What this category's data looks like
For progress records and statistics verification of peer review organizations, the materials come from three types of documents: review invitations, expert review comments, and author revision notes, summarized weekly or monthly. Review invitations contain the invitation date, expert name, manuscript number, response deadline, and receipt status; expert review comments contain the comment submission date, reviewer signature, review conclusion, and revision items; author revision notes contain the revision date, point-by-point responses, author signature, and version number. When the materials enter the tool calling node, review invitations provide the time anchors for invitation issuance and receipt, expert review comments provide the comment items and signature credentials, and author revision notes provide the revision version and response items. The update rhythm is that each invitation, each comment, and each round of revision generates one record, and weekly or monthly reports are summarized by week or month. The field characteristics are five categories: date, name, quantity, signature, and version number. The verification focus is whether the name, quantity, and date of the same record can be aligned across the three materials, whether the version is synchronized, and whether the signature or receipt is complete.
Configuration and implementation checks
This step is executed by the tool calling node in the workflow (the model decides whether to call, and the node executes), outputting the tool call result (the input parameters and return in the call record). The "progress table and statistical scope description" is then completed by a subsequent AI node or manual verification. Based on the tool introduction, parameter introduction, and whether parameters are required, the model determines whether to call the tool this time; when there are no required parameters, the model may fabricate parameter values on its own, and when there are required parameters but no suitable value in the context, it may not call.
| Object | Check | Verification action |
|---|---|---|
| Review invitation | Fields, dates, and signatures: whether the invitation date, expert name, manuscript number, response deadline, and receipt status are complete | Open the tool node introduction fields and check whether the description can be understood independently; run a test with a question missing a required parameter to see whether it asks first; check the values of toolChoice and functionCall in the call record |
| Expert review comments | Fields, dates, and signatures: whether the comment submission date, reviewer signature, review conclusion, and revision items align with the invitation record | Open each parameter configuration one by one and check the parameter introduction and whether it is required; check whether the name, quantity, and date of the same manuscript number are consistent between the invitation and the comments |
| Author revision notes | Fields, dates, and signatures: whether the revision date, point-by-point responses, author signature, and version number correspond to the comment items | Check the diamond connectors and node status on the canvas; check whether the version number is synchronized and whether missing signatures or receipts are marked in the return result |
| Tool calling node connections | The diamond interface is connected to the target tool, and after multiple tools are connected in series, the results do not cross over | Check the call records of toolChoice and functionCall, confirm that input parameters and returns correspond one-to-one, and that there are no values that do not exist in the business materials |
Three common errors
- Symptom: The name, quantity, and date of the same manuscript do not match across the invitation, comments, and revision notes. Cause: The three materials are entered separately, not aligned by the same number, and the versions are not synchronized.
- Symptom: Values that do not exist in the business materials appear in the return result. Cause: When there are no required parameters, the model fabricates parameter values on its own, and the tool introduction does not specify the return scope.
- Symptom: After multiple tools are connected in series, results cross over with each other, and missing signatures or receipts are not detected. Cause: The connections and parameters are not checked item by item, and the receipt status is not constrained as a required field.
How to verify the setup
Acceptance of this feature: run a test with a question missing a required parameter, check the input parameters and return in the call record, and confirm whether it asks first or calls according to the introduction; check whether the values of toolChoice and functionCall meet expectations.
Business test: use one week of records to verify the totals and see whether the scope and exceptions are clearly stated; compare the fields, dates, and signatures of the review invitations, expert review comments, and author revision notes one by one to confirm that the record counts and statistical counts match.
- Open the tool node introduction fields and check whether the description can be understood when taken out on its own; open each parameter configuration one by one and check the introduction and whether it is required.
- Check the diamond connectors and node status on the canvas; run a test with a question missing that field to see whether it asks first rather than fabricating directly.