BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:CIDeR-ML General Meeting
DTSTART:20260515T000000Z
DTEND:20260516T024500Z
DTSTAMP:20260628T001300Z
UID:indico-event-10554@indico.slac.stanford.edu
DESCRIPTION:https://u-tokyo-ac-jp.zoom.us/j/83932834349Minutes:\n\nQuick r
 ecap\nThis meeting was a project update session where team members present
 ed their current work progress. Tituan shared improvements to his siren mo
 del training\, including the creation of a 3D lookup table for PMT accepta
 nce correction and addressing overfitting issues through second derivative
  corrections. Omar reported merging Refactor V2 with production codes and 
 adding neutrino telescope functionality to Lucid. Riya discussed working o
 n systematically fixing gradient problems in the Lucid code. Ryotaro provi
 ded an update on focusing on the ADD dataset from the Rio de Janeiro exper
 iment. Yifan presented progress on addressing BDX distribution biasing iss
 ues and setting up losses for multiple events. Zhenxiong updated the team 
 on code repository updates\, validation work\, and running the calibration
  pipeline with COSMIC data. The conversation ended with Kazuhiro agreeing 
 to chair next week's Super K meeting.\nNext steps\n\nKazuhiro: Chair and s
 hare the meeting next week in Patrick's absence.\nOmar: Run the notebooks 
 again and clean up documentation and functions before finalizing the merge
  to main branch.\nRiya: Continue systematically addressing the Lucid code 
 gradient problem as discussed with Omar.\nRyotaro: Continue checking and a
 nalyzing the LED experimental dataset.\nTitouan: Investigate ways to reduc
 e model runtime\nYifan: Continue working on resolving memory-related issue
 s in the current model implementation.\nZhenxiong: Perform validation to e
 nsure the new code in the branch does not impact previous training and cal
 ibration\, then split changes into separate pull requests for each feature
  and submit for review.\nZhenxiong: Check the status of reconstructed vari
 ables and performance on real data before proceeding with siren tuning.\n\
 nSummary\npmtSIREN Model Training Progress Updates\nTitouan presented upda
 tes on his model training progress\, focusing on improving performance usi
 ng a 3D lookup table for PMT acceptance correction. He addressed overfitti
 ng issues by implementing a correction based on the second derivative and 
 shared the resulting model performance. He also discussed runtime analysis
  of his model\, noting that while 80 milliseconds is acceptable\, it is sl
 ightly higher than Nahuel's waterSIREN.\nLUCiD Refactor-V2 Production Merg
 e Update\nOmar reported that he merged Refactor V2 with Cesar's production
  code branch\, making it close to becoming the main branch. The remaining 
 work includes running notebooks and cleaning up documentation and function
 s. Omar also mentioned adding a new mode for neutrino telescopes\, includi
 ng Ice Cube functionality in Lucid\, which will be merged soon. Riya expre
 ssed interest in learning more about this new feature.\nMie Scattering Gra
 dient Fix Progress Update and LEDs\nRiya reported working on systematicall
 y changing code to fix a gradient problem in the Lucid codebase following 
 a discussion with Omar. Ryotaro indicated no progress on LED implementatio
 n but is focusing on experimental data for the Rio de Janeiro dataset.\ndE
 /dx Distribution Biasing Updates\nYifan discussed updates on addressing dE
 /dx distribution biasing issues and implementing changes to propagate and 
 collapse distribution after the recombination stage. They are also working
  on setting up loss functions for multiple events and dealing with memory-
 related challenges.\nOpticSIREN\nZhenxiong updated the code repository wit
 h a new branch and plans to validate recent changes while running the cali
 bration pipeline with COSMIC data. Patrick and Zhenxiong discussed the sta
 tus of reconstructed variables and performance testing on real data\, whic
 h had not yet been completed. Zhenxiong planned to double-check the impact
  on existing code before making a pull request\, with Patrick suggesting t
 o split the changes into separate pull requests for different features.\n
  \nKazuhiro agreed to chair next week's Super-K meeting in Patrick's abse
 nce.\n\n\nhttps://indico.slac.stanford.edu/event/10554/
URL:https://indico.slac.stanford.edu/event/10554/
END:VEVENT
END:VCALENDAR