Paper Citation Record · LEDGER

RL Post-Training Builds Compositional Reasoning Strategies

As of 5 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2607.07646.

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

pith.paper-citation-record.v1
2607.07646 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-09T04:04:13.942267Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

15 of 15 outbound references displayed

verified exact12
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9e5a1bfb-af03-4cbb-aa3e-1ee2e1e513c2 · outbound

This paper cites Reasoning with Exploration: An Entropy Perspective.

RL Post-Training Builds Compositional Reasoning Strategies Reasoning with Exploration: An Entropy Perspective

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T04:05:55.478521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b9b34299-e08b-4ff3-99f0-4fbe54755ddf · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

RL Post-Training Builds Compositional Reasoning Strategies SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T04:05:55.481095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 886e0802-4b12-49da-8643-0c054b72ab5a · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

RL Post-Training Builds Compositional Reasoning Strategies Training Verifiers to Solve Math Word Problems

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.491553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d1161cd2-2b67-4b46-a2a0-96cc8d128ea2 · outbound

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

RL Post-Training Builds Compositional Reasoning Strategies DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.493284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e4c210a0-bc67-4d85-8272-b4298fb9f1cd · outbound

This paper cites Let's Verify Step by Step.

RL Post-Training Builds Compositional Reasoning Strategies Let's Verify Step by Step

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.461276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f5c25b2d-c968-4333-b469-e58d2bcee014 · outbound

This paper cites ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models.

RL Post-Training Builds Compositional Reasoning Strategies ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.490553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a4720dae-dd96-4b8a-a84b-9300af08d97d · outbound

This paper cites Rethinking sample polarity in reinforcement learning with verifiable rewards.

RL Post-Training Builds Compositional Reasoning Strategies Rethinking sample polarity in reinforcement learning with verifiable rewards

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-09T04:05:55.475237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 91d72329-834d-4aa9-85a3-a02ad3547861 · outbound

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

RL Post-Training Builds Compositional Reasoning Strategies Solving math word problems with process- and outcome-based feedback

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.471938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1af94325-0b81-4800-a5d4-2bc2ea721aa8 · outbound

This paper cites Emergent hierarchical reasoning in llms through reinforcement learning.

RL Post-Training Builds Compositional Reasoning Strategies Emergent hierarchical reasoning in llms through reinforcement learning

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-09T04:05:55.484824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2a0565b5-129a-4dc0-886a-f67595930fbc · outbound

This paper cites The invisible leash: Why rlvr may or may not escape its origin.

RL Post-Training Builds Compositional Reasoning Strategies The invisible leash: Why rlvr may or may not escape its origin

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-09T04:05:55.474654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6299d2f4-a2e8-4d50-99c9-9b112124ab68 · outbound

This paper cites A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce.

RL Post-Training Builds Compositional Reasoning Strategies A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.457832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation da7a4ad2-faa1-42e5-942e-73e99f1353fb · outbound

This paper cites arXiv preprint arXiv:2509.25123 , year=.

RL Post-Training Builds Compositional Reasoning Strategies arXiv preprint arXiv:2509.25123 , year=

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-09T04:05:55.478757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 19bbfce2-7ce2-4954-9f7a-bed918ce15fb · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

RL Post-Training Builds Compositional Reasoning Strategies Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.489088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 94236739-64e4-4465-84ec-8c5cb5f8ea07 · outbound

This paper cites STaR: Bootstrapping Reasoning With Reasoning.

RL Post-Training Builds Compositional Reasoning Strategies STaR: Bootstrapping Reasoning With Reasoning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.483803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e419ae80-2f9d-411a-bc8c-2a8f4b32b3d2 · outbound

This paper cites Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining.

RL Post-Training Builds Compositional Reasoning Strategies Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.494223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.