Skip to main content
← Back to Paper

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

Stale32d ago20 refs / 3 sources / Verification pending
Export BriefOpen in Build LoopConnect with Author
View PDF ↗
Viability
0.0/10

Compared to this week’s papers

Verification pending

Use This Via API or MCP

Use Signal Canvas as the narrative proof surface

Signal Canvas is the citation-first public layer for turning one paper into a structured commercialization narrative. Use it to hand off into REST, MCP, Build Loop, and launch-pack execution without losing source lineage.

Signal Canvas APIPaper Proof PageOpen Build LoopLaunch Pack Example

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh

stale
Proof freshness
stale
Proof status
unverified
Display score
3/10
Last proof check
2026-03-30
Score updated
2026-04-02
Score fresh until
2026-05-02
References
20
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

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

Canonical ID why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh | Route /signal-canvas/why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh",
    "query_text": "Summarize Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models",
  "normalized_query": "2603.26410",
  "route": "/signal-canvas/why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh",
  "paper_ref": "why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 7

References: 20

Proof: Verification pending

Freshness state: computing

Source paper: Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

PDF: https://arxiv.org/pdf/2603.26410v1

Source count: 3

Coverage: 50%

Last proof check: 2026-03-30T21:59:36.306Z

Signal Canvas receipt window

Not build-ready: Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

/buildability/why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh

Ignoreblocked

Subject: Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

Verdict

Ignore

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

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh

Paper ref

why-models-know-but-don-t-say-chain-of-thought-faithfulness-divergence-between-thinking-tokens-and-answers-in-open-weigh

arXiv id

2603.26410

Freshness

Generated at

2026-03-30T21:59:36.306Z

Evidence freshness

stale

Last verification

2026-03-30T21:59:36.306Z

Sources

3

References

20

Coverage

50%

Hash state

Lineage hash

0f1a8641d7eed9673cbcab90454e65d725d46a8310110e5b750e3d90b60f3508

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

  • Missing: repo_url
  • Missing: proof_status
  • Missing: distribution_readiness_scores
  • Unknown: distribution readiness has not been computed yet
  • Unknown: proof verification has not been recorded yet

20 refs / 3 sources / Verification pending

repo_url

proof_status

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.
Open receiptAPI receiptBuild LoopPaper proof pageProof divergenceDivergence APIBrier outcomes API

Paper Conversation

Citation-first answers with explicit evidence receipts, disagreement handling, commercialization framing, and next actions.

Paper Mode

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

Overall score: 3/10
Lineage: 0f1a8641d7ee…

Canonical Paper Receipt

Last verification: 2026-03-30T21:59:36.306Z

Freshness: stale

Proof: unverified

Repo: missing

References: 20

Sources: 3

Coverage: 50%

Missingness
  • - repo_url
  • - proof_status
  • - distribution_readiness_scores
Unknowns
  • - distribution readiness has not been computed yet
  • - proof verification has not been recorded yet

Preparing verified analysis

Dimensions overall score 3.0

GitHub Code Pulse

No public code linked for this paper yet.

Key claims

Strong 7Mixed 0Weak 0
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.

Startup potential card

Startup potential card preview
Share on XLinkedIn

Related Resources

Related resources will appear here when this paper maps cleanly to topic, benchmark, or dataset surfaces.

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $10K - $14K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.