{
  "story_id": "a989e8d74b9cbc26f59b4a3a6bd6d231",
  "desk": "drm3",
  "revision": 1,
  "published_at": "2026-09-02T04:00:00.000Z",
  "content_hash": "22830ae92bea6e63893c2784df8b1faa2446a0942c0898a86dfccfd4df6bb48d",
  "hash_basis": "sha256 over `headline\\ndek\\nprose`, plus `\\n` + the canonical citations JSON when any source is placed, plus `\\n#blog` for blogs",
  "basis": {
    "headline": "Study Reveals Instability in Surface Water Segmentation Model Rankings",
    "dek": "Research on Sen1Floods11 shows model rankings vary by seed and geography, requiring distinct evidence for deployment claims.",
    "prose": "Close orderings of model configurations vary across different seeds and geographic weighting schemes in the Sen1Floods11 evaluation. [^1]\n\nPerformance evaluation for surface-water segmentation commonly uses an aggregate metric such as global intersection-over-union (IoU) to rank model configurations. [^2]\n\nThe authors conclude that aggregate metrics remain useful for ranking complete configurations, but ranking stability, component attribution, input reliance, and deployment scope require distinct evidence. [^3]\n\nThe cross-modal student achieved the highest three-seed mean Intersection-over-Union (IoU) on the Sen1Floods11 dataset. [^4]\n\nOn the challenge's five-fold split, the mean Dice was 0.554 and mean lesion-level F1 was 0.528 without scribbles, rising to 0.751 and 0.733 after five correction rounds. [^5]\n\nThe autoPET/CT V challenge addresses the complexity of automated lesion segmentation in whole-body PET/CT caused by varying physiological tracer uptake patterns and differing lesion appearances across tracers. [^6]\n\nThe submitted model is a scribble-conditioned residual encoder U-Net operating on four input channels: CT, PET, and a sparse scribble map for each of foreground and background. [^7]\n\nThe researchers concluded that interaction largely compensates for how well or badly a given model segments unaided. [^8]",
    "cited": "[{\"statement\":\"Close orderings of model configurations vary across different seeds and geographic weighting schemes in the Sen1Floods11 evaluation.\",\"source\":\"takara.ai\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-08-31T14:48:18.000Z\",\"publisher_count\":1,\"sources\":[\"takara.ai\"]},{\"statement\":\"Performance evaluation for surface-water segmentation commonly uses an aggregate metric such as global intersection-over-union (IoU) to rank model configurations.\",\"source\":\"takara.ai\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-08-31T14:48:18.000Z\",\"publisher_count\":1,\"sources\":[\"takara.ai\"]},{\"statement\":\"The authors conclude that aggregate metrics remain useful for ranking complete configurations, but ranking stability, component attribution, input reliance, and deployment scope require distinct evidence.\",\"source\":\"takara.ai\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-08-31T14:48:18.000Z\",\"publisher_count\":1,\"sources\":[\"takara.ai\"]},{\"statement\":\"The cross-modal student achieved the highest three-seed mean Intersection-over-Union (IoU) on the Sen1Floods11 dataset.\",\"source\":\"takara.ai\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-08-31T14:48:18.000Z\",\"publisher_count\":1,\"sources\":[\"takara.ai\"]},{\"statement\":\"On the challenge's five-fold split, the mean Dice was 0.554 and mean lesion-level F1 was 0.528 without scribbles, rising to 0.751 and 0.733 after five correction rounds.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The autoPET/CT V challenge addresses the complexity of automated lesion segmentation in whole-body PET/CT caused by varying physiological tracer uptake patterns and differing lesion appearances across tracers.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The submitted model is a scribble-conditioned residual encoder U-Net operating on four input channels: CT, PET, and a sparse scribble map for each of foreground and background.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The researchers concluded that interaction largely compensates for how well or badly a given model segments unaided.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]}]",
    "kind": "news"
  },
  "receipt_verify": "Ed25519 over the dot-joined string `slice_hash.cursor_from.cursor_to.view.view_version.row_count`; public_key and sig are base64url of the raw 32-byte key / 64-byte signature",
