{
  "total": 96,
  "topics": [
    {
      "id": 693888,
      "title": "That's a Wrap! Competition Closing - Congratulations to the Winners!",
      "comment_count": 14,
      "views": 0,
      "votes": 8
    },
    {
      "id": 668270,
      "title": "Thank you for your participation!",
      "comment_count": 11,
      "views": 0,
      "votes": 11
    },
    {
      "id": 613052,
      "title": "Welcome to the Scientific Image Forgery Detection Challenge!",
      "comment_count": 25,
      "views": 0,
      "votes": 14
    },
    {
      "id": 614069,
      "title": "Getting Deeper into Scientific Image Copy-Move Forgeries",
      "comment_count": 7,
      "views": 0,
      "votes": 16
    },
    {
      "id": 613025,
      "title": "How to get started + Competition's Official Discord",
      "comment_count": 5,
      "views": 0,
      "votes": 8
    },
    {
      "id": 695702,
      "title": "1st Place Solution",
      "comment_count": 5,
      "views": 0,
      "votes": 37
    },
    {
      "id": 700586,
      "title": "6th place solution: SuperPoint + LightGlue",
      "comment_count": 0,
      "views": 0,
      "votes": 3
    },
    {
      "id": 697699,
      "title": "5th Place Solution — DINOv3 Semantic Segmentation",
      "comment_count": 0,
      "views": 0,
      "votes": 5
    },
    {
      "id": 697621,
      "title": "4th Place Solution",
      "comment_count": 0,
      "views": 0,
      "votes": 5
    },
    {
      "id": 697809,
      "title": "2nd Place Solution/SIFT Maching",
      "comment_count": 0,
      "views": 0,
      "votes": 3
    },
    {
      "id": 697675,
      "title": "Solution: Public LB 8th place | Private LB 3rd place (updated 2026-04-28)",
      "comment_count": 0,
      "views": 0,
      "votes": 4
    },
    {
      "id": 694397,
      "title": "2nd Place Solution",
      "comment_count": 10,
      "views": 0,
      "votes": 15
    },
    {
      "id": 694442,
      "title": "65th Place Solution🥈|  DINOv2 with a Tiny Convolutional Decoder",
      "comment_count": 2,
      "views": 0,
      "votes": 8
    },
    {
      "id": 694015,
      "title": "Inquiry regarding removal from competition and missing private score",
      "comment_count": 6,
      "views": 0,
      "votes": 1
    },
    {
      "id": 694168,
      "title": "RECOD.AI - LUC Scientific Image Forgery Detection - 29th Place Solution",
      "comment_count": 0,
      "views": 0,
      "votes": 7
    },
    {
      "id": 694037,
      "title": "Why do older submissions show warning icons (⚠️)?",
      "comment_count": 1,
      "views": 0,
      "votes": 3
    },
    {
      "id": 684191,
      "title": "Data Update + Announcing the SCIFOR Workshop @ ICIP 2026!",
      "comment_count": 9,
      "views": 0,
      "votes": 6
    },
    {
      "id": 687043,
      "title": "Request for Dataset Access – Academic Research",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 674890,
      "title": "Solution: Public LB 8th place | Private LB 3rd place (updated 2026-04-28)",
      "comment_count": 6,
      "views": 0,
      "votes": 7
    },
    {
      "id": 673770,
      "title": "Competition closed!",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 673252,
      "title": "Is Mask-RCNN a valid general approach?",
      "comment_count": 3,
      "views": 0,
      "votes": null
    },
    {
      "id": 669686,
      "title": "Sharing Training Methods",
      "comment_count": 0,
      "views": 0,
      "votes": 0
    },
    {
      "id": 668521,
      "title": "RSIID Dataset",
      "comment_count": 5,
      "views": 0,
      "votes": 4
    },
    {
      "id": 668500,
      "title": "problem with the leaderboard",
      "comment_count": 2,
      "views": 0,
      "votes": 2
    },
    {
      "id": 668452,
      "title": "What happens now?",
      "comment_count": 0,
      "views": 0,
      "votes": 3
    },
    {
      "id": 668259,
      "title": "Evaluating Image Classification into GEL, PLANT, and OTHER Categories.",
      "comment_count": 2,
      "views": 0,
      "votes": null
    },
    {
      "id": 668017,
      "title": "Appreciation Post",
      "comment_count": 2,
      "views": 0,
      "votes": 3
    },
    {
      "id": 667669,
      "title": "Help with snntorch or any other package for submit",
      "comment_count": 3,
      "views": 0,
      "votes": null
    },
    {
      "id": 667549,
      "title": "Test data not available",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 667326,
      "title": "time taken for the submission",
      "comment_count": 2,
      "views": 0,
      "votes": null
    },
    {
      "id": 666251,
      "title": "CV vs Public LB",
      "comment_count": 3,
      "views": 0,
      "votes": 0
    },
    {
      "id": 665144,
      "title": " Scientific Image Forgery Detection submission scoring error ",
      "comment_count": 2,
      "views": 0,
      "votes": 0
    },
    {
      "id": 666656,
      "title": "What is your best score for a single model? ",
      "comment_count": 1,
      "views": 0,
      "votes": 0
    },
    {
      "id": 665866,
      "title": "why not dinov2 large?",
      "comment_count": 4,
      "views": 0,
      "votes": 1
    },
    {
      "id": 665875,
      "title": "Help needed: RLE submission format check (multiple connected components + authentic example)",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 654741,
      "title": "Is the test image \"45.png\" authentic or forged? What does your model tell you?",
      "comment_count": 7,
      "views": 0,
      "votes": 3
    },
    {
      "id": 665205,
      "title": "Does Augmentation make a difference ?",
      "comment_count": 3,
      "views": 0,
      "votes": 1
    },
    {
      "id": 664542,
      "title": "How good is your score compared to all authentic baseline?",
      "comment_count": 6,
      "views": 0,
      "votes": 6
    },
    {
      "id": 664956,
      "title": "Submission Scoring Error",
      "comment_count": 2,
      "views": 0,
      "votes": 2
    },
    {
      "id": 664624,
      "title": "Clarification on Copy–Move Forgery Variants and Transformations in the Dataset",
      "comment_count": 1,
      "views": 0,
      "votes": 1
    },
    {
      "id": 664426,
      "title": "Mask data RGB versus 3 separate cells?",
      "comment_count": 2,
      "views": 0,
      "votes": 2
    },
    {
      "id": 664236,
      "title": "Multi channel masks",
      "comment_count": 5,
      "views": 0,
      "votes": 2
    },
    {
      "id": 635546,
      "title": "Discussion about Segmentation score",
      "comment_count": 5,
      "views": 0,
      "votes": 2
    },
    {
      "id": 664197,
      "title": "Language of code submitted?",
      "comment_count": 0,
      "views": 0,
      "votes": 0
    },
    {
      "id": 663917,
      "title": "Any luck with classification models?",
      "comment_count": 3,
      "views": 0,
      "votes": 1
    },
    {
      "id": 664094,
      "title": "Good IOU / per-pixel F1",
      "comment_count": 0,
      "views": 0,
      "votes": 0
    },
    {
      "id": 664051,
      "title": "Submission.csv wrong example format",
      "comment_count": 0,
      "views": 0,
      "votes": 0
    },
    {
      "id": 663896,
      "title": "conformation",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 657899,
      "title": "Huge differences between train and supplemental images",
      "comment_count": 2,
      "views": 0,
      "votes": 7
    },
    {
      "id": 663365,
      "title": "Is test set going to have pairs?",
      "comment_count": 1,
      "views": 0,
      "votes": 3
    },
    {
      "id": 663517,
      "title": "Submission scoring error",
      "comment_count": 5,
      "views": 0,
      "votes": null
    },
    {
      "id": 663565,
      "title": "How to attach additional datasets?",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 655298,
      "title": "imbalance issue",
      "comment_count": 2,
      "views": 0,
      "votes": 1
    },
    {
      "id": 658623,
      "title": "Surprising Gap between Local Validation Score (0.722) and in Public LB (0.103)",
      "comment_count": 6,
      "views": 0,
      "votes": 4
    },
    {
      "id": 613586,
      "title": "The \"research papers leaderboard scores during this phase are not meaningful.\"",
      "comment_count": 9,
      "views": 0,
      "votes": 7
    },
    {
      "id": 663084,
      "title": "(No internet)",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 641008,
      "title": "Using Segment Anything (SAM2) Masks to Generate Forgery Candidates",
      "comment_count": 7,
      "views": 0,
      "votes": 3
    },
    {
      "id": 617968,
      "title": "Supplemental train data added",
      "comment_count": 13,
      "views": 0,
      "votes": 18
    },
    {
      "id": 662500,
      "title": "How to carry out the two-stage process of training and prediction？",
      "comment_count": 2,
      "views": 0,
      "votes": null
    },
    {
      "id": 617903,
      "title": "CV / LB gap - massive?",
      "comment_count": 6,
      "views": 0,
      "votes": 8
    },
    {
      "id": 617749,
      "title": "Model comparison: DINOv2, DeepLabV3, ConvNeXT...",
      "comment_count": 5,
      "views": 0,
      "votes": 22
    },
    {
      "id": 651831,
      "title": "Correct format",
      "comment_count": 1,
      "views": 0,
      "votes": 1
    },
    {
      "id": 651586,
      "title": "fogery images and authentic images",
      "comment_count": 3,
      "views": 0,
      "votes": 1
    },
    {
      "id": 641092,
      "title": "The competition metric is extremely unfair. ",
      "comment_count": 7,
      "views": 0,
      "votes": 10
    },
    {
      "id": 614763,
      "title": "Correct submission format",
      "comment_count": 11,
      "views": 0,
      "votes": 10
    },
    {
      "id": 639248,
      "title": "Bug: Dependency Manager failure on submission",
      "comment_count": 2,
      "views": 0,
      "votes": null
    },
    {
      "id": 613246,
