debug(f"Found {len(cited_keys)} cited keys, filtering BibTeX")
+                        filtered_content = filter_bibtex_by_citations(bib_content, {}, tex_content)
+                        return filtered_content
+                return bib_content
                     
         elif bib_content:
             logger.info(f"Found .bib files in ArXiv source for {arxiv_id}")

utils/doi_utils.py

@@ -99,6 +99,10 @@ def compare_dois(doi1: str, doi2: str) -> bool:
     """
     Compare two DOIs for equality, handling different formats and prefixes.
     
+    This function performs exact matching after normalization, which means
+    DOIs are only considered equal if they are identical after removing
+    prefixes, case differences, and punctuation.
+    
     Args:
         doi1: First DOI to compare
         doi2: Second DOI to compare
@@ -109,21 +113,11 @@ def compare_dois(doi1: str, doi2: str) -> bool:
     if not doi1 or not doi2:
         return False
     
-    # Normalize both DOIs (already converted to lowercase)
+    # Normalize both DOIs (handles prefixes, case, punctuation)
     norm_doi1 = normalize_doi(doi1)
     norm_doi2 = normalize_doi(doi2)
 
-    # If DOIs are identical, they match
-    if norm_doi1 == norm_doi2:
-        return True
-
-    # Check if first two components match (publisher.registrant)
-    doi1_parts = norm_doi1.split('.')
-    doi2_parts = norm_doi2.split('.')
-
-    if len(doi1_parts) >= 2 and len(doi2_parts) >= 2:
-        return doi1_parts[0] == doi2_parts[0] and doi1_parts[1].split('/')[0] == doi2_parts[1].split('/')[0]
-    
+    # DOIs must be exactly identical after normalization
     return norm_doi1 == norm_doi2
 
 

utils/error_utils.py

@@ -9,6 +9,86 @@ for reference checkers.
 from typing import Dict, List, Any, Optional
 
 
+def print_labeled_multiline(label: str, text: str) -> None:
+    """
+    Print a multi-line message with consistent label formatting.
+    
+    This function ensures consistent indentation for all error and warning messages,
+    regardless of emoji width differences in the labels.
+    
+    Args:
+        label: The label (e.g., "❌ Error", "⚠️  Warning")
+        text: The multi-line text to print
+    """
+    prefix = f"      {label}: "
+    lines = (text or "").splitlines() or [""]
+    
+    # Print the first line with the label prefix
+    print(prefix + lines[0])
+    
+    # Print subsequent lines with fixed indentation to ensure consistency
+    # Use fixed 19-character indentation to align regardless of emoji width
+    fixed_indent = " " * 15
+    for line in lines[1:]:
+        print(fixed_indent + line)
+
+
+def format_three_line_mismatch(mismatch_type: str, left: str, right: str) -> str:
+    """
+    Format a three-line mismatch message with fixed indentation.
+
+    This creates a clean, consistently formatted mismatch message that separates
+    the mismatch type from the values being compared:
+
+    Example:
+    Title mismatch:
+        'Cited Title'
+    vs: 'Correct Title'
+
+    Args:
+        mismatch_type: The type of mismatch (e.g., "Author 2 mismatch", "Title mismatch")
+        left: The cited/incorrect value
+        right: The correct value
+
+    Returns:
+        Three-line formatted mismatch message
+    """
+    # Ensure mismatch_type ends with a colon
+    if not mismatch_type.endswith(":"):
+        mismatch_type = mismatch_type.rstrip() + ":"
+    
+    # Use fixed indentation for clean, consistent alignment
+    indent = ""  # spaces for content indentation
+    vs_indent = ""   # vs: starts at column 0 for clear visual separation
+    
+    return f"{mismatch_type}\n{indent}cited:  '{left}'\n{vs_indent}actual: '{right}'"
+
+
+def format_title_mismatch(cited_title: str, verified_title: str) -> str:
+    """
+    Format a three-line title mismatch message.
+
+    Output format:
+    Title mismatch:
+        'Cited Title'
+    vs: 'Correct Title'
+    """
+    return format_three_line_mismatch("Title mismatch", cited_title, verified_title)
+
+
+def format_year_mismatch(cited_year: int | str, correct_year: int | str) -> str:
+    """
+    Three-line year mismatch message.
+    """
+    return format_three_line_mismatch("Year mismatch", str(cited_year), str(correct_year))
+
+
+def format_doi_mismatch(cited_doi: str, correct_doi: str) -> str:
+    """
+    Three-line DOI mismatch message.
+    """
+    return format_three_line_mismatch("DOI mismatch", str(cited_doi), str(correct_doi))
+
 def create_author_error(error_details: str, correct_authors: List[Dict[str, str]]) -> Dict[str, str]:
     """
     Create a standardized author error dictionary.
@@ -40,7 +120,7 @@ def create_year_warning(cited_year: int, correct_year: int) -> Dict[str, Any]:
     """
     return {
         'warning_type': 'year',
-        'warning_details': f"Year mismatch: cited as {cited_year} but actually {correct_year}",
+        'warning_details': format_year_mismatch(cited_year, correct_year),
         'ref_year_correct': correct_year
     }
 
@@ -64,7 +144,7 @@ def create_doi_error(cited_doi: str, correct_doi: str) -> Optional[Dict[str, str
     if cited_doi_clean != correct_doi_clean:
         return {
             'error_type': 'doi',
-            'error_details': f"DOI mismatch: cited as {cited_doi} but actually {correct_doi}",
+            'error_details': format_doi_mismatch(cited_doi, correct_doi),
             'ref_doi_correct': correct_doi
         }
     
@@ -120,11 +200,20 @@ def create_venue_warning(cited_venue: str, correct_venue: str) -> Dict[str, str]
     
     return {
         'warning_type': 'venue',
-        'warning_details': f"Venue mismatch: cited as '{clean_cited}' but actually '{clean_correct}'",
+        'warning_details': format_three_line_mismatch("Venue mismatch", clean_cited, clean_correct),
         'ref_venue_correct': correct_venue
     }
 
 
+def format_venue_mismatch(cited_venue: str, verified_venue: str) -> str:
+    """
+    Format a three-line venue mismatch message with cleaned venue names.
+    """
+    clean_cited = clean_venue_for_comparison(cited_venue)
+    clean_verified = clean_venue_for_comparison(verified_venue)
+    return format_three_line_mismatch("Venue mismatch", clean_cited, clean_verified)
+
+
 def create_url_error(error_details: str, correct_url: Optional[str] = None) -> Dict[str, str]:
     """
     Create a standardized URL error dictionary.
@@ -189,6 +278,59 @@ def create_generic_warning(warning_type: str, warning_details: str, **kwargs) ->
     return warning_dict
 
 
+def format_author_mismatch(author_number: int, cited_author: str, correct_author: str) -> str:
+    """
+    Format a three-line author mismatch message.
+    
+    Args:
+        author_number: The author position (1-based)
+        cited_author: The cited author name
+        correct_author: The correct author name
+        
+    Returns:
+        Formatted three-line author mismatch message
+    """
+    return format_three_line_mismatch(f"Author {author_number} mismatch", cited_author, correct_author)
+
+
+def format_first_author_mismatch(cited_author: str, correct_author: str) -> str:
+    """
+    Format a three-line first author mismatch message.
+    
+    Args:
+        cited_author: The cited first author name
+        correct_author: The correct first author name
+        
+    Returns:
+        Formatted three-line first author mismatch message
+    """
+    return format_three_line_mismatch("First author mismatch", cited_author, correct_author)
+
+
+def format_author_count_mismatch(cited_count: int, correct_count: int, cited_authors: list, correct_authors: list) -> str:
+    """
+    Format an author count mismatch message showing all cited and correct authors.
+    
+    Args:
+        cited_count: Number of cited authors
+        correct_count: Number of correct authors  
+        cited_authors: List of cited author names
+        correct_authors: List of correct author names
+        
+    Returns:
+        Formatted multi-line author count mismatch message
+    """
+    # Create the header with count information
+    header = f"Author count mismatch: {cited_count} cited vs {correct_count} correct"
+    
+    # Format author lists
+    cited_list = ", ".join(cited_authors) if cited_authors else "None"
+    correct_list = ", ".join(correct_authors) if correct_authors else "None"
+    
+    # Use the same format as other mismatches
+    return format_three_line_mismatch(header, cited_list, correct_list)
+
+
 def format_authors_list(authors: List[Dict[str, str]]) -> str:
     """
     Format a list of author dictionaries into a readable string.

