Buildability / Receipt
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
/buildability/on-the-benefits-of-free-exploration-for-regret-minimization-in-multi-armed-bandits
Subject: On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits
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.
Data
Hou, Zhong and Tan # Appendix G. Technical Lemmas - Lemma 21 Given any instance ν and any consistent algorithm π with a deterministic FE policy πFE, with FE budget TFE
Truth Boundary
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.
Compute
Hou, Zhong and Tan # Appendix G. Technical Lemmas - Lemma 21 Given any instance ν and any consistent algorithm π with a deterministic FE policy πFE, with FE budget TFE, the regret saved by the algorithm π is upper bounded by Save∗(ν,TFE) as in (3). Proof Let KLi := Dkl(νi,ν1) and RTFE+1:T = RTFE+1:T(π;ν)
Inference
Hou, Zhong and Tan # Appendix G. Technical Lemmas - Lemma 21 Given any instance ν and any consistent algorithm π with a deterministic FE policy πFE, with FE budget TFE, the regret saved by the algorithm π is upper bounded by Save∗(ν,TFE) as in (3). Proof Let KLi := Dkl(νi,ν1) and RTFE+1:T = RTFE+1:T(π;ν)
Hardware
Hou, Zhong and Tan # Appendix G. Technical Lemmas - Lemma 21 Given any instance ν and any consistent algorithm π with a deterministic FE policy πFE, with FE budget TFE, the regret saved by the algorithm π is upper bounded by Save∗(ν,TFE) as in (3). Proof Let KLi := Dkl(νi,ν1) and RTFE+1:T = RTFE+1:T(π;ν)
Receipt path
/buildability/on-the-benefits-of-free-exploration-for-regret-minimization-in-multi-armed-bandits
Paper ref
on-the-benefits-of-free-exploration-for-regret-minimization-in-multi-armed-bandits
arXiv id
2605.25789
Generated at
2026-05-27T00:05:19.913Z
Evidence freshness
stale
Last verification
2026-05-27T00:05:19.913Z
Sources
3
References
0
Coverage
50%
Lineage hash
e640cd8cc06ac126da9438641bd92b8430c99a79bc690776782c9c5049a06e7e
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.
Some score or evidence fields are outside the preferred freshness window.
repo_url
references