{
  "total": 151,
  "topics": [
    {
      "id": 679898,
      "title": "Recap of Competition - Congratulations to the Winners!",
      "comment_count": 1,
      "views": 0,
      "votes": 9
    },
    {
      "id": 679385,
      "title": "Thank you for helping us read the scrolls! ",
      "comment_count": 14,
      "views": 0,
      "votes": 30
    },
    {
      "id": 672634,
      "title": "Update: Test set fix, submission rescore, and deadline extension",
      "comment_count": 93,
      "views": 0,
      "votes": 48
    },
    {
      "id": 667658,
      "title": "Why what you are doing matters",
      "comment_count": 3,
      "views": 0,
      "votes": 16
    },
    {
      "id": 619251,
      "title": "Welcome to Vesuvius Challenge - Surface Detection competition",
      "comment_count": 5,
      "views": 0,
      "votes": 24
    },
    {
      "id": 664184,
      "title": "Dataset update with improved label quality",
      "comment_count": 51,
      "views": 0,
      "votes": 33
    },
    {
      "id": 662972,
      "title": "Prize pool DOUBLED! 😱",
      "comment_count": 8,
      "views": 0,
      "votes": 42
    },
    {
      "id": 639347,
      "title": "Bonus prizes available!",
      "comment_count": 2,
      "views": 0,
      "votes": 14
    },
    {
      "id": 619242,
      "title": "How to get started + Competition's Official Discord",
      "comment_count": 2,
      "views": 0,
      "votes": 17
    },
    {
      "id": 715066,
      "title": "PHerc 1667 - Congratulations!",
      "comment_count": 0,
      "views": 0,
      "votes": 3
    },
    {
      "id": 679238,
      "title": "1st Place Solution for the Vesuvius Challenge - Surface Detection Competition",
      "comment_count": 31,
      "views": 0,
      "votes": 66
    },
    {
      "id": 681341,
      "title": "Amazing results after 4,000 epochs: PB=0.635",
      "comment_count": 4,
      "views": 0,
      "votes": 9
    },
    {
      "id": 679222,
      "title": "4-th Place Solution",
      "comment_count": 13,
      "views": 0,
      "votes": 31
    },
    {
      "id": 679241,
      "title": "9th Place Solution SUPER-CONSERVATIVE(0.623->0.616)",
      "comment_count": 14,
      "views": 0,
      "votes": 24
    },
    {
      "id": 679360,
      "title": "5th Place Solution",
      "comment_count": 21,
      "views": 0,
      "votes": 51
    },
    {
      "id": 680280,
      "title": "6-th place solution",
      "comment_count": 0,
      "views": 0,
      "votes": 6
    },
    {
      "id": 680414,
      "title": "Why Is Median Filtering Effective? (Answer by ChatGPT-5.4)",
      "comment_count": 1,
      "views": 0,
      "votes": 3
    },
    {
      "id": 679221,
      "title": "Bronze Medal - ChatGPT Vibe Coding!",
      "comment_count": 43,
      "views": 0,
      "votes": 32
    },
    {
      "id": 679227,
      "title": "10th place solution ",
      "comment_count": 30,
      "views": 0,
      "votes": 27
    },
    {
      "id": 679278,
      "title": "2nd Place Solution Vesuvius Challenge – A postprocessing win",
      "comment_count": 9,
      "views": 0,
      "votes": 27
    },
    {
      "id": 679907,
      "title": "49th Place Solution - Vesuvius Surface Detection",
      "comment_count": 0,
      "views": 0,
      "votes": 10
    },
    {
      "id": 679251,
      "title": "7th Place Solution for the Vesuvius Challenge",
      "comment_count": 5,
      "views": 0,
      "votes": 16
    },
    {
      "id": 679362,
      "title": "Median Filter ×7 Is REALLY All You Need (Private Score: 0.614 -> 0.628)",
      "comment_count": 15,
      "views": 0,
      "votes": 14
    },
    {
      "id": 679236,
      "title": " 3rd place solution",
      "comment_count": 12,
      "views": 0,
      "votes": 24
    },
    {
      "id": 679220,
      "title": "18th : median filter x 7 post processing is very strong",
      "comment_count": 12,
      "views": 0,
      "votes": 32