  "receipt": null,
  "receipt_note": "this revision predates receipt-keeping (before v0.37.0); the filed row lives in the record",
  "generation_chain": {
    "wire": {
      "stream": "fountain_news",
      "story_id": "6fe2cd3aff2b482f4db6c06690a12864",
      "thread_id": "57c9963fc432c7de69d4cd6d41949521",
      "thread_label": "U-Net",
      "novelty": "UPDATE",
      "content_hash": "90c4e7c16bc7e4835e5c2830cca01662ee0827c8ba473320210bfc6f61102141",
      "last_published_at": "2026-09-02T04:00:00.000Z",
      "read_receipt": {
        "slice_hash": "3905664cf10c2126ea131af76eb59a4e670141af2a4606d101f9336a8aaf6e3e",
        "cursor_from": "eyJ0cyI6IjIwMjYtMDktMDJUMDM6NDM6MDAuMDAwMDAwWiIsImlkIjoiZjIzZjc5YTk3YjM4MGMyNDgzZTRlNzYxMjNlZjg2M2QiLCJ2IjoiMSJ9",
        "cursor_to": "eyJ0cyI6IjIwMjYtMDktMDJUMDQ6MDQ6MjYuMDAwMDAwWiIsImlkIjoiN2M3MjY3YjA5MzczMjU3ZjI0ZDZiY2NmZWY3ZDVjNGUiLCJ2IjoiMSJ9",
        "view": "v_fountain_news",
        "view_version": "1",
        "row_count": 100,
        "window_days": 3,
        "bytes_scanned": 12017721,
        "credits": 8,
        "price_per_100_rows": 8,
        "sig": "juwMycx6aGSQfawfzLUaISZZUKKkbvDiOPDpZxKn6fmy0KIBoISR1qDjkJuogjQ0TUgCk4tYeoc9JF0bPKfOCw",
        "public_key": "bMUigy8O0jOnBxQ4Sc-5lwhIZ8LQVAhxMbR7qESVuUE",
        "signer_path": "lakehouse/data-extract/v1",
        "alg": "Ed25519",
        "signed": true
      }
    },
    "written_at": "2026-09-02T22:35:59.154Z"
  },
  "cited_facts": [
    {
      "statement": "Close orderings of model configurations vary across different seeds and geographic weighting schemes in the Sen1Floods11 evaluation.",
      "source": "takara.ai",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-08-31T14:48:18.000Z",
      "publisher_count": 1,
      "sources": [
        "takara.ai"
      ]
    },
    {
      "statement": "Performance evaluation for surface-water segmentation commonly uses an aggregate metric such as global intersection-over-union (IoU) to rank model configurations.",
      "source": "takara.ai",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-08-31T14:48:18.000Z",
      "publisher_count": 1,
      "sources": [
        "takara.ai"
      ]
    },
    {
      "statement": "The authors conclude that aggregate metrics remain useful for ranking complete configurations, but ranking stability, component attribution, input reliance, and deployment scope require distinct evidence.",
      "source": "takara.ai",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-08-31T14:48:18.000Z",
      "publisher_count": 1,
      "sources": [
        "takara.ai"
      ]
    },
    {
      "statement": "The cross-modal student achieved the highest three-seed mean Intersection-over-Union (IoU) on the Sen1Floods11 dataset.",
      "source": "takara.ai",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-08-31T14:48:18.000Z",
      "publisher_count": 1,
      "sources": [
        "takara.ai"
      ]
    },
    {
      "statement": "On the challenge's five-fold split, the mean Dice was 0.554 and mean lesion-level F1 was 0.528 without scribbles, rising to 0.751 and 0.733 after five correction rounds.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-02T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    },
    {
      "statement": "The autoPET/CT V challenge addresses the complexity of automated lesion segmentation in whole-body PET/CT caused by varying physiological tracer uptake patterns and differing lesion appearances across tracers.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-02T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    },
    {
      "statement": "The submitted model is a scribble-conditioned residual encoder U-Net operating on four input channels: CT, PET, and a sparse scribble map for each of foreground and background.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-02T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    },
    {
      "statement": "The researchers concluded that interaction largely compensates for how well or badly a given model segments unaided.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-02T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    }
  ],
  "note": "A signature proves who filed this and that it has not changed since. It never makes a claim true."
}