Interpretable long-term traffic modelling on national road networks using theory-informed deep learning

Interpretable long-term traffic modelling on national road networks using theory-informed deep learning | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning

stale

Proof freshness: stale
Proof status: unverified
Display score: 4/10
Last proof check: 2026-03-30
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 51
Source count: 6
Coverage: 50%

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 interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning | Route /signal-canvas/interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning",
    "query_text": "Summarize Interpretable long-term traffic modelling on national road networks using theory-informed deep learning"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Interpretable long-term traffic modelling on national road networks using theory-informed deep learning",
  "normalized_query": "2603.26440",
  "route": "/signal-canvas/interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning",
  "paper_ref": "interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: 51

Proof: Verification pending

Freshness state: computing

Source paper: Interpretable long-term traffic modelling on national road networks using theory-informed deep learning

PDF: https://arxiv.org/pdf/2603.26440v1

Source count: 6

Coverage: 50%

Last proof check: 2026-03-30T21:57:14.175Z

Signal Canvas receipt window

Not build-ready: Interpretable long-term traffic modelling on national road networks using theory-informed deep learning

/buildability/interpretable-long-term-traffic-modelling-on-national-road-networks-using-theory-informed-deep-learning

Ignoreblocked

Subject: Interpretable long-term traffic modelling on national road networks using theory-informed deep learning

Verdict

Ignore

Verdict is Ignore because current viability and proof state do not clear the buildability gate.

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
Under random cross-validation, DeepDemand achieves an R2 of 0.718 and an MAE of 7406 vehicles, outperforming linear, ridge, random forest, and gravity-style baselines.
Implicationpartial
This is a direct quantitative result stated in the abstract and supported by the definition of R2 and MAE metrics in the text.
Verificationpartial
partial
Evidencepartial
Performance remains strong under spatial cross-validation (R2 = 0.665), indicating good geographic transferability.
Implicationpartial
This is a direct quantitative result stated in the abstract, specifically addressing the transferability aspect.
Verificationpartial
partial
Evidencepartial
The framework integrates a competitive two-source Dijkstra procedure for local origin-destination (OD) region extraction and OD pair screening with a differentiable architecture modelling OD interactions and travel-time deterrence.
Implicationpartial
This describes a specific component of the proposed methodology, clearly outlined in the abstract.
Verificationpartial
partial
Evidencepartial
The framework integrates a competitive two-source Dijkstra procedure for local origin-destination (OD) region extraction and OD pair screening with a differentiable architecture modelling OD interactions and travel-time deterrence.
Implicationpartial
This describes a core technical aspect of the DeepDemand framework, as stated in the abstract.
Verificationpartial
partial
Evidencepartial
The model is evaluated using eight years (2017-2024) of observations on the UK strategic road network, covering 5088 highway segments.
Implicationpartial
This specifies the dataset and scope of the evaluation, providing verifiable details.
Verificationpartial
partial
Evidencepartial
Interpretability analysis reveals a stable nonlinear travel-time deterrence pattern, key socioeconomic drivers of demand, and polycentric OD interaction structures aligned with major employment centres and transport hubs.
Implicationpartial
This is a specific finding from the interpretability analysis, as stated in the abstract.
Verificationpartial
partial
Evidencepartial
Interpretability analysis reveals a stable nonlinear travel-time deterrence pattern, key socioeconomic drivers of demand, and polycentric OD interaction structures aligned with major employment centres and transport hubs.
Implicationpartial
This is a specific finding from the interpretability analysis, as stated in the abstract.
Verificationpartial
partial
Evidencepartial
Unless otherwise stated, the default configuration uses multilayer perceptrons (MLPs) for fO, fD, fOD, and ft. The node encoders fO and fD use hidden and output dimensions of [16, 16], the OD pair scorer fOD uses dimensions 11 [16, 8], and the travel-time deterrence network ft uses dimensions [16, 16].
Implicationpartial
This details the specific neural network architecture and its configuration, which is a technical aspect of the method.
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.

Interpretable long-term traffic modelling on national road networks using theory-informed deep learning

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface