$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
Last proof check: 2026-05-18
Score updated: 2026-05-18
Score fresh until: 2026-06-17
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 f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data | Route /signal-canvas/f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data",
    "query_text": "Summarize $f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data",
  "normalized_query": "2605.15417",
  "route": "/signal-canvas/f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data",
  "paper_ref": "f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data",
  "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: $f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

PDF: https://arxiv.org/pdf/2605.15417v1

Source count: 3

Coverage: 50%

Last proof check: 2026-05-18T20:31:45.547Z

Signal Canvas receipt window

Watch and verify: $f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

/buildability/f-trajectory-balance-a-loss-family-for-tuning-gflownets-generative-models-and-llms-with-off-and-on-policy-data

Watchwatch

Subject: $f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

Verdict

Watch

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface