Paper Citation Record · LEDGER

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks

As of 5 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2605.22205.

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

pith.paper-citation-record.v1
2605.22205 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T05:56:09.398837Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

16 of 16 outbound references displayed

verified exact3
verified fuzzy8
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d013e204-34e8-4a5e-8d48-317290e2c683 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Training Verifiers to Solve Math Word Problems

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T06:01:09.208070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5f0efdcb-cd26-496b-95a3-525fc5c7b614 · outbound

This paper cites D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T06:01:09.213426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dbce427d-703e-4f60-a3c2-b88f1c0cab06 · outbound

This paper cites Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:01:09.203937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3a17784b-6e53-40d8-82e0-27e528f027d3 · outbound

This paper cites FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:01:09.198716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a321c49c-5e1b-418a-a342-ccfe48d336b1 · outbound

This paper cites mention the key- word ‘AI’ at least 3 times.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks mention the key- word ‘AI’ at least 3 times

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.515673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 75ffe3d1-9703-401a-9c47-3edbb0e5b68e · outbound

This paper cites We rescale: X←X· diag(s−1), W←diag(s)·W thus transferring channel-wise quantization difficulty from X to W.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks We rescale: X←X· diag(s−1), W←diag(s)·W thus transferring channel-wise quantization difficulty from X to W

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.558772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 380ffa26-e6a7-46c5-bab4-56aab96ec5d1 · outbound

This paper cites And then apply a second-stage rank-wise smoothing: a appropriate orthogonal rotation matrix Q to dis- perses the energy evenly across dimensions:Arot = AQ, B rot =Q T B.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks And then apply a second-stage rank-wise smoothing: a appropriate orthogonal rotation matrix Q to dis- perses the energy evenly across dimensions:Arot = AQ, B rot =Q T B

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.536066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eacf4854-575b-4172-9ccb-1d9f7f4dd0a6 · outbound

This paper cites an unresolved cited work.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-05-22T06:06:09.527591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1e062d3e-3372-41ae-9219-ab7727145f5e · outbound

This paper cites The output is intermediate result in INT32 format.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks The output is intermediate result in INT32 format

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.531776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1788a308-9912-46bd-ad38-c521244236c6 · outbound

This paper cites This truncated INT8 matrix is then used as input to a second matrix multipli- cation with ˆBsmooth, again using Tensor Core ac- celeration: INT8· ˆBsmooth →INT32.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks This truncated INT8 matrix is then used as input to a second matrix multipli- cation with ˆBsmooth, again using Tensor Core ac- celeration: INT8· ˆBsmooth →INT32

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.549232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 10cc8d0b-c0d7-42a0-a2fb-4efaee1bac46 · outbound

This paper cites an unresolved cited work.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-22T06:06:09.564013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fdde8241-7b1d-4f2b-b69f-3cb99927b4c5 · outbound

This paper cites an unresolved cited work.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-05-22T06:06:09.523437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f4b5d7f9-4da3-479f-95a1-84210c7f2a27 · outbound

This paper cites an unresolved cited work.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-05-22T06:06:09.519536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c48bd97f-a9e4-4906-b7fb-74d879e041ec · outbound

This paper cites Math” skillpack yields higher-quality output than routing to the “Dialogue.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Math” skillpack yields higher-quality output than routing to the “Dialogue

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.554186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2632ec22-91e7-43e2-af92-01626e6aaa5f · outbound

This paper cites There are 1000 milliseconds in 1 second.200 milliseconds / 1000 milliseconds/second = 0.2 seconds.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks There are 1000 milliseconds in 1 second.200 milliseconds / 1000 milliseconds/second = 0.2 seconds

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.540216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 87c5621b-3efe-487d-bfb9-e1d8637a8671 · outbound

This paper cites Backbone.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Backbone

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T06:06:09.544745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

No inbound Pith citation observations are available.