utils/text_utils.py

@@ -554,6 +554,10 @@ def clean_title_basic(title):
     # Remove trailing punctuation
     title = re.sub(r'[.,;:]+$', '', title)
     
+    # Remove BibTeX publication type indicators at the end (common in Chinese and some international BibTeX styles)
+    # [J] = Journal, [C] = Conference, [M] = Monograph/Book, [D] = Dissertation, [P] = Patent, [R] = Report
+    title = re.sub(r'\s*\[[JCMDPRS]\]\s*$', '', title)
+    
     return title
 
 
@@ -578,6 +582,9 @@ def clean_title_for_search(title):
     title = title.replace('\n', ' ').strip()
     title = re.sub(r'\s+', ' ', title)  # Normalize whitespace only
     
+    # Remove BibTeX publication type indicators that are not part of the actual title
+    title = re.sub(r'\s*\[[JCMDPRS]\]\s*$', '', title)
+    
     # Note: We intentionally preserve:
     # - Capitalization (helps with exact matching)
     # - Colons and other meaningful punctuation (structural markers)
@@ -2076,6 +2083,8 @@ def compare_authors(cited_authors: list, correct_authors: list, normalize_func=N
     # The key insight: if the citation has "et al", we should only verify the listed authors
     # and not penalize for the authoritative source having more authors
     if has_et_al:
+        # Import here to avoid circular imports
+        from utils.error_utils import format_author_mismatch
         # For et al cases, check if each cited author matches ANY author in the correct list
         # rather than comparing positionally, since author order can vary
         for i, cited_author in enumerate(cleaned_cited):
@@ -2088,10 +2097,11 @@ def compare_authors(cited_authors: list, correct_authors: list, normalize_func=N
                     break
             
             if not author_found:
-                # Create a more informative error message that doesn't assume positional matching
-                # Show the full list of correct authors instead of truncating
+                # Use standardized three-line formatting for author mismatch
+                cited_display = format_author_for_display(cited_author)
                 full_author_list = ', '.join(correct_names)
-                return False, f"Author {i+1} mismatch: '{cited_author}' not found in author list (et al case). Correct authors include: {full_author_list}"
+                error_msg = format_author_mismatch(i+1, f"{cited_display} (not found in author list - et al case)", f"Correct authors: {full_author_list}")
+                return False, error_msg
         
         return True, f"Authors match (verified {len(cleaned_cited)} of {len(correct_names)} with et al)"
     
@@ -2100,7 +2110,11 @@ def compare_authors(cited_authors: list, correct_authors: list, normalize_func=N
         # For non-et-al cases, be more strict about count mismatches
         # Allow minor flexibility (1 author difference) but not more
         if abs(len(cleaned_cited) - len(correct_names)) > 1:
-            return False, f"Author count mismatch: {len(cleaned_cited)} cited vs {len(correct_names)} correct"
+            from utils.error_utils import format_author_count_mismatch
+            # Convert cited names to display format (First Last) before showing in error
+            display_cited = [format_author_for_display(author) for author in cleaned_cited]
+            error_msg = format_author_count_mismatch(len(cleaned_cited), len(correct_names), display_cited, correct_names)
+            return False, error_msg
         
         # Use the shorter list for comparison
         min_len = min(len(cleaned_cited), len(correct_names))
@@ -2110,6 +2124,9 @@ def compare_authors(cited_authors: list, correct_authors: list, normalize_func=N
         comparison_cited = cleaned_cited
         comparison_correct = correct_names
     
+    # Use shared three-line formatter (imported lazily to avoid circular imports)
+    from utils.error_utils import format_first_author_mismatch, format_author_mismatch
+
     # Compare first author (most important) using the enhanced name matching
     if comparison_cited and comparison_correct:
         cited_first = comparison_cited[0]
@@ -2119,7 +2136,7 @@ def compare_authors(cited_authors: list, correct_authors: list, normalize_func=N
             # Use consistent display format for both names
             cited_display = format_author_for_display(cited_first)
             correct_display = format_author_for_display(correct_first)
-            return False, f"First author mismatch: '{cited_display}' vs '{correct_display}'"
+            return False, format_first_author_mismatch(cited_display, correct_display)
     
