Buildability / Receipt
ASMR-Bench: Auditing for Sabotage in ML Research
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
Watch and verify: ASMR-Bench: Auditing for Sabotage in ML Research
/buildability/asmr-bench-auditing-for-sabotage-in-ml-research
Subject: ASMR-Bench: Auditing for Sabotage in ML Research
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.
Compute envelope
Data
safely deploying potentially subversive AI systems, and control evaluations test these protocols in specific settings such as code generation [27, 22], agentic tasks [28]
Compute
pruning [44], adversarial robustness [45, 46, 47], ML for COVID-19 [48], and ML reproducibility more broadly [49]. If unintentional design flaws of this kind are common enough to go undetected by peer review, intentional design sabotages that mimic them may be unincriminating and even harder to catch
Inference
pruning [44], adversarial robustness [45, 46, 47], ML for COVID-19 [48], and ML reproducibility more broadly [49]. If unintentional design flaws of this kind are common enough to go undetected by peer review, intentional design sabotages that mimic them may be unincriminating and even harder to catch
Hardware
pruning [44], adversarial robustness [45, 46, 47], ML for COVID-19 [48], and ML reproducibility more broadly [49]. If unintentional design flaws of this kind are common enough to go undetected by peer review, intentional design sabotages that mimic them may be unincriminating and even harder to catch
Evidence ids
Receipt path
/buildability/asmr-bench-auditing-for-sabotage-in-ml-research
Paper ref
asmr-bench-auditing-for-sabotage-in-ml-research
arXiv id
2604.16286
Freshness
Generated at
2026-04-20T20:23:20.695Z
Evidence freshness
stale
Last verification
2026-04-20T20:23:20.695Z
Sources
3
References
0
Coverage
50%
Hash state
Lineage hash
0a81c5ad90b221bc89d6d8d57de485295e91d134c330edb115949d10555c7854
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: references
- Missing: proof_status
- Unknown: proof verification has not been recorded yet
Some score or evidence fields are outside the preferred freshness window.
repo_url
references
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, public Brier calibration, judge divergence, or external adoption unless explicitly sourced.