    },
    {
      "id": 679772,
      "title": "A costly mistake to learn from",
      "comment_count": 3,
      "views": 0,
      "votes": 3
    },
    {
      "id": 679301,
      "title": "24th Place Solution - Vesuvius Challenge ",
      "comment_count": 7,
      "views": 0,
      "votes": 14
    },
    {
      "id": 679237,
      "title": "11th place",
      "comment_count": 3,
      "views": 0,
      "votes": 20
    },
    {
      "id": 679565,
      "title": "123rd place — not where I aimed, but here's what I learned",
      "comment_count": 2,
      "views": 0,
      "votes": 8
    },
    {
      "id": 679223,
      "title": "92th solution - coded with AI",
      "comment_count": 10,
      "views": 0,
      "votes": 13
    },
    {
      "id": 678904,
      "title": "Is the hidden dataset different from the training data?",
      "comment_count": 52,
      "views": 0,
      "votes": 9
    },
    {
      "id": 679259,
      "title": "12th place solution",
      "comment_count": 1,
      "views": 0,
      "votes": 19
    },
    {
      "id": 679248,
      "title": "8th-place-solution",
      "comment_count": 4,
      "views": 0,
      "votes": 13
    },
    {
      "id": 679371,
      "title": "Why are long epochs needed? I'd like to discuss this.",
      "comment_count": 4,
      "views": 0,
      "votes": 8
    },
    {
      "id": 679229,
      "title": "27th placement solution",
      "comment_count": 0,
      "views": 0,
      "votes": 14
    },
    {
      "id": 679225,
      "title": "Quick Preview of the 1st place solution",
      "comment_count": 0,
      "views": 0,
      "votes": 13
    },
    {
      "id": 679262,
      "title": "Don't trust LB too much.  😭",
      "comment_count": 12,
      "views": 0,
      "votes": 4
    },
    {
      "id": 679255,
      "title": "43rd Place Solution - Two-stage nnU-Net for Hole Filling",
      "comment_count": 0,
      "views": 0,
      "votes": 10
    },
    {
      "id": 679230,
      "title": "25th place solution",
      "comment_count": 3,
      "views": 0,
      "votes": 10
    },
    {
      "id": 679224,
      "title": "Probing Results (Train and Test Scroll IDs)",
      "comment_count": 8,
      "views": 0,
      "votes": 4
    },
    {
      "id": 679581,
      "title": "35th SilverSolution🥈High-Epoch nnU-Net Cascade with Optimized Patch ",
      "comment_count": 0,
      "views": 0,
      "votes": 2
    },
    {
      "id": 679575,
      "title": "From Cell Segmentation to Ancient Scrolls: WNet3D + nnUNet (LB 113, 0.582)",
      "comment_count": 0,
      "views": 0,
      "votes": 2
    },
    {
      "id": 679276,
      "title": "Bronze Medal - 29 Hours of TPU Continued Training（TransUNet）",
      "comment_count": 2,
      "views": 0,
      "votes": 5
    },
    {
      "id": 679345,
      "title": "TransUNet-epochs[1400] PB[0.586]",
      "comment_count": 7,
      "views": 0,
      "votes": 2
    },
    {
      "id": 679379,
      "title": "Z Compression Experiments",
      "comment_count": 2,
      "views": 0,
      "votes": 2
    },
    {
      "id": 679231,
      "title": "88th solution with Topology-Preserving 3D U-Net  and 5-Loss Stack  HybridCon",
      "comment_count": 0,
      "views": 0,
      "votes": 5
    },
    {
      "id": 679391,
      "title": "Cohesion enhancing shock filtering",
      "comment_count": 0,
      "views": 0,
      "votes": 0
    },
    {
      "id": 679209,
      "title": "Question: Does Kaggle fully replicate the notebook runtime in submission reruns?",
      "comment_count": 2,
      "views": 0,
      "votes": -1
    },
    {
      "id": 679194,
      "title": "Submission deadline - deadline to start a submission, or end it?",
      "comment_count": 3,
      "views": 0,
      "votes": null
    },
    {
      "id": 679053,
      "title": "Any workaround to submit inference notebook without gpu quota left?",
      "comment_count": 5,
      "views": 0,
      "votes": null
