Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/curia-2-scaling-self-supervised-learning-for-radiology-foundation-models

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-04-03
Score updated: 2026-04-03
Score fresh until: 2026-05-03
References: 0
Source count: 0
Coverage: 33%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID curia-2-scaling-self-supervised-learning-for-radiology-foundation-models | Route /signal-canvas/curia-2-scaling-self-supervised-learning-for-radiology-foundation-models

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/curia-2-scaling-self-supervised-learning-for-radiology-foundation-models

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "curia-2-scaling-self-supervised-learning-for-radiology-foundation-models",
    "query_text": "Summarize Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models",
  "normalized_query": "2604.01987",
  "route": "/signal-canvas/curia-2-scaling-self-supervised-learning-for-radiology-foundation-models",
  "paper_ref": "curia-2-scaling-self-supervised-learning-for-radiology-foundation-models",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

PDF: https://arxiv.org/pdf/2604.01987v1

Source count: Pending verification

Coverage: 33%

Last proof check: 2026-04-03T20:50:40.576Z

Signal Canvas receipt window

Watch and verify: Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

/buildability/curia-2-scaling-self-supervised-learning-for-radiology-foundation-models

Watchwatch

Subject: Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
Curia-2, which significantly improves the original pre-training strategy and representation quality to better capture the specificities of radiological data.
Implicationpartial
Directly stated in abstract with clear comparison to previous framework
Verificationpartial
partial
Evidencepartial
The proposed methodology enables scaling the architecture up to billion-parameter Vision Transformers, marking a first for multi-modal CT and MRI FMs.
Implicationpartial
Explicitly stated as a first achievement in the field
Verificationpartial
partial
Evidencepartial
Our results demonstrate that Curia-2 outperforms all FMs on vision-focused tasks
Implicationpartial
Directly stated in results section of abstract
Verificationpartial
partial
Evidencepartial
fairs competitively to vision-language models on clinically complex tasks such as finding detection.
Implicationpartial
Directly stated in results section of abstract
Verificationpartial
partial
Evidencepartial
we formalize the evaluation of these models by extending and restructuring CuriaBench into two distinct tracks: a 2D track tailored for slice-based vision models and a 3D track for volumetric benchmarking.
Implicationpartial
Explicitly stated as a formalization of evaluation methodology
Verificationpartial
partial
Evidencepartial
The rapid growth of medical imaging has fueled the development of Foundation Models (FMs) to reduce the growing, unsustainable workload on radiologists.
Implicationpartial
Directly stated as motivation in abstract
Verificationpartial
partial
Evidencepartial
Weights will be made publicly available to foster further research.
Implicationpartial
Explicit commitment stated in abstract
Verificationpartial
partial
Evidencepartial
there remains significant room to optimize how these models learn from complex radiological volumes.
Implicationpartial
Implied as motivation for the work, though not explicitly quantified
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface