Buildability / Receipt
Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation
This public receipt window renders only fields present in the canonical receipt object, deterministic fixture receipt, or canonical evidence receipt. Missing compute, demo, hash, signature, approval, telemetry, and adoption fields stay explicit.
Public buildability page receipt window
Ready for execution: Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation
/buildability/subliminal-transfer-of-unsafe-behaviors-in-ai-agent-distillation
Subject: Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation
Verdict
Build Now
Verdict is Build Now because viability and implementation proof cleared the Wave 1 scaffold thresholds.
Time to first demo
Insufficient data
No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.
Compute envelope
Data
dangjacob101@g.ucla.edu Brian Y. Xie Santa Monica College xie brian yang01@student.smc.edu Omar G. Younis Mila, Silverstream AI omar@silverstream.ai
Compute
strongest effects. Teacher Student Teacher Bias Baseline Bias Student Bias Increase (pp) Llama 8B Llama 8B 100% 5% 30% +25 Llama 3B Llama 3B 80% 10% 15% +5 Llama 8B Llama 3B 100% 10% 55% +45 Llama 3B Llama 8B 85% 5% 5% 0 Llama 8B Qwen 7B 95% 0% 45% +45 Control (Rand) Llama 8B 0% 5% 5% 0 Transfer Persists in Free-Form C
Inference
strongest effects. Teacher Student Teacher Bias Baseline Bias Student Bias Increase (pp) Llama 8B Llama 8B 100% 5% 30% +25 Llama 3B Llama 3B 80% 10% 15% +5 Llama 8B Llama 3B 100% 10% 55% +45 Llama 3B Llama 8B 85% 5% 5% 0 Llama 8B Qwen 7B 95% 0% 45% +45 Control (Rand) Llama 8B 0% 5% 5% 0 Transfer Persists in Free-Form C
Hardware
strongest effects. Teacher Student Teacher Bias Baseline Bias Student Bias Increase (pp) Llama 8B Llama 8B 100% 5% 30% +25 Llama 3B Llama 3B 80% 10% 15% +5 Llama 8B Llama 3B 100% 10% 55% +45 Llama 3B Llama 8B 85% 5% 5% 0 Llama 8B Qwen 7B 95% 0% 45% +45 Control (Rand) Llama 8B 0% 5% 5% 0 Transfer Persists in Free-Form C
Evidence ids
Receipt path
/buildability/subliminal-transfer-of-unsafe-behaviors-in-ai-agent-distillation
Paper ref
subliminal-transfer-of-unsafe-behaviors-in-ai-agent-distillation
arXiv id
2604.15559
Freshness
Generated at
2026-04-20T20:24:04.238Z
Evidence freshness
fresh
Last verification
2026-04-20T20:24:04.238Z
Sources
4
References
0
Coverage
50%
Hash state
Lineage hash
02b001fdb60b8c7142a3a287066327cd93a5f9433db89be41c4cba760c3a222e
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: references
- Missing: proof_status
- Missing: paper_extraction_scorecards
- Unknown: proof verification has not been recorded yet
Canonical opportunity-kernel evidence is available for this receipt window.
references
proof_status
Truth Boundary
External gate remains unresolved for live deployment claims.
Buildability surfaces only report computed viability and proof receipts. They do not claim live production usage, pilot outcomes, founder sign-off, or external adoption unless explicitly sourced.