2022-08-26 09:00:13
В самых горячих областях науки отбор текстов и сопутствующая коммуникация давно отличаются от традиционных журнальных.
Вот как это устроено на, вероятно, самой престижной конференции по машинному обучению ICLR. Открытое рецензирование практикуется там изначально, с 2013 г., и, видимо, повлияло на взлет площадки.
И, кстати, в отличие от журнальных мейджоров сходу не вижу там ничего про санкции и SDN. Интересно, как это с double-blind и тотально анонимизированными submissions работает? Штука-то весьма американская, при этом те же Сколтех и Физтех туда очень хотят подаваться.
Reviewing Process
Submissions to ICLR are uploaded on OpenReview, which enables public discussion. Official reviews are anonymous and publicly visible. During the public discussion phase, anybody who is logged in can post comments that are publicly visible, or restrict visibility to reviewers and up, ACs and up, or just PCs. In addition, the author of a comment can decide to post anonymously or not. Login is required before posting any comment.
Once reviews have been posted, authors are encouraged to revise their paper until the paper submission deadline. Authors can participate in the discussion about their paper, as well as about any other paper submitted to the conference, at any time.
Full reviews are posted by Nov 4. Reviews are anonymous and publicly visible in Open Review. Once the reviews are posted, authors are free to upload modifications to the paper during the discussion period.
During the discussion period, if you choose to update the submission, a pdfdiff will be applied to compare new changes to the paper against the original submission. Area chairs and reviewers reserve the right to ignore changes that are significantly different from the original paper. In addition, during this period, any submission that is cited will be given an anonymous BibTex entry.
After discussion there will be an internal discussion period amongst reviewers and ACs with the aim of summarizing the review process, after which acceptance decisions are made. Papers that are not accepted will be considered non-archival, and may be submitted elsewhere (modified or not), although the OpenReview site will maintain the reviews, the comments, and links to the versions submitted to ICLR.
All submitted papers (accepted or rejected) will be deanonymized after the notification. The submissions and reviews will be released to the public.
To allow citation of papers that are under review at ICLR2023, OpenReview provides BibTeX entries that do not list the authors, but does give the title, year and url. Author names are revealed at the end of the conference. https://iclr.cc/
508 views06:00