I am either missing something, or there is a bug, it seems I am being ranked not by my selected submissions but my best submission instead.
\n\nMy score should be 0.70043, but I see me at 0.70132 on the LB.
", "messages": [ { "id": 471155, "postDate": "2019-02-14T04:54:52.027Z", "content": "I am either missing something, or there is a bug, it seems I am being ranked not by my selected submissions but my best submission instead.
\n\nMy score should be 0.70043, but I see me at 0.70132 on the LB.
", "rawMarkdown": "I am either missing something, or there is a bug, it seems I am being ranked not by my selected submissions but my best submission instead.\n\nMy score should be 0.70043, but I see me at 0.70132 on the LB.\n", "votes": 14 }, { "id": 471701, "postDate": "2019-02-14T19:29:30.050Z", "content": "The score you are seeing for your selected submissions are from your Stage 1 submission. You can see the Stage 2 scoring of that submission, which is the one used for the private LB, by finding the \"Kernel Rerun for Submission\" version. The leaderboard is confirmed as correct and based only on selected submissions.
\n\nThank you for raising the issue. We recognize how this may be causing confusion and are working on an improvement to the UI.
", "rawMarkdown": "The score you are seeing for your selected submissions are from your Stage 1 submission. You can see the Stage 2 scoring of that submission, which is the one used for the private LB, by finding the \"Kernel Rerun for Submission\" version. The leaderboard is confirmed as correct and based only on selected submissions.\n\nThank you for raising the issue. We recognize how this may be causing confusion and are working on an improvement to the UI. ", "votes": 5 }, { "id": 471168, "postDate": "2019-02-14T05:25:50.587Z", "content": "@carloshuertas, your post made me check and I noticed a dsparity in mine too. I am ranked by an unselected submission with score = 0.70364 whilst my selected submission scores 0.70371, strange! They have already awarded the medals and probably the points as well?
", "rawMarkdown": "@carloshuertas, your post made me check and I noticed a dsparity in mine too. I am ranked by an unselected submission with score = 0.70364 whilst my selected submission scores 0.70371, strange! They have already awarded the medals and probably the points as well?", "votes": 3, "replies": [ { "id": 471198, "postDate": "2019-02-14T06:18:44.797Z", "content": "I don't think so, too early for that, but giving my position in the 600th I am safe of any medals :D
", "rawMarkdown": "I don't think so, too early for that, but giving my position in the 600th I am safe of any medals :D", "votes": 3 }, { "id": 471207, "postDate": "2019-02-14T06:29:46.243Z", "content": "@carloshuertas, my account shows my silver medal already and my world ranking have improved a few places but can see only a difference of 336 points in my total points.
\n\nUpdate
\n\nI just read the competition finalized post by @inversion. He confirmed in response to someone's question that they rerun our kernels with the stage-2 test which is 376k (total) = 56k (public) + 320k (private). I then checked my account again and saw my rerun kernel is shown right next to my selected kernel both with the same name but different scores. I had to sort them by scores to see them displayed next to each other. Yours may be different if you have a kernel with score that lies between your selection and the rerun.
", "rawMarkdown": "@carloshuertas, my account shows my silver medal already and my world ranking have improved a few places but can see only a difference of 336 points in my total points.\n\n**Update**\n\nI just read the [competition finalized post][1] by @inversion. He confirmed in response to someone's question that they rerun our kernels with the stage-2 test which is 376k (total) = 56k (public) + 320k (private). I then checked my account again and saw my rerun kernel is shown right next to my selected kernel both with the same name but different scores. I had to sort them by scores to see them displayed next to each other. Yours may be different if you have a kernel with score that lies between your selection and the rerun.\n\n\n [1]: https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/80511", "votes": 1 }, { "id": 471358, "postDate": "2019-02-14T10:50:32.520Z", "content": "same here! the score reflected on leaderboard is not the one I'm selected as final submission.. Weird!
", "rawMarkdown": "same here! the score reflected on leaderboard is not the one I'm selected as final submission.. Weird!", "votes": 12 } ] }, { "id": 471366, "postDate": "2019-02-14T11:03:36.073Z", "content": "@carloshuertas Agree. Same here as my score on private LB is not the selected one -> 0.70573.
", "rawMarkdown": "@carloshuertas Agree. Same here as my score on private LB is not the selected one -> 0.70573.", "votes": 1 }, { "id": 471273, "postDate": "2019-02-14T08:29:26.113Z", "content": "Same here. Looks like lot of teams' best score was taken not a selected kernel submission
", "rawMarkdown": "Same here. Looks like lot of teams' best score was taken not a selected kernel submission" }, { "id": 471218, "postDate": "2019-02-14T06:42:40.733Z", "content": "I checked my submission.\nThey re-run my select two kernel, and choose the best score one to be the final score (one of selected kernels).\nFor those not re-run kernel, I got better score than the re-run kernel score on selected kernel.\nI think they only use re-run score to be the final score.