    },
    {
      "id": 674052,
      "title": "VOI Metric - Critical Issue?",
      "comment_count": 11,
      "views": 0,
      "votes": 8
    },
    {
      "id": 674697,
      "title": "Competing with Limited Hardware: Are Public Models Enough to Medal?",
      "comment_count": 6,
      "views": 0,
      "votes": null
    },
    {
      "id": 676231,
      "title": "competition metric",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 674680,
      "title": "Models tested so far?",
      "comment_count": 3,
      "views": 0,
      "votes": null
    },
    {
      "id": 672996,
      "title": "Request to host - Transparency on new leaderboard scoring",
      "comment_count": 10,
      "views": 0,
      "votes": 37
    },
    {
      "id": 674104,
      "title": "Stuck because of Inference Time for past few days",
      "comment_count": 4,
      "views": 0,
      "votes": null
    },
    {
      "id": 673535,
      "title": "Does this count as a hole?",
      "comment_count": 10,
      "views": 0,
      "votes": 9
    },
    {
      "id": 673522,
      "title": "Does dinov3 allowed in this competition?",
      "comment_count": 2,
      "views": 0,
      "votes": -3
    },
    {
      "id": 673114,
      "title": "Do binary hole filling algorithms fail?",
      "comment_count": 8,
      "views": 0,
      "votes": 4
    },
    {
      "id": 671434,
      "title": "TensorRT pain",
      "comment_count": 11,
      "views": 0,
      "votes": 2
    },
    {
      "id": 672354,
      "title": "TIMEOUT ERROR  - Vesuvius Challenge - Surface Detection",
      "comment_count": 11,
      "views": 0,
      "votes": -5
    },
    {
      "id": 672740,
      "title": "Extend teaming deadline [denied]",
      "comment_count": 12,
      "views": 0,
      "votes": 11
    },
    {
      "id": 673713,
      "title": "Kaggle inference performance",
      "comment_count": 0,
      "views": 0,
      "votes": -2
    },
    {
      "id": 671160,
      "title": "[CRITICAL] Why the local validation is invalid, and potentially the whole leaderboard.",
      "comment_count": 45,
      "views": 0,
      "votes": 55
    },
    {
      "id": 672974,
      "title": "Voxel spacing (µm/voxel) for Kaggle Surface Detection dataset?",
      "comment_count": 1,
      "views": 0,
      "votes": 3
    },
    {
      "id": 672464,
      "title": "Unable to initialize TPU v5e-8",
      "comment_count": 13,
      "views": 0,
      "votes": 4
    },
    {
      "id": 672447,
      "title": "Questions for the host about the metric.",
      "comment_count": 6,
      "views": 0,
      "votes": 6
    },
    {
      "id": 672627,
      "title": "Doubt on Inference",
      "comment_count": 2,
      "views": 0,
      "votes": 2
    },
    {
      "id": 673206,
      "title": "Has rescoring finished?",
      "comment_count": 0,
      "views": 0,
      "votes": -8
    },
    {
      "id": 672383,
      "title": "suggestion regarding kaggle progression",
      "comment_count": 3,
      "views": 0,
      "votes": 4
    },
    {
      "id": 672708,
      "title": "The competition has been extended by more than ten days, right?",
      "comment_count": 1,
      "views": 0,
      "votes": -3
    },
    {
      "id": 672397,
      "title": "Debugging submission errors",
      "comment_count": 5,
      "views": 0,
      "votes": -3
    },
    {
      "id": 671325,
      "title": "polynomial volume",
      "comment_count": 5,
      "views": 0,
      "votes": 13
    },
    {
      "id": 672308,
      "title": "I estimate that there will be even higher-scoring public proposals in the last few days.",
      "comment_count": 1,
      "views": 0,
      "votes": -10
    },
    {
      "id": 672302,
      "title": "About CV strategy",
      "comment_count": 0,
      "views": 0,
      "votes": -5
    },
    {
      "id": 666453,
      "title": "[Host Baseline] -- modified nnUNet 0.543 LB raw, 0.562 w/ post processing",
      "comment_count": 48,
