Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T03:59:13.198980Z
Paper Citation Record · LEDGER
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents
As of 11 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2605.08721.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
22 of 22 outbound references displayed
- verified exact1
- verified fuzzy15
- unresolved4
- parse uncertain0
- malformed identifier0
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 9cad5851-df3c-427d-b3b2-78398015ea4e · outbound
This paper cites TextArena.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents TextArena
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T06:46:43.663160Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 82090acd-4b38-49fd-97da-c4d435347163 · outbound
This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Kimi k1.5: Scaling Reinforcement Learning with LLMs
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T06:46:43.680046Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 431c2fb2-bbba-4a20-8eec-e496e562c7f3 · outbound
This paper cites Qwen3 Technical Report.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Qwen3 Technical Report
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T06:46:43.668302Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 8a7a4dd3-ee0f-49d9-8b87-4e708599fdad · outbound
This paper cites We select the hyperbolic tangent kernel: σ(t) =P(S |δ (t)) = 1−tanh(δ (t)).(19).
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents We select the hyperbolic tangent kernel: σ(t) =P(S |δ (t)) = 1−tanh(δ (t)).(19)
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:16:44.263645Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 9c580a0b-0795-4208-a5c3-f1019166d0ce · outbound
This paper cites (20) Substituting these specific kernels yields the instan- tiation used in DEPT:λ (t) =σ (t) ·γ (t).
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents (20) Substituting these specific kernels yields the instan- tiation used in DEPT:λ (t) =σ (t) ·γ (t)
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.514143Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 16cb49d1-f37f-4326-b177-64804ece2077 · outbound
This paper cites Thus, the advantage for the M dominant samples ap- proaches zero.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Thus, the advantage for the M dominant samples ap- proaches zero
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:16:44.270619Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation b39a3ee6-2275-412c-bb41-1156f134116a · outbound
This paper cites Since Vmax ≥R p(τ) for τ∈ D dom, the term (Rp(τ)−V max) is strictly non-positive.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Since Vmax ≥R p(τ) for τ∈ D dom, the term (Rp(τ)−V max) is strictly non-positive
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.496179Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 48f3a4ff-26f5-4f7d-a4af-4ef869cfb9bb · outbound
This paper cites The term (Rp(τ ′)−V min) is maximized, as- signing a high positive weight to these sparse signals.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents The term (Rp(τ ′)−V min) is maximized, as- signing a high positive weight to these sparse signals
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.509147Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 2f249552-9e3e-4e32-a3a0-9d0774f9e6c9 · outbound
This paper cites These benchmark cover a wide range of topics including algebra, geometry, and competitive mathematic.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents These benchmark cover a wide range of topics including algebra, geometry, and competitive mathematic
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:16:44.267528Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation bb0b6bde-3668-497d-bccf-2ae639e91b3d · outbound
This paper cites I think this is fair because ... [ Propose ] $X . XX \.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents I think this is fair because ... [ Propose ] $X . XX \
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:16:44.273806Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 302a32a7-d7b9-46a8-aa0b-d416678ab315 · outbound
This paper cites an unresolved cited work.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T17:21:42.503866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 49df0166-9fba-4738-aebe-e3279c1b1253 · outbound
This paper cites an unresolved cited work.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T17:21:42.543660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 448ad6b4-0ef4-4c6d-bf58-66017103a6bb · outbound
This paper cites comb " in a context that must naturally arise during the conversation . For example , if you are discussing hair care or grooming , the word.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents comb " in a context that must naturally arise during the conversation . For example , if you are discussing hair care or grooming , the word
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.557399Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6978db0c-967f-475a-8092-6eda30fdc18d · outbound
This paper cites an unresolved cited work.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T17:16:44.277303Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a087d721-eac2-4f96-a582-897383dd0a15 · outbound
This paper cites an unresolved cited work.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Unresolved cited work
Reference 15
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T17:21:42.560930Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ae9d90af-ed9d-494e-9b67-fe50b83ec2ae · outbound
This paper cites I think this is fair because ... [ Propose ] $X . XX.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents I think this is fair because ... [ Propose ] $X . XX
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.531411Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 4960f535-30d1-4357-9f15-116136126590 · outbound
This paper cites - This means Player 1 would receive $0 .01 of the total $2 .00.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents - This means Player 1 would receive $0 .01 of the total $2 .00
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.535189Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 844158cb-a80c-40eb-8845-ccd689c1a0ce · outbound
This paper cites They would get only 0.5% of the total $2 .00 , which is $0 .01.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents They would get only 0.5% of the total $2 .00 , which is $0 .01
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.525509Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 2bd470fe-ba43-4f03-9016-a32af0221924 · outbound
This paper cites - Accepting the current proposal would result in Player 1 receiving $0 .01 , which is far below their required $1 .60.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents - Accepting the current proposal would result in Player 1 receiving $0 .01 , which is far below their required $1 .60
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.538882Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation e963184d-5e71-4446-8eb8-8eebe0173228 · outbound
This paper cites - By rejecting , Player 1 maintains the option to propose a better deal in the next round or wait for Player 0 to make a more fair offer.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents - By rejecting , Player 1 maintains the option to propose a better deal in the next round or wait for Player 0 to make a more fair offer
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.553081Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f7968f5a-765f-4791-b4b3-d8594bb9754c · outbound
This paper cites Player 1 would be worse off than refusing to cooperate at all ( which would result in $0 .00 for both players ).
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents Player 1 would be worse off than refusing to cooperate at all ( which would result in $0 .00 for both players )
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.519542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 5d6f9fcd-a8ba-481e-9017-3c333facb65d · outbound
This paper cites For example , a proposal like $1 .60 for Player 1 and $0 .40 for Player 0 would satisfy Player 1's instructions.
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents For example , a proposal like $1 .60 for Player 1 and $0 .40 for Player 0 would satisfy Player 1's instructions
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T17:21:42.548185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Pith citing papers
No inbound Pith citation observations are available.