Paper Citation Record · LEDGER

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills

As of 15 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2608.07885.

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

pith.paper-citation-record.v1
2608.07885 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:48:16.749809Z

measured 17 of 17 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 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

17 of 17 outbound references displayed

verified exact0
verified fuzzy2
unresolved14
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3a0d2039-973c-463e-9ad5-67369f8133a6 · outbound

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

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-12T00:48:16.677497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3cbe42e-78ee-4d47-a124-c09e9cb42f2d · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.644972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741a600d-c1e7-45c2-a52f-3dc82bb0b012 · outbound

This paper cites SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.689031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159d5c36-fd7e-42d8-9463-fc481d8e0205 · outbound

This paper cites s1: Simple test-time scaling.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills s1: Simple test-time scaling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.695352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7314c0d-6fb6-4175-a34c-302d43d2d188 · outbound

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

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.700888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfaa7a18-f56a-4c94-8d7b-0903aad2f919 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.711446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5af422-70e1-4731-9786-0692b282588f · outbound

This paper cites $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.729182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc564357-6d6c-415d-af6c-9cf619a5206a · outbound

This paper cites LIMO: Less is More for Reasoning.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills LIMO: Less is More for Reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.734406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10f97529-a5dd-4525-9c44-d41282936bf6 · outbound

This paper cites TextGrad: Automatic "Differentiation" via Text.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills TextGrad: Automatic "Differentiation" via Text

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.739659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df39928-e67a-474c-ab4d-c75f9c060111 · outbound

This paper cites Rules are imperative, concrete, and cite corpus statistics computed by the distiller.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills Rules are imperative, concrete, and cite corpus statistics computed by the distiller

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:48:17.062959Z

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 8cd88abd-ec68-4494-aef5-bfb4a1ec3072 · outbound

This paper cites Before calling find_user_id_by_email or find_user_id_by_name_zip, check that the customer’s message actually contains a real email address, or a real first name + last name + zip.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills Before calling find_user_id_by_email or find_user_id_by_name_zip, check that the customer’s message actually contains a real email address, or a real first name + last name + zip

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:48:17.045341Z

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 9cdedc58-3b07-4296-be41-9bcfdff56a18 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.706050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f26bf447-6316-4e22-87b2-4dfca4107819 · outbound

This paper cites Chain of Draft: Thinking Faster by Writing Less.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills Chain of Draft: Thinking Faster by Writing Less

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.722601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd6782c1-62e7-49d7-8dc0-b3f287705592 · outbound

This paper cites Agent Workflow Memory.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills Agent Workflow Memory

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.716846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1754144d-b303-4b84-b465-fa3da986c2b0 · outbound

This paper cites DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.683371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c64cd75d-eefc-46fc-ab04-7b0c0cd4fcc2 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.672182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d44784-24b8-48fe-be4f-f500e99f9cf6 · outbound

This paper cites GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning.

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-12T00:48:16.622608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.