      "views": 0,
      "votes": 28
    },
    {
      "id": 671790,
      "title": "As a beginner here, I am confused. Help me",
      "comment_count": 7,
      "views": 0,
      "votes": 1
    },
    {
      "id": 671930,
      "title": "Which model work best for this?",
      "comment_count": 3,
      "views": 0,
      "votes": -7
    },
    {
      "id": 669919,
      "title": "feeling a bit down",
      "comment_count": 37,
      "views": 0,
      "votes": 17
    },
    {
      "id": 671782,
      "title": "I like this competition because it's difficult to improve your score, so the leaderboard doesn't change too quickly.",
      "comment_count": 2,
      "views": 0,
      "votes": 1
    },
    {
      "id": 671984,
      "title": "Notebook Time Limit Exceeded Error",
      "comment_count": 1,
      "views": 0,
      "votes": -2
    },
    {
      "id": 671613,
      "title": "Running more than 200 epochs?",
      "comment_count": 4,
      "views": 0,
      "votes": 1
    },
    {
      "id": 671272,
      "title": "Stranger things - sheet merges",
      "comment_count": 0,
      "views": 0,
      "votes": 3
    },
    {
      "id": 669994,
      "title": "CV0.5806/LB0.529？？？",
      "comment_count": 21,
      "views": 0,
      "votes": 4
    },
    {
      "id": 670979,
      "title": "Feel Free to Use This To Write Your Suggestions",
      "comment_count": 2,
      "views": 0,
      "votes": 2
    },
    {
      "id": 671176,
      "title": "Scoring time",
      "comment_count": 2,
      "views": 0,
      "votes": 2
    },
    {
      "id": 671230,
      "title": "What are the deprecated data?",
      "comment_count": 1,
      "views": 0,
      "votes": -1
    },
    {
      "id": 671195,
      "title": "If using nnunet for training, how do people usually set the number of epochs? Is the default 1000? Do you train with the full dataset for 1000 epochs?",
      "comment_count": 4,
      "views": 0,
      "votes": 1
    },
    {
      "id": 669787,
      "title": "Too Much time on Submission",
      "comment_count": 9,
      "views": 0,
      "votes": 2
    },
    {
      "id": 669984,
      "title": "kaggle error",
      "comment_count": 1,
      "views": 0,
      "votes": 1
    },
    {
      "id": 669939,
      "title": "Kaggle System Error when submitting.",
      "comment_count": 1,
      "views": 0,
      "votes": 2
    },
    {
      "id": 665764,
      "title": "Question about GPU Support for Training Deep Learning Models",
      "comment_count": 13,
      "views": 0,
      "votes": 5
    },
    {
      "id": 668313,
      "title": "Ignore label is a trap",
      "comment_count": 21,
      "views": 0,
      "votes": 11
    },
    {
      "id": 668911,
      "title": "Available time for notebook execution",
      "comment_count": 6,
      "views": 0,
      "votes": 1
    },
    {
      "id": 621455,
      "title": "Is the metric calculation included within the overall 9-hour limit?",
      "comment_count": 7,
      "views": 0,
      "votes": 8
    },
    {
      "id": 668841,
      "title": "why the environment is not stable?",
      "comment_count": 1,
      "views": 0,
      "votes": -6
    },
    {
      "id": 666322,
      "title": "2.5D segmentation solutions",
      "comment_count": 2,
      "views": 0,
      "votes": 7
    },
    {
      "id": 667218,
      "title": "How long does it take to train one fold, and what GPU do you use?",
      "comment_count": 9,
      "views": 0,
      "votes": 4
    },
    {
      "id": 665682,
      "title": "Test Set Size & Private Leaderboard Time Limit?",
      "comment_count": 14,
      "views": 0,
      "votes": 2
    },
    {
      "id": 667135,
      "title": "Diffeomorphic Suface Fitting",
      "comment_count": 6,
      "views": 0,
      "votes": 10
    },
    {
      "id": 636548,
      "title": "Submission failures?",
      "comment_count": 24,
      "views": 0,
      "votes": 5
    },
    {