     # For complete verification, check all authors if reasonable number
     if len(comparison_cited) <= 5:  # Only do full check for reasonable author counts
@@ -2128,7 +2145,7 @@ def compare_authors(cited_authors: list, correct_authors: list, normalize_func=N
                 # Use consistent display format for both names
                 cited_display = format_author_for_display(cited_author)
                 correct_display = format_author_for_display(correct_author)
-                return False, f"Author {i+1} mismatch: '{cited_display}' vs '{correct_display}'"
+                return False, format_author_mismatch(i+1, cited_display, correct_display)
     
     return True, "Authors match"
 
@@ -2512,6 +2529,97 @@ def strip_latex_commands(text):
     return text
 
 
+def extract_balanced_braces(text, start_pos):
+    """
+    Extract content from balanced braces starting at start_pos.
+    
+    This function properly handles nested braces, which is important for LaTeX content
+    where patterns like {Jos{\'e} Meseguer} need to be extracted as complete units.
+    
+    Args:
+        text: The text to search in
+        start_pos: Position of the opening brace
+        
+    Returns:
+        tuple: (content, end_pos) or (None, start_pos) if no balanced content found
+    """
+    if start_pos >= len(text) or text[start_pos] != '{':
+        return None, start_pos
+    
+    brace_count = 1
+    pos = start_pos + 1
+    
+    while pos < len(text) and brace_count > 0:
+        if text[pos] == '{':
+            brace_count += 1
+        elif text[pos] == '}':
+            brace_count -= 1
+        pos += 1
+    
+    if brace_count == 0:
+        return text[start_pos + 1:pos - 1], pos
+    else:
+        return None, start_pos
+
+
+def extract_bibinfo_person_content(text):
+    """
+    Extract all person names from \\bibinfo{person}{...} with proper brace handling.
+    
+    This function correctly handles nested braces in author names, such as:
+    \\bibinfo{person}{Jos{\\'e} Meseguer}
+    
+    Args:
+        text: Text containing \\bibinfo{person}{...} patterns
+        
+    Returns:
+        list: List of extracted person names with balanced braces preserved
+    """
+    return extract_bibinfo_field_content(text, 'person', return_all=True)
+
+
+def extract_bibinfo_field_content(text, field_type, return_all=False):
+    """
+    Extract content from \\bibinfo{field_type}{...} with proper brace handling.
+    
+    This function correctly handles nested braces in field content, such as:
+    \\bibinfo{journal}{\\emph{Commun. ACM}}
+    
+    Args:
+        text: Text containing \\bibinfo{field_type}{...} patterns
+        field_type: The field type to extract (e.g., 'person', 'journal', 'title')
+        return_all: If True, return list of all matches; if False, return first match or None
+        
+    Returns:
+        list or str or None: Extracted content based on return_all parameter
+    """
+    pattern = f'\\\\bibinfo\\{{{re.escape(field_type)}\\}}\\{{'
+    matches = []
+    pos = 0
+    
+    while True:
+        match = re.search(pattern, text[pos:])
+        if not match:
+            break
+        
+        # Find the start of the content braces
+        brace_start = pos + match.end() - 1  # -1 because we want the opening brace
+        content, end_pos = extract_balanced_braces(text, brace_start)
+        
+        if content is not None:
+            matches.append(content)
+            pos = end_pos
+            if not return_all:
+                break  # Return first match only
+        else:
+            pos += match.end()
+    
+    if return_all:
+        return matches
+    else:
+        return matches[0] if matches else None
+
+
 def extract_cited_keys_from_latex(tex_content):
     r"""
     Extract citation keys from LaTeX content by finding \cite{} commands.
@@ -2936,8 +3044,8 @@ def extract_latex_references(text, file_path=None):  # pylint: disable=unused-ar
                     
                     if brace_count == 0:
                         author_content = content[start_pos:pos-1]
-                        # Extract individual authors from \bibinfo{person}{Name} tags
-                        person_matches = re.findall(r'\\bibinfo\{person\}\{([^}]+)\}', author_content)
+                        # Extract individual authors from \bibinfo{person}{Name} tags using balanced brace extraction
+                        person_matches = extract_bibinfo_person_content(author_content)
                         if person_matches:
                             # Clean and format author names
                             authors = []