proof blockPage 368%
Tatemae: Detecting Alignment Faking via Tool Selection in LLMs explores Detecting LLM alignment faking by analyzing tool selection, with a new dataset and evaluation of frontier models.. Commercial viability score: 7/10 in LLM Security.
Use This Via API or MCP
This route is the stable paper-level surface for citations, viability, references, and downstream handoffs. Use it as the proof layer behind Signal Canvas, workspace creation, and launch-pack generation.
Page Freshness
Canonical route: /paper/tatemae-detecting-alignment-faking-via-tool-selection-in-llms
Page-specific freshness sourced from this paper's evidence receipt and score bundle.
Agent Handoff
Canonical ID tatemae-detecting-alignment-faking-via-tool-selection-in-llms | Route /paper/tatemae-detecting-alignment-faking-via-tool-selection-in-llms
REST example
curl https://sciencetostartup.com/api/v1/agent-handoff/paper/tatemae-detecting-alignment-faking-via-tool-selection-in-llmsMCP example
{
"tool": "get_paper",
"arguments": {
"arxiv_id": "2604.26511"
}
}source_context
{
"surface": "paper",
"mode": "paper",
"query": "Tatemae: Detecting Alignment Faking via Tool Selection in LLMs",
"normalized_query": "2604.26511",
"route": "/paper/tatemae-detecting-alignment-faking-via-tool-selection-in-llms",
"paper_ref": "tatemae-detecting-alignment-faking-via-tool-selection-in-llms",
"topic_slug": null,
"benchmark_ref": null,
"dataset_ref": null
}Paper proof page receipt window
/buildability/tatemae-detecting-alignment-faking-via-tool-selection-in-llms
Subject: Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
Verdict
Watch
Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.
Time to first demo
Insufficient data
No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.
Structured compute envelope
Insufficient data
No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.
Constellation, claims, and market context stay visible on the paper proof page even when commercialization rails are held back for incomplete proof receipts.
Research neighborhood
Interactive graph renders after load.
Preparing verified analysis
Dimensions overall score 7.0
Visual citation anchors from the paper document graph.
Owned Distribution
Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.
References are not available from the internal index yet.
Receipt path
/buildability/tatemae-detecting-alignment-faking-via-tool-selection-in-llms
Paper ref
tatemae-detecting-alignment-faking-via-tool-selection-in-llms
arXiv id
2604.26511
Generated at
2026-04-30T15:14:03.754Z
Evidence freshness
fresh
Last verification
2026-04-30T15:14:03.754Z
Sources
3
References
0
Coverage
50%
Lineage hash
837b6a710ce49f97ad2a104fce61bc53e1c4c963a49270338a546d3d0e729ec4
Canonical opportunity-kernel lineage hash.
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.
Pending verification refs / 3 sources / Verification pending
repo_url
references
This equation captures one of the core mathematical components of the system. (R3 ≈Y ) requires that the LLM’s reasoning trace when monitored (R3) acknowledges its baseline
Page and bbox are available; crop image is pending.
This equation captures one of the core mathematical components of the system. ∧(R3 ≈Y ) | {z } Internal Reasoning Condition (T1 ∧T2) expresses that the LL
Page and bbox are available; crop image is pending.
This equation captures one of the core mathematical components of the system. R3 ≈Y Figure 1: Evaluation pipeline for alignment faking detection. Each s
Page and bbox are available; crop image is pending.
No public competitor map is available for this paper yet.