Paper Citation Record · LEDGER

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning

As of 16 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2605.29782.

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

pith.paper-citation-record.v1
2605.29782 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T04:26:24.074391Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

19 of 19 outbound references displayed

verified exact0
verified fuzzy0
unresolved14
parse uncertain0
malformed identifier2
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c6e7e5f7-7236-48cd-a1f1-03b73300bfd1 · outbound

This paper cites Offline Reinforcement Learning with Implicit Q-Learning.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Offline Reinforcement Learning with Implicit Q-Learning

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T08:43:15.445367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 29c8779f-fdda-409e-80f1-508e656c1a1f · outbound

This paper cites MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T08:43:14.669708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0a303672-891d-4b0b-9604-177825d56b39 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T08:43:14.666563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5f312830-4cf0-4aa6-affd-cbadde38aa03 · outbound

This paper cites Assumption A.1(Answer Parsing).The final answer for both states is parsed from one action a, which corresponds to one token.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Assumption A.1(Answer Parsing).The final answer for both states is parsed from one action a, which corresponds to one token

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d212c651-8b0a-4eaa-b0c5-a1c230eb079b · outbound

This paper cites an unresolved cited work.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fab8912-a53d-4dbf-8ea5-5f512bcc4d39 · outbound

This paper cites Thus, the corresponding eigenvalue isλ ∥ = dϵ ∥x∥2 2+dϵ.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Thus, the corresponding eigenvalue isλ ∥ = dϵ ∥x∥2 2+dϵ

Reference 6

Resolution: malformed identifier; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f473ed68-7dda-4f91-8346-1d113bd5bf45 · outbound

This paper cites Suppose we continue the generation of s1 and s2 until (T−1) -th state located at the token index ℓ.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Suppose we continue the generation of s1 and s2 until (T−1) -th state located at the token index ℓ

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c78888f1-c705-46c0-b21e-f0723b0e069c · outbound

This paper cites A General Case In previous section, we only prove the correlation between MinDistanceof hidden states and final reward in a simple case, where.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning A General Case In previous section, we only prove the correlation between MinDistanceof hidden states and final reward in a simple case, where

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be727993-136a-4e6c-8cbd-2ead0138ad68 · outbound

This paper cites an unresolved cited work.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7956b08b-ea97-42dc-be55-b03b2198d1ae · outbound

This paper cites an unresolved cited work.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5831e3c3-ec11-4cef-a11d-a72dbd323a95 · outbound

This paper cites To expand Theorem A.11 to general case, we need to re- view these three assumptions.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning To expand Theorem A.11 to general case, we need to re- view these three assumptions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb323b79-50ff-480c-8f3f-c00ae34c329a · outbound

This paper cites Now, the problem becomes, the relation between the final reward of ˆs2 and s2.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Now, the problem becomes, the relation between the final reward of ˆs2 and s2

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d50afa9f-a2d0-42ad-a1e7-4faa3360f6f2 · outbound

This paper cites , η 2}, the dot product score p1,i is replicated ˆri times in the first block of p2, where ˆri are nonnegative integers satisfyingPη2 i=1 ˆri =η 1.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning , η 2}, the dot product score p1,i is replicated ˆri times in the first block of p2, where ˆri are nonnegative integers satisfyingPη2 i=1 ˆri =η 1

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9977850-c895-4943-8fe6-87ce659b43e2 · outbound

This paper cites , ℓ}, the entry p2,η1+i−η2 in p2 equalsp 1,i +δ i for someδ i ∈R.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning , ℓ}, the entry p2,η1+i−η2 in p2 equalsp 1,i +δ i for someδ i ∈R

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bc1ee54-db30-4a84-bab3-7340a6b767aa · outbound

This paper cites Without loss of generality, we assume s1’s hidden states Xl 1 ∈R η1,d and s2’s hidden states Xl 2 ∈R η2,d, where η1 > η2.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Without loss of generality, we assume s1’s hidden states Xl 1 ∈R η1,d and s2’s hidden states Xl 2 ∈R η2,d, where η1 > η2

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ec788a2-686d-4ecf-8d56-389ead59fee9 · outbound

This paper cites Now, we need to build correlation between ˆXl 2 and Xl.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Now, we need to build correlation between ˆXl 2 and Xl

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df0f422-faef-42d5-9afb-28ed16c62a59 · outbound

This paper cites important.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning important

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 710fa810-ac94-409c-bb64-0de3069c356f · outbound

This paper cites an unresolved cited work.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-29T08:37:07.868266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da1feee1-300c-4718-86d9-f081ce785f5b · outbound

This paper cites The result is presented in Table 10.

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning The result is presented in Table 10

Reference 19

Resolution: malformed identifier; arxiv_id, observed 2026-06-29T08:43:15.447991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation f36e8105-ebcc-453b-9b13-0eabe99137a5 · inbound

APeB: Benchmarking Personalization Ability of Large Language Model Agents cites this paper.

APeB: Benchmarking Personalization Ability of Large Language Model Agents Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T04:26:24.074391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.