      "title": "CRITICAL: Submission Scoring Error (Wrong Number of Rows) - Sample Submission Parsing Issue",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 633723,
      "title": "Question about fogery images",
      "comment_count": 5,
      "views": 0,
      "votes": 0
    },
    {
      "id": 630062,
      "title": "Score Improvement: Background Coverage & New Dataset Options",
      "comment_count": 0,
      "views": 0,
      "votes": 7
    },
    {
      "id": 613580,
      "title": "Many teams have a score of 0.3 on the Leaderboard. How are these teams with the same score of 0.3 ranked?",
      "comment_count": 5,
      "views": 0,
      "votes": 1
    },
    {
      "id": 633418,
      "title": "Performance Metrics on the Separately Split Validation Set",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 613765,
      "title": "Anyone observing discrepancies between local validation and LB?",
      "comment_count": 4,
      "views": 0,
      "votes": 2
    },
    {
      "id": 615080,
      "title": "Why This Challenge Is So Difficult",
      "comment_count": 13,
      "views": 0,
      "votes": 22
    },
    {
      "id": 617806,
      "title": "The Impact of Randomness in Deep Learning",
      "comment_count": 1,
      "views": 0,
      "votes": 3
    },
    {
      "id": 621903,
      "title": "Is a cropped images dataset useful?",
      "comment_count": 0,
      "views": 0,
      "votes": 1
    },
    {
      "id": 614778,
      "title": "Error in the code or data on the inference",
      "comment_count": 7,
      "views": 0,
      "votes": 5
    },
    {
      "id": 615048,
      "title": "Do we need to annotate BOTH the source region AND the target region in our predicted masks to maximize the oF1 score?",
      "comment_count": 3,
      "views": 0,
      "votes": 2
    },
    {
      "id": 615334,
      "title": "Recod.ai/LUC - Scientific Image Forgery Detection",
      "comment_count": 0,
      "views": 0,
      "votes": 2
    },
    {
      "id": 615300,
      "title": "Understanding mask shape",
      "comment_count": 3,
      "views": 0,
      "votes": 1
    },
    {
      "id": 613707,
      "title": "Some masks do not seem correct",
      "comment_count": 4,
      "views": 0,
      "votes": 3
    },
    {
      "id": 613200,
      "title": "Note: the mask highlights both the copy+pasted part AND the original part that was copied from",
      "comment_count": 10,
      "views": 0,
      "votes": 10
    },
    {
      "id": 613990,
      "title": "The score does not improve beyond 0.303 significantly!!! Why?",
      "comment_count": 3,
      "views": 0,
      "votes": 11
    },
    {
      "id": 613694,
      "title": "Possible Labeling Error: Computed Mask vs. Ground Truth Mask Mismatch",
      "comment_count": 6,
      "views": 0,
      "votes": 11
    },
    {
      "id": 613666,
      "title": "What do you think makes this competition hard?",
      "comment_count": 8,
      "views": 0,
      "votes": 1
    },
    {
      "id": 614650,
      "title": "Clarification on test data distribution and final evaluation set",
      "comment_count": 3,
      "views": 0,
      "votes": 1
    },
    {
      "id": 613401,
      "title": "Gradio:  RECOD Segmentation Training & Inference Dashboard",
      "comment_count": 2,
      "views": 0,
      "votes": 15
    },
    {
      "id": 613803,
      "title": "thanks to the organizers!",
      "comment_count": 0,
      "views": 0,
      "votes": 2
    },
    {
      "id": 613876,
      "title": "【Question】Can I Use Pretrained Weights for This Competition?",
      "comment_count": 4,
      "views": 0,
      "votes": null
    },
    {
      "id": 613066,
      "title": "Copy-move forgery (CMFD) detection technique with DCT (Discrete Cosine Transform)",
      "comment_count": 2,
      "views": 0,
      "votes": 38
    },
    {
      "id": 613199,
      "title": "Test Images Folder",
      "comment_count": 0,
      "views": 0,
      "votes": 4
    },
    {
      "id": 613077,
      "title": "Would additional postprocessing typically applied after copy-paste manipulations？",
      "comment_count": 1,
      "views": 0,
      "votes": null
    },
    {
      "id": 613461,
      "title": "Help!! The notebook cannot run.",
      "comment_count": 4,
      "views": 0,
      "votes": null
    },
    {
      "id": 613293,
      "title": "Suggestion for Interactive Mode & Clarification on Test Set Path",
      "comment_count": 0,
      "views": 0,
      "votes": 2
    },
    {
      "id": 613091,
      "title": "pairs of authentic ans forged images in the test set",
      "comment_count": 3,
      "views": 0,
      "votes": null
    },
    {
      "id": 613314,
      "title": "The Strategic Synthesis: Optimizing Deep Learning for Scientific Forgery Detection",
      "comment_count": 0,
      "views": 0,
      "votes": 1
    },
    {
      "id": 613273,
      "title": "test data is 1 image only",
      "comment_count": 2,
      "views": 0,
      "votes": null
    }
  ],
  "errors": []
}