      "id": 668093,
      "title": "some problem",
      "comment_count": 0,
      "views": 0,
      "votes": 1
    },
    {
      "id": 666084,
      "title": "Anyone with Colab pro or other cloud GPU would like to share and team up with me?",
      "comment_count": 3,
      "views": 0,
      "votes": 3
    },
    {
      "id": 666660,
      "title": "Question about unlabeled data",
      "comment_count": 1,
      "views": 0,
      "votes": 4
    },
    {
      "id": 627529,
      "title": "Training speed improves 10x if you convert TIFF dataset to NPY / RLE",
      "comment_count": 9,
      "views": 0,
      "votes": 17
    },
    {
      "id": 666081,
      "title": "What do you guys do in middle of the Competition ?",
      "comment_count": 9,
      "views": 0,
      "votes": 4
    },
    {
      "id": 649869,
      "title": "Machine specifications",
      "comment_count": 2,
      "views": 0,
      "votes": 1
    },
    {
      "id": 666940,
      "title": "error to submit forked and modified notebook.",
      "comment_count": 2,
      "views": 0,
      "votes": -6
    },
    {
      "id": 664320,
      "title": "Marching ANTS is all you need !!!",
      "comment_count": 27,
      "views": 0,
      "votes": 23
    },
    {
      "id": 651532,
      "title": "[placeholder] my solution : it is connecting the dots!",
      "comment_count": 162,
      "views": 0,
      "votes": 58
    },
    {
      "id": 666350,
      "title": "Could Kaggle provide one submission per day even running out gpu quota?",
      "comment_count": 4,
      "views": 0,
      "votes": -5
    },
    {
      "id": 665060,
      "title": "Leaderboard rescore underway [Now complete]",
      "comment_count": 31,
      "views": 0,
      "votes": 19
    },
    {
      "id": 666213,
      "title": "How do we downgrade our environment?",
      "comment_count": 1,
      "views": 0,
      "votes": 1
    },
    {
      "id": 651700,
      "title": "Few questions to host",
      "comment_count": 4,
      "views": 0,
      "votes": 5
    },
    {
      "id": 664776,
      "title": "Share the old dataset.",
      "comment_count": 3,
      "views": 0,
      "votes": 8
    },
    {
      "id": 664478,
      "title": "old and new data: what has changed",
      "comment_count": 7,
      "views": 0,
      "votes": 16
    },
    {
      "id": 664676,
      "title": "Is it possible to still access old data?",
      "comment_count": 4,
      "views": 0,
      "votes": 2
    },
    {
      "id": 619309,
      "title": "Video how to use Kaggle server in VS Code",
      "comment_count": 3,
      "views": 0,
      "votes": 27
    },
    {
      "id": 665206,
      "title": "train_labels has only value 2 (pixel value)",
      "comment_count": 1,
      "views": 0,
      "votes": -6
    },
    {
      "id": 663144,
      "title": "3D Viewer Utility",
      "comment_count": 6,
      "views": 0,
      "votes": 78
    },
    {
      "id": 651550,
      "title": "Has anyone tried warpping loss (in topo-pitfalls project and paper)? ",
      "comment_count": 11,
      "views": 0,
      "votes": 7
    },
    {
      "id": 660123,
      "title": "Some thoughts on challenge design",
      "comment_count": 17,
      "views": 0,
      "votes": 19
    },
    {
      "id": 653482,
      "title": "ignoring unlabelled region in evaluation ... a problem?",
      "comment_count": 4,
      "views": 0,
      "votes": 11
    },
    {
      "id": 664021,
      "title": "Has anyone tried 3d yolov8-seg (or other instance seg method) ? ",
      "comment_count": 0,
      "views": 0,
      "votes": 1
    },
    {
      "id": 663127,
      "title": "Affinity Feature Strenghtening Network",
      "comment_count": 8,
      "views": 0,
      "votes": 5
    },
    {
      "id": 663476,
      "title": "Can we use yolo from ultralytics? as it is AGPL-3.0 LICENSE.",
      "comment_count": 1,
      "views": 0,
      "votes": 2
    },
    {
      "id": 653876,
