NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution

NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution

stale

Proof freshness: stale
Proof status: unverified
Display score: 8/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

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 notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution | Route /signal-canvas/notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution",
    "query_text": "Summarize NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution",
  "normalized_query": "2603.05617",
  "route": "/signal-canvas/notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution",
  "paper_ref": "notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 7

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution

PDF: https://arxiv.org/pdf/2603.05617v1

Source count: Pending verification

Coverage: 17%

Last proof check: 2026-04-02T02:30:40.136Z

Signal Canvas receipt window

Watch and verify: NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution

/buildability/notai-ai-explainable-detection-of-machine-generated-text-via-curvature-and-feature-attribution

Watchwatch

Subject: NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution

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 7Mixed 0Weak 0

Evidencepartial
We present NOTAI.AI, an explainable framework for machine-generated text detection that extends Fast-DetectGPT by integrating curvature-based signals with neural and stylometric features in a supervised setting.
Implicationpartial
Directly and explicitly stated in the abstract as the core methodological contribution.
Verificationpartial
partial
Evidencepartial
The system combines 17 interpretable features, including Conditional Probability Curvature, ModernBERT detector score, readability metrics, and stylometric cues, within a gradient-boosted tree (XGBoost) meta-classifier
Implicationpartial
Explicitly stated in the abstract with specific feature examples listed.
Verificationpartial
partial
Evidencepartial
within a gradient-boosted tree (XGBoost) meta-classifier to determine whether a text is human- or AI-generated.
Implicationpartial
Directly stated in the abstract as the classification model used.
Verificationpartial
partial
Evidencepartial
Furthermore, NOTAI.AI applies Shapley Additive Explanations (SHAP) to provide both local and global feature-level attribution.
Implicationpartial
Explicitly stated in the abstract as a key component of the explainability approach.
Verificationpartial
partial
Evidencepartial
These attributions are further translated into structured natural-language rationales through an LLM-based explanation layer, which enables user-facing interpretability.
Implicationpartial
Directly stated in the abstract as a specific implementation detail for enhancing interpretability.
Verificationpartial
partial
Evidencepartial
The system is deployed as an interactive web application that supports real-time analysis, visual feature inspection, and structured evidence presentation.
Implicationpartial
Explicitly stated in the abstract as a deployment and interface claim.
Verificationpartial
partial
Evidencepartial
The source code and demo video are publicly available to support reproducibility.
Implicationpartial
Directly and explicitly stated in the abstract as a fact about availability.
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.

NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface