Pith. sign in

Paper Citation Record · LEDGER

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions

As of 16 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 1 inbound Pith citation observation for arXiv:1908.09094.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
1908.09094 v3

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T11:33:59.388397Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T17:14:43.057308Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

12 of 12 outbound references displayed

  • verified exact1
  • verified fuzzy7
  • unresolved2
  • parse uncertain2
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 94755ede-7607-4f2d-acca-37e2aa912433 · outbound

This paper cites an unresolved cited work.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-14T11:33:59.581360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.345516Z digest=sha256:9836ede76ac04538f2088ca477c1993461a5ece3752b583550cd8f6b7e374050

Observation 94e4001a-15cd-430c-95b6-6fb1d13d663b · outbound

This paper cites ,K}, solve the following for yj = yj(c) (set y1(c) = 1) and let xj(c) for each j≥ 2 denote the corresponding minimizer: inf x∈[m(µj),m(µ1)] KLinf(µ1, x) + yj KLinf(µj, x) = c.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions ,K}, solve the following for yj = yj(c) (set y1(c) = 1) and let xj(c) for each j≥ 2 denote the corresponding minimizer: inf x∈[m(µj),m(µ1)] KLinf(µ1, x) + yj KLinf(µj, x) = c

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T11:33:59.555707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.354638Z digest=sha256:265f440a7d03b186017da0e3ed5c97e0375db8aa32fe1eb2c114c9631e586931

Observation ff031aa8-a61f-4151-9855-bfde8cbb5393 · outbound

This paper cites an unresolved cited work.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions Unresolved cited work

Reference 3

Resolution
parse uncertain
raw_fallback, observed 2026-08-14T11:33:59.567047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.350405Z digest=sha256:38f2b67485b0bf306f885c84a2f5d53a6fed7e8e069b152d8938aadfd6413327

Observation 2472ca28-5307-4c6f-9d20-240cf5011c28 · outbound

This paper cites ,K} and V(µ) = c∗t∗ 1.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions ,K} and V(µ) = c∗t∗ 1

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T11:33:59.527210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.362313Z digest=sha256:58c9a504101954d8b8d3b8f99b323da30929d7436d4430c76308df69a587e72c

Observation 91ad6545-0a7c-4fc4-9fd8-b9e4eb7189d9 · outbound

This paper cites an unresolved cited work.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-14T11:33:59.540383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.358411Z digest=sha256:04ee4a8729d7acd7fd081528f5edaaeb8d9fbf00e1e93d398ca7c9280f8fc456

Observation de8c41cf-6138-49df-8235-c17af0651192 · outbound

This paper cites Lemma 28 For any ua∈ℜ , non-negative constants ˜Ba and rectangle Ga, P ( K⋂ a=1 { max λa∈Ga L(λa, m(µa), ˆµa(n))≥ ua,Cd a }) ≤ K ∏ a=1 e ˜Bae−taua.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions Lemma 28 For any ua∈ℜ , non-negative constants ˜Ba and rectangle Ga, P ( K⋂ a=1 { max λa∈Ga L(λa, m(µa), ˆµa(n))≥ ua,Cd a }) ≤ K ∏ a=1 e ˜Bae−taua

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T11:33:59.515356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.366286Z digest=sha256:b8ce2ea33368874afc428bf47b2a0759720b92b7b5264d5d7935a4a406b1c097

Observation 9c1c28cd-2484-43aa-841c-d831ac89f804 · outbound

This paper cites an unresolved cited work.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions Unresolved cited work

Reference 8

Resolution
parse uncertain
raw_fallback, observed 2026-08-14T11:33:59.501607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.373713Z digest=sha256:4df1fcdd8dd7309d7f00c268f9419ade3e3adf4154f8f3941bfd93e73fde6bba

Observation 1d131472-7da2-4f42-a0a9-b952639a4583 · outbound

This paper cites Thus, P ( K⋂ a=1 { max λa∈Ga L(λa, m(µa), ˆµa(n))≥ ua,Cd a }) ≤ P ( K⋂ a=1 { Sa(n,λa0)≥ Na(n)ua,Cd a }) ≤ P  1 Cde { K ∑ a=1 θaSa(n,λa0) } ≥ e { K ∑ a=1 θaNa(n)ua } .

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions Thus, P ( K⋂ a=1 { max λa∈Ga L(λa, m(µa), ˆµa(n))≥ ua,Cd a }) ≤ P ( K⋂ a=1 { Sa(n,λa0)≥ Na(n)ua,Cd a }) ≤ P  1 Cde { K ∑ a=1 θaSa(n,λa0) } ≥ e { K ∑ a=1 θaNa(n)ua } 

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T11:33:59.470162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.380915Z digest=sha256:34c82aad1305c313a0304fa90ddd466f6963281066f56f510f54006aa21c61d7

Observation a90ed438-03ba-4247-a472-81ccb230884e · outbound

This paper cites generalized likelihood ratio.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions generalized likelihood ratio

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T11:33:59.457388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.384331Z digest=sha256:87c640af6b2df0c9c75632a972d28d35845e4766a97d5bf87dce76df46bfbc2d

Observation b414ea7a-2ea3-44af-b67c-b5cae507c55e · outbound

This paper cites To this end, Figure 1 plots the ratio of average number of samples needed by AL1 to stop, and the lower bound on this quantity, as a function of log (δ).

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions To this end, Figure 1 plots the ratio of average number of samples needed by AL1 to stop, and the lower bound on this quantity, as a function of log (δ)

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T11:33:59.445129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.388397Z digest=sha256:b374f0bc0b779a4cd96b2a02f6e030d57073018778b82ff022a4a5a12e05a135

Observation 4867e33a-01ae-4273-b10a-1b07757a2399 · outbound

This paper cites Let Λa(θ,λa0) = log Eµa ( e{θ log(1−(X−m(µa))λa 10−(B− f (|Xi|))λa 20+|X−m(µa)|δa 1+|B− f (|X|)|δa 2)}) , and θa = arg max θ≥0 {θua− Λa(θ,λa0)}.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions Let Λa(θ,λa0) = log Eµa ( e{θ log(1−(X−m(µa))λa 10−(B− f (|Xi|))λa 20+|X−m(µa)|δa 1+|B− f (|X|)|δa 2)}) , and θa = arg max θ≥0 {θua− Λa(θ,λa0)}

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T11:33:59.482794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.377568Z digest=sha256:f395b48ce7fdb9658ea27cecad63428144abb71264b271033e34a98de0ee040b

Observation 29296a21-edbd-4acd-9a03-b7e9f7c66ba8 · outbound

This paper cites doi: 10.1007/s10994-011-5257-4.

Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions doi: 10.1007/s10994-011-5257-4

Reference 2011

Resolution
verified exact
doi, observed 2026-08-14T11:33:59.430634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-08-14T11:33:59.338519Z digest=sha256:c281e49a5058cc732d29372aa118f6062b7e8f475bf145ab25a009837f73b24f

Pith citing papers

Observation 498bd2ba-3821-46d7-be3e-6a9a3eedd7ac · inbound

Decision-Centric Large Deviations for Data-Driven Capital Buffers in Ruin Models cites this paper.

Decision-Centric Large Deviations for Data-Driven Capital Buffers in Ruin Models Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T17:14:43.057308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T17:14:43.057308Z digest=sha256:b7d6045e16d98197282b8773f9d9844e0f2dc6d54c3533693daddf673e418dd4