Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning

Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-04-27
Score updated: 2026-04-27
Score fresh until: 2026-05-27
References: 0
Source count: 3
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 preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning | Route /signal-canvas/preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning",
    "query_text": "Summarize Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning",
  "normalized_query": "2604.22229",
  "route": "/signal-canvas/preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning",
  "paper_ref": "preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 0

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning

PDF: https://arxiv.org/pdf/2604.22229v1

Source count: 3

Coverage: 50%

Last proof check: 2026-04-27T20:15:42.107Z

Signal Canvas receipt window

Watch and verify: Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning

/buildability/preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-learning

Watchwatch

Subject: Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning

Verdict

Watch

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

Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface