Paper Citation Record · LEDGER

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies

As of 22 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 2 inbound Pith citation observations for arXiv:2512.01970.

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

pith.paper-citation-record.v1
2512.01970 v3

Coverage vector

measured 4 of 4 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T19:07:04.210463Z

measured 6 of 6 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T01:13:11.483599Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-03T20:38:56.026958Z

Reference resolution

4 of 4 outbound references displayed

verified exact0
verified fuzzy0
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 25b11f3f-3d21-4de8-b296-2d65599bc6c5 · outbound

This paper cites write newline.

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T19:07:04.006487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a283426f-01c5-4a6c-adc0-d954a06bc0a7 · outbound

This paper cites @esa (Ref.

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies @esa (Ref

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T19:07:04.106918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65543cbb-cdf0-4a2f-9a43-00b3a29ac7d2 · outbound

This paper cites an unresolved cited work.

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T19:07:04.164507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdc1de4-8710-43c4-92d5-64789f809779 · outbound

This paper cites an unresolved cited work.

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T19:07:04.210463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0428cd94-e17c-42ca-ad2a-d88a0d704612 · inbound

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models cites this paper.

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-28T02:04:12.409186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3f8bbe48-5cf5-4c84-9c98-8a1f6792b6fb · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies

Reference 172

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T20:38:56.028353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.