New author system

.github/ISSUE_TEMPLATE/02-name-correction.yml

@@ -37,8 +37,8 @@ body:
     attributes:
       label: Author ORCID
       description: |
-        Provide a valid [ORCID](https://orcid.org) link here. This will be used to help match future papers to your Anthology ID.
-      placeholder: ex. https://orcid.org/my-orcid?orcid=0009-0003-8868-7504
+        Provide a valid [ORCID](https://orcid.org) link here, and [add your name variants to your ORCID profile](https://aclanthology.org/info/orcid_id). This will be used to match papers to your Anthology ID.
+      placeholder: ex. https://orcid.org/0009-0003-8868-7504
     validations:
       required: true
   - type: textarea

.github/ISSUE_TEMPLATE/99-bulk-metadata-correction.yml

@@ -7,11 +7,11 @@ body:
   - type: markdown
     attributes:
       value: >
-        **This form is not meant to be used manually.** Instead, it is activated by clicking the yellow "Fix data" button found on each paper page in the Anthology (e.g., https://aclanthology.org/K17-1003/). Clicking this button displays a UI tool for modifying the title, abstract, and author list. Submission of that form will automatically populate the title above and data block below.
+        **Please do not edit the JSON below.** This form is not meant to be used manually; instead, it is activated by clicking the yellow "Fix data" button found on each paper page in the Anthology (e.g., https://aclanthology.org/K17-1003/). Doing so displays a UI tool for modifying the title, abstract, and author list. Submission of that form will automatically populate the title above and data block below.
   - type: markdown
     attributes:
       value: >
-        Corrections will be processed in bulk on a weekly basis after verification by Anthology staff.
+        Corrections will be manually reviewed by Anthology staff and processed in bulk on a roughly weekly basis.
   - type: textarea
     id: data
     attributes:

.github/workflows/code-quality.yml

@@ -74,6 +74,6 @@ jobs:
 
       # Coverage report
       - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}

bin/create_extra_bib.py

@@ -36,6 +36,7 @@
 import msgspec
 from pathlib import Path
 import re
+from rich.console import Console
 from rich.progress import track
 import shutil
 import subprocess
@@ -48,6 +49,7 @@
 
 BIB2XML = None
 XML2END = None
+CONSOLE = Console(stderr=True)
 
 # Max shard size in MiB
 MAX_SHARD_MB = 49
@@ -89,6 +91,7 @@ def create_bibtex(builddir, clean=False) -> None:
                 reverse=True,
             ),
             description="Create anthology.bib.gz...  ",
+            console=CONSOLE,
         ):
             with open(volume_file, "r") as f:
                 bibtex = f.read()
@@ -124,6 +127,7 @@ def create_bibtex(builddir, clean=False) -> None:
                 reverse=True,
             ),
             description="       +abstracts.bib.gz... ",
+            console=CONSOLE,
         ):
             with open(collection_file, "rb") as f:
                 data = msgspec.json.decode(f.read())
@@ -351,7 +355,7 @@ def batch_convert_to_mods_and_endf(bibtex, context):
         )
 
     log_level = log.DEBUG if args["--debug"] else log.INFO
-    tracker = setup_rich_logging(level=log_level)
+    tracker = setup_rich_logging(console=CONSOLE, level=log_level)
 
     max_workers = int(args["--max-workers"]) if args["--max-workers"] else None
     if (BIB2XML := shutil.which("bib2xml")) is None:

bin/create_hugo_data.py

@@ -39,6 +39,7 @@
 import msgspec
 from omegaconf import OmegaConf
 import os
+from rich.console import Console
 from rich.progress import (
     Progress,
     TextColumn,
@@ -52,6 +53,7 @@
 from acl_anthology.collections.paper import PaperDeletionType
 from acl_anthology.collections.volume import VolumeType
 from acl_anthology.utils.logging import setup_rich_logging
+from acl_anthology.utils.ids import is_verified_person_id
 from acl_anthology.utils.text import (
     interpret_pages,
     month_str2num,
@@ -60,6 +62,7 @@
 
 
 BIBLIMIT = None
+CONSOLE = Console(stderr=True)
 ENCODER = msgspec.json.Encoder()
 SCRIPTDIR = os.path.dirname(os.path.realpath(__file__))
 
@@ -93,7 +96,7 @@ def make_progress():
         TaskProgressColumn(show_speed=True),
         TimeRemainingColumn(elapsed_when_finished=True),
     ]
-    return Progress(*columns)
+    return Progress(*columns, console=CONSOLE)
 
 
 @cache
@@ -392,13 +395,19 @@ def export_people(anthology, builddir, dryrun):
                     )
                     if n.script is not None:
                         diff_script_variants.append(n.as_full())
-                if diff_script_variants:
+                if diff_script_variants and is_verified_person_id(person_id):
                     data["full"] = f"{data['full']} ({', '.join(diff_script_variants)})"
             if person.comment is not None:
                 data["comment"] = person.comment
+            if person.orcid is not None:
+                data["orcid"] = person.orcid
             similar = anthology.people.similar.subset(person_id)
-            if len(similar) > 1:
-                data["similar"] = list(similar - {person_id})
+            similar.remove(person_id)
+            if similar_verified := [id_ for id_ in similar if is_verified_person_id(id_)]:
+                data["similar_verified"] = sorted(list(similar_verified))
+                similar.difference_update(similar_verified)
+            if similar:  # any remaining IDs are unverified
+                data["similar_unverified"] = sorted(list(similar))
             people[person_id] = data
             progress.update(task, advance=1)
 
@@ -567,7 +576,7 @@ def export_anthology(anthology, builddir, clean=False, dryrun=False):
         )
 
     log_level = log.DEBUG if args["--debug"] else log.INFO
-    tracker = setup_rich_logging(level=log_level)
+    tracker = setup_rich_logging(console=CONSOLE, level=log_level)
 
     if limit := args["--bib-limit"]:
         BIBLIMIT = int(limit)