Evidence Receipt. Related Resources.
Evaluating Generative Models via One-Dimensional Code Distributions
Use This Via API or MCP
Use this Signal Canvas via API or MCP
Route this paper proof surface into REST, MCP, or developer workflows while preserving the same evidence receipt and related-resource context.
Page Freshness
Signal Canvas proof surface
Canonical route: /signal-canvas/evaluating-generative-models-via-one-dimensional-code-distributions
- 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
Evaluating Generative Models via One-Dimensional Code Distributions
Canonical ID evaluating-generative-models-via-one-dimensional-code-distributions | Route /signal-canvas/evaluating-generative-models-via-one-dimensional-code-distributions
REST example
curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/evaluating-generative-models-via-one-dimensional-code-distributionsMCP example
{
"tool": "search_signal_canvas",
"arguments": {
"mode": "paper",
"paper_ref": "evaluating-generative-models-via-one-dimensional-code-distributions",
"query_text": "Summarize Evaluating Generative Models via One-Dimensional Code Distributions"
}
}source_context
{
"surface": "signal_canvas",
"mode": "paper",
"query": "Evaluating Generative Models via One-Dimensional Code Distributions",
"normalized_query": "2603.08064",
"route": "/signal-canvas/evaluating-generative-models-via-one-dimensional-code-distributions",
"paper_ref": "evaluating-generative-models-via-one-dimensional-code-distributions",
"topic_slug": null,
"benchmark_ref": null,
"dataset_ref": null
}Preparing verified analysis
Dimensions overall score 8.0
GitHub Code Pulse
No public code linked for this paper yet.
Claim map
- Evidencepartial
Most evaluations of generative models rely on feature-distribution metrics such as FID, which operate on continuous recognition features that are explicitly trained to be invariant to appearance variations, and thus discard cues critical for perceptual quality.
ImplicationpartialThe abstract explicitly states this as a motivation for the proposed method.
Verificationpartialpartial
- Evidencepartial
where modern 1D image tokenizers compactly encode both semantic and perceptual information and quality manifests as predictable token statistics.
ImplicationpartialThe abstract directly states this as a premise for their evaluation approach.
Verificationpartialpartial
- Evidencepartial
We introduce Codebook Histogram Distance (CHD), a training-free distribution metric in token space
ImplicationpartialThe abstract introduces CHD and explicitly states its characteristics.
Verificationpartialpartial
- Evidencepartial
and Code Mixture Model Score (CMMS), a no-reference quality metric learned from synthetic degradations of token sequences.
ImplicationpartialThe abstract introduces CMMS and explicitly states its characteristics.
Verificationpartialpartial
- Evidencepartial
we further propose VisForm, a benchmark of 210K images spanning 62 visual forms and 12 generative models with expert annotations.
ImplicationpartialThe abstract provides specific details about the VisForm benchmark.
Verificationpartialpartial
- Evidencepartial
Across AGIQA, HPDv2/3, and VisForm, our token-based metrics achieve state-of-the-art correlation with human judgments
ImplicationpartialThe abstract directly states the performance of their metrics compared to human judgments across multiple benchmarks.
Verificationpartialpartial
- Evidencepartial
and we will release all code and datasets to facilitate future research.
ImplicationpartialThe abstract explicitly states their intention to release resources.
Verificationpartialpartial
