Lorenz Official — Kaggle submission CSVs (ZOR-ND, 84.98)

[dumitrunovic-svg]

Kaggle result (Lorenz_Official)

Version	Score	File
v20	84.98	submissions/Lorenz_Kaggle/submission_lorenz_ZOR-ND_v20.csv
v16	83.40	submissions/Lorenz_Kaggle/submission_lorenz_ZOR-ND_v16_final.csv

This PR adds submission CSVs only (no model code or submodules).

Folder: submissions/Lorenz_Kaggle/

[dumitrunovic-svg]

Hi @yyexela @yuezhao6371 — friendly ping on this PR. ESN_Tuned is ready with predictions for all 9 Lorenz_Official pairs. Dev-set mean score: 35.3 (+35% vs default ESN). Related KS work in PR #20. Could you advise on review timeline and the official Kaggle submission process? Thanks!

[yyexela]

Hello @dumitrunovic-svg sorry for the late response! I'll take a look this weekend, thank you for your interest in our package:) Hopefully you were able to submit to the Kaggle without any issues!

[yyexela]

Hello @dumitrunovic-svg unfortunately this PR won't be merged. The purpose of the top-level ctf4science package is to hold data handling and evaluation scripts that can be used with individually implemented models. This PR adds CSV scores for a separate competition we hosted. We do not store evaluation results in this github repository. Thank you for understanding!

[dumitrunovic-svg]

Hi, Thank you for clarifying — I completely understand. That was my misunderstanding. Initially I thought GitHub was also the right place to share community results, but later realised that the official evaluation was handled through the Kaggle submission system. I had already submitted the solution on Kaggle a few days ago, where it received a final score of 84.97711. I understand now that the main repository is intended only for data handling and evaluation tools, not for storing evaluation results. If useful, I’m happy to share the submission CSV or adapt the contribution into a more suitable format (for example, a model implementation, discussion, or separate example). Thanks again for taking the time to review it and for the helpful feedback. [image: image.png]

…

On Sat, 30 May 2026 at 20:40, Alexey Yermakov ***@***.***> wrote: *yyexela* left a comment (CTF-for-Science/ctf4science#19) <#19 (comment)> Hello @dumitrunovic-svg <https://github.com/dumitrunovic-svg> unfortunately this PR won't be merged. The purpose of the top-level ctf4science package is to hold data handling and evaluation scripts that can be used with individually implemented models. This PR adds CSV scores for a separate competition we hosted. We do not store evaluation results in this github repository. Thank you for understanding! — Reply to this email directly, view it on GitHub <#19?email_source=notifications&email_token=BWGOIMJN34GY3365AZTUXXT45M2JDA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTINJYGQYTSMZZG4Y2M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJLDGN5XXIZLSL5RWY2LDNM#issuecomment-4584193971>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BWGOIMJPX3ML5IYNV4MBKUT45M2JDAVCNFSM6AAAAACYWV3XOKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHM2DKOBUGE4TGOJXGE> . Triage notifications, keep track of coding agent tasks and review pull requests on the go with GitHub Mobile for iOS <https://github.com/notifications/mobile/ios/BWGOIMKCSLAIFMJKWOVLI5L45M2JDA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTINJYGQYTSMZZG4Y2M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJKTGN5XXIZLSL5UW64Y> and Android <https://github.com/notifications/mobile/android/BWGOIMPQUDCQ6UHUZXN7NE345M2JDA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTINJYGQYTSMZZG4Y2M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJLTGN5XXIZLSL5QW4ZDSN5UWI>. Download it today! You are receiving this because you were mentioned.Message ID: ***@***.***>

-- B*est regards* *,Dumitru Novic* 07394357743