      "title": "CSA-Net [LB-0.472] - Cross attention across layers",
      "comment_count": 3,
      "views": 0,
      "votes": 4
    },
    {
      "id": 658755,
      "title": "i ask chatgpt to trace the scroll",
      "comment_count": 6,
      "views": 0,
      "votes": 6
    },
    {
      "id": 656352,
      "title": "sample_submission.csv",
      "comment_count": 5,
      "views": 0,
      "votes": 1
    },
    {
      "id": 644215,
      "title": "Work Sharing - 3D Stationary Velocity Field Prediction ",
      "comment_count": 22,
      "views": 0,
      "votes": 12
    },
    {
      "id": 651113,
      "title": "Insights on competetion metric.",
      "comment_count": 1,
      "views": 0,
      "votes": 12
    },
    {
      "id": 642922,
      "title": "Training large models on Kaggle without your own GPU",
      "comment_count": 12,
      "views": 0,
      "votes": 5
    },
    {
      "id": 650742,
      "title": "how batch size weight in model training?",
      "comment_count": 1,
      "views": 0,
      "votes": 1
    },
    {
      "id": 641509,
      "title": "Access to additional unlabeled data",
      "comment_count": 2,
      "views": 0,
      "votes": 15
    },
    {
      "id": 638037,
      "title": "About data of different sizes",
      "comment_count": 4,
      "views": 0,
      "votes": 3
    },
    {
      "id": 630100,
      "title": "[Info] [UPDATED] Vesuvius `npy` and `tfrecord` format",
      "comment_count": 4,
      "views": 0,
      "votes": 7
    },
    {
      "id": 631311,
      "title": "a feature for discussion, \"sheetness\"",
      "comment_count": 2,
      "views": 0,
      "votes": 9
    },
    {
      "id": 641906,
      "title": "Question about mapping the five scrolls from the website to train.csv IDs",
      "comment_count": 1,
      "views": 0,
      "votes": 1
    },
    {
      "id": 628688,
      "title": "Unlabeled regions",
      "comment_count": 10,
      "views": 0,
      "votes": 6
    },
    {
      "id": 641165,
      "title": "Dataset creation",
      "comment_count": 4,
      "views": 0,
      "votes": 1
    },
    {
      "id": 635524,
      "title": "Considerations and heuristics for finding valid surface curves",
      "comment_count": 4,
      "views": 0,
      "votes": 2
    },
    {
      "id": 623696,
      "title": "[Info] Keras 3 Multi-Backend 2D and 3D Imaging Library",
      "comment_count": 2,
      "views": 0,
      "votes": 6
    },
    {
      "id": 636937,
      "title": "Problems with the  Volume Cartographer ",
      "comment_count": 10,
      "views": 0,
      "votes": 1
    },
    {
      "id": 638852,
      "title": "Error message:  papermill.exceptions.PapermillExecutionError: ",
      "comment_count": 2,
      "views": 0,
      "votes": 1
    },
    {
      "id": 635357,
      "title": "Quick Clarification on Annotation Detail and Score Ceiling",
      "comment_count": 1,
      "views": 0,
      "votes": 11
    },
    {
      "id": 620810,
      "title": "Careful when teaming up! (Ghost teammates)",
      "comment_count": 3,
      "views": 0,
      "votes": 7
    },
    {
      "id": 628565,
      "title": "Are you training in your submission notebooks?",
      "comment_count": 2,
      "views": 0,
      "votes": 3
    },
    {
      "id": 622943,
      "title": "How to read greek on these scrolls? Images have no Ελληνικά γράμματα. Only lines. ",
      "comment_count": 4,
      "views": 0,
      "votes": 12
    },
    {
      "id": 627574,
      "title": "What does \"Submission scoring error\" mean?",
      "comment_count": 1,
      "views": 0,
      "votes": 2
    },
    {
      "id": 624340,
      "title": "Is the goal to predict just the recto surfaces or all surfaces",
      "comment_count": 1,
      "views": 0,
      "votes": 2
    },
    {
      "id": 619283,
      "title": "Baseline segmentation",
      "comment_count": 0,
      "views": 0,
      "votes": 1
    }
  ],
  "errors": []
}