", "rawMarkdown": "I checked my submission.\nThey re-run my select two kernel, and choose the best score one to be the final score (one of selected kernels).\nFor those not re-run kernel, I got better score than the re-run kernel score on selected kernel.\nI think they only use re-run score to be the final score.", "replies": [ { "id": 471230, "postDate": "2019-02-14T07:06:01.687Z", "content": "@super13579, you are correct. See my updated comment above.
", "rawMarkdown": "@super13579, you are correct. See my updated comment above." } ] }, { "id": 471210, "postDate": "2019-02-14T06:32:21.073Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 471701, "author_name": "Julia Elliott", "author_url": "", "post_date": "2019-02-14T19:29:30.050000", "content": "The score you are seeing for your selected submissions are from your Stage 1 submission. You can see the Stage 2 scoring of that submission, which is the one used for the private LB, by finding the \"Kernel Rerun for Submission\" version. The leaderboard is confirmed as correct and based only on selected submissions.
\n\nThank you for raising the issue. We recognize how this may be causing confusion and are working on an improvement to the UI.
", "votes": 5, "replies": [] }, { "id": 471168, "author_name": "YaGana Sheriff-Hussaini", "author_url": "", "post_date": "2019-02-14T05:25:50.587000", "content": "@carloshuertas, your post made me check and I noticed a dsparity in mine too. I am ranked by an unselected submission with score = 0.70364 whilst my selected submission scores 0.70371, strange! They have already awarded the medals and probably the points as well?
", "votes": 3, "replies": [ { "id": 471198, "author_name": "NxGTR", "author_url": "", "post_date": "2019-02-14T06:18:44.797000", "content": "I don't think so, too early for that, but giving my position in the 600th I am safe of any medals :D
", "votes": 3, "replies": [] }, { "id": 471207, "author_name": "YaGana Sheriff-Hussaini", "author_url": "", "post_date": "2019-02-14T06:29:46.243000", "content": "@carloshuertas, my account shows my silver medal already and my world ranking have improved a few places but can see only a difference of 336 points in my total points.
\n\nUpdate
\n\nI just read the competition finalized post by @inversion. He confirmed in response to someone's question that they rerun our kernels with the stage-2 test which is 376k (total) = 56k (public) + 320k (private). I then checked my account again and saw my rerun kernel is shown right next to my selected kernel both with the same name but different scores. I had to sort them by scores to see them displayed next to each other. Yours may be different if you have a kernel with score that lies between your selection and the rerun.
", "votes": 1, "replies": [] }, { "id": 471358, "author_name": "", "author_url": "", "post_date": "2019-02-14T10:50:32.520000", "content": "same here! the score reflected on leaderboard is not the one I'm selected as final submission.. Weird!
", "votes": 12, "replies": [] } ] }, { "id": 471366, "author_name": "Amit Kumar Jaiswal", "author_url": "", "post_date": "2019-02-14T11:03:36.073000", "content": "@carloshuertas Agree. Same here as my score on private LB is not the selected one -> 0.70573.
", "votes": 1, "replies": [] }, { "id": 471273, "author_name": "Shahebaz Mohammad", "author_url": "", "post_date": "2019-02-14T08:29:26.113000", "content": "Same here. Looks like lot of teams' best score was taken not a selected kernel submission
", "votes": 0, "replies": [] }, { "id": 471218, "author_name": "0xFunky", "author_url": "", "post_date": "2019-02-14T06:42:40.733000", "content": "I checked my submission.\nThey re-run my select two kernel, and choose the best score one to be the final score (one of selected kernels).\nFor those not re-run kernel, I got better score than the re-run kernel score on selected kernel.\nI think they only use re-run score to be the final score.
", "votes": 0, "replies": [ { "id": 471230, "author_name": "YaGana Sheriff-Hussaini", "author_url": "", "post_date": "2019-02-14T07:06:01.687000", "content": "@super13579, you are correct. See my updated comment above.
", "votes": 0, "replies": [] } ] }, { "id": 471210, "author_name": "", "author_url": "", "post_date": "2019-02-14T06:32:21.073000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "471155": "I am either missing something, or there is a bug, it seems I am being ranked not by my selected submissions but my best submission instead.\n\nMy score should be 0.70043, but I see me at 0.70132 on the LB.\n", "471701": "The score you are seeing for your selected submissions are from your Stage 1 submission. You can see the Stage 2 scoring of that submission, which is the one used for the private LB, by finding the \"Kernel Rerun for Submission\" version. The leaderboard is confirmed as correct and based only on selected submissions.\n\nThank you for raising the issue. We recognize how this may be causing confusion and are working on an improvement to the UI. ", "471168": "@carloshuertas, your post made me check and I noticed a dsparity in mine too. I am ranked by an unselected submission with score = 0.70364 whilst my selected submission scores 0.70371, strange! They have already awarded the medals and probably the points as well?", "471366": "@carloshuertas Agree. Same here as my score on private LB is not the selected one -> 0.70573.", "471273": "Same here. Looks like lot of teams' best score was taken not a selected kernel submission", "471218": "I checked my submission.\nThey re-run my select two kernel, and choose the best score one to be the final score (one of selected kernels).\nFor those not re-run kernel, I got better score than the re-run kernel score on selected kernel.\nI think they only use re-run score to be the final score.", "471210": "" } }