IBM Support

JR64053: DUPLICATED TRAINING SAMPLES LOWERING EXTRACTION MODEL ACCURACY

Subscribe to this APAR

By subscribing, you receive periodic emails alerting you to the status of the APAR, along with a link to the fix after it becomes available. You can track this item individually or track all items by product.

Notify me when this APAR changes.

Notify me when an APAR for this component changes.

 

APAR status

  • Closed as program error.

Error description

  • Duplicated training samples or training samples with high
similarity are reducing the extraction model accuracy

Local fix

  • Delete duplicate training documents and retrain

Problem summary

  • ****************************************************************
* USERS AFFECTED:                                              *
* ADP Application Developers                                   *
****************************************************************
* PROBLEM DESCRIPTION:                                         *
* Duplicate documents in ADP sample data are causing lower     *
* extraction accuracy.                                         *
****************************************************************
* RECOMMENDATION:                                              *
* Remove duplicates.                                           *
****************************************************************

Problem conclusion

  • Defect created

Temporary fix

  • 



Comments


    

  • 



APAR Information




    

  • APAR number
    JR64053
    • 

  • Reported component name
    CLOUD PAK FOR A
    • 

  • Reported component ID
    5737I2300
    • 

  • Reported release
    L00
    • 

  • Status
    CLOSED  PER
    • 

  • PE
    NoPE
    • 

  • HIPER
    NoHIPER
    • 

  • Special Attention
    NoSpecatt / Xsystem
    • 

  • Submitted date
    2021-08-11
    • 

  • Closed date
    2021-08-11
    • 

  • Last modified date
    2021-08-11
    • 





    

  • APAR is sysrouted FROM one or more of the following:
    

    • 

  • APAR is sysrouted TO one or more of the following:
    

    • 



Fix information


    

  • Fixed component name
    CLOUD PAK FOR A
    • 

  • Fixed component ID
    5737I2300
    • 



Applicable component levels


    








      
              
                            

              

              [{"Business Unit":{"code":"BU059","label":"IBM Software w\/o TPS"},"Product":{"code":"SSBYVB","label":"IBM Cloud Pak for Business Automation"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"L00","Line of Business":{"code":"LOB45","label":"Automation"}}]
              

                          

          
 
        

      

    

      

        

          

            
Document Information


            

            


                        

            Modified date:
            

            11 March 2022
            

            
                      

        


        

        


      

    

  



    

  

  
    
            

          
Page Feedback