fix creators parsing#83
Open
slint wants to merge 3 commits into
Open
Conversation
gpt-oss-20b drops an ORCID nested under each creator in tool calls; parallel name/orcid/affiliation lists survive. Adds synthetic field examples.
A bare appended list misaligned when some authors had no ORCID; inline placement keeps each ID tied to its author.
gpt-oss fabricates 0000-0000-0000-0000 for authors with no ORCID. Filter by the ISO 7064 check digit in to_suggestions, not on the LLM output schema, since a schema error feeds back and the model invents a checksum-valid fake instead of leaving it null.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
fix(schema): flatten creators into parallel lists
gpt-oss-20b drops an ORCID nested under each creator in tool calls; parallel name/orcid/affiliation lists survive. Adds synthetic field examples.
fix(extractor): inline ORCIDs next to their author
A bare appended list misaligned when some authors had no ORCID; inline placement keeps each ID tied to its author.
fix(schema): drop ORCIDs that fail the check digit
gpt-oss fabricates 0000-0000-0000-0000 for authors with no ORCID. Filter by the ISO 7064 check digit in to_suggestions, not on the LLM output schema, since a schema error feeds back and the model invents a checksum-valid fake instead of leaving it null.