Paper Citation Record · LEDGER

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing

As of 19 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2608.08889.

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

pith.paper-citation-record.v1
2608.08889 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:26:47.868491Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy1
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2a9f874b-4792-4038-89e3-ab08e1a80f84 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Constitutional AI: Harmlessness from AI Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.479715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e58e54e-fcfd-4cc8-a06d-b21552931a9c · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.902591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7e14900b-7023-41e4-a48c-165066c526b0 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.885263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fbdbb7d4-afda-4af8-86a1-e4dcdd2a8be1 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.570294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f00ffde-6f26-41c2-afeb-c0680a620836 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.589373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b36d6a3-d771-474f-83a6-2ee76a7005c7 · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.619998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdd9958b-cf13-4482-b772-91360af1ffd4 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.859131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 568f6374-13f1-4272-b137-e56d9bc93cdb · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.815668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dbaacdfa-cf0d-45d9-9a3f-f527ed5cde2f · outbound

This paper cites Large Language Models are Zero-Shot Rankers for Recommender Systems.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Large Language Models are Zero-Shot Rankers for Recommender Systems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.647375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4053e7c-6b2c-4909-887b-c596556a57d3 · outbound

This paper cites Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.673647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfa64e23-ff6f-4080-8c17-09f645d7b7a9 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.776007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b97efb01-1728-4610-80ae-7e6d9588468b · outbound

This paper cites Let's Verify Step by Step.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Let's Verify Step by Step

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.709817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a30feda-1133-4996-9e6a-4a44e8956143 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Understanding R1-Zero-Like Training: A Critical Perspective

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.718213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62d16b3f-c358-4ad9-bb00-e7aea316c439 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.731135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3cc4fa88-61a5-45d0-9cb6-1e5d53304460 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.698844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ae2cffa4-b0ee-4190-b999-3d1af7c1529d · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.662861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation aed165fa-3c4a-49f8-abe4-ed72f216bd7f · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.638082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 44ee03b0-7acc-43d0-9657-d0babdf0db0b · outbound

This paper cites In-Context Impersonation Reveals Large Language Models' Strengths and Biases.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing In-Context Impersonation Reveals Large Language Models' Strengths and Biases

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.770640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4093d75-36ef-42dc-96cd-d50a61f8b70c · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.608262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c6b0815-f2aa-47a1-a6f8-270d2a2cabd7 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.783195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cbbf3be-2b40-4657-96f5-e1f2c4e51961 · outbound

This paper cites FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.791072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dbdf1ae-c941-41d9-a034-df607adbd745 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Solving math word problems with process- and outcome-based feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.803519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e47ca4b6-7375-43c0-bf87-6c68b9fa5cf5 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.544820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 773b2450-6a12-41ba-b2fb-73855c9b8e8c · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Aligning Large Language Models with Human: A Survey

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.828577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e75afa79-432c-4187-8302-5100f73caae7 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.492596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 54e65b5f-c4c0-4e70-bec6-21d6082675fb · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:26:48.464864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 78ed482a-2fba-4c45-9209-706b4b1295e9 · outbound

This paper cites an unresolved cited work.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.848651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c2c94b-f661-427c-b5e3-c7f7a129b54d · outbound

This paper cites Xing, et al.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Xing, et al

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:26:48.412977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 756df110-d73e-46fd-9cc7-8596d7b502eb · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Fine-Tuning Language Models from Human Preferences

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.868491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf8b121a-2f95-46fa-88b6-861b052a1901 · outbound

This paper cites Group Sequence Policy Optimization.

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Group Sequence Policy Optimization

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-14T04:26